交通出行、仿真、公交、公共交通

The growing demand for integrated and shared mobility services has resulted in a number of public–private partnerships, where public transit agencies and mobility companies collaborate to expand transit service coverage. Nonetheless, many collaborative efforts have failed due to financial restraints and low ridership. The failure of many of the integrated systems can be ascribed to the ineffective pre-implementation evaluation of the integrated system. The lack of a reliable performance evaluation tool capable of assessing the integrated system’s performance prior to implementation could be the case of such failures. Considering this gap, this paper proposes a support tool for decision process of multimodal integrated transport system that examines the viability of an integrated mobility service system comprised of a Fixed Route Transit (FRT) service system and on-demand services. The decision process is powered by an agent-based simulation framework that tests scenarios covering various modal integration strategies. The on-demand services could be Demand Response Transit (DRT) and Transportation Network Company (TNC) services, that particularly act as feeders for FRT to ensure first and last-mile connectivity. This study proposes four integration-strategies with ten potential integration scenarios and four non-integration scenarios, comprising a total of fourteen possible scenarios to complete a trip between any origin–destination pair. Using the agent-based simulation model, various scenarios can be constructed for origin–destination pairs, and based on the generalized system cost, the preferred integration strategy can be selected. The proposed model analyzed the generalized system cost for each scenario by incorporating three key cost components: user cost, agency cost, and external costs. The proposed method was implemented on two different networks, which are the Sioux Falls network and a real-world case study of the Morristown city network in Tennessee, United States. Simulation outcomes indicate that 69% of trips in the Sioux Falls network and 73% of trips in Morristown could be connected to the existing FRT network using feeder services as first and last-mile connectivity solutions. The results suggest that a properly evaluated integrated system could enhance the accessibility of FRT significantly. Therefore, the proposed methodology assesses the advantages of the integrated system prior to its implementation, assisting transit planners and policymakers in the efficient execution of integration strategies and enhancing user experience and mobility.

No abstract available

No abstract available

No abstract available

No abstract available

When electrified transit systems make grid aware choices, improved social welfare is achieved by reducing grid stress, reducing system loss, and minimizing power quality issues. Electrifying transit fleet has numerous challenges like non availability of buses during charging, varying charging costs and so on, that are related the electric grid behavior. However, transit systems do not have access to the information about the co-evolution of the grid's power flow and therefore cannot account for the power grid's needs in its day-to-day operation. In this paper we propose a framework of transportation-grid co-simulation, analyzing the spatio-temporal interaction between the transit operations with electric buses and the power distribution grid. Real-world data for a day's traffic from Chattanooga city's transit system is simulated in SUMO and integrated with a realistic distribution grid simulation (using GridLAB-D) to understand the grid impact due to transit electrification. Charging information is obtained from the transportation simulation to feed into grid simulation to assess the impact of charging. We also discuss the impact to the grid with higher degree of transit electrification that further necessitates such an integrated transportation-grid co-simulation to operate the integrated system optimally. Our future work includes extending the platform for optimizing the charging and trip assignment operations.

In this study, two approaches are presented to account for vehicle circulations when incorporating GTFS data into the agent-based simulation framework MATSim. The first approach directly builds on an existing data converter; the second approach integrates the external public transit planning tool LinTim into MATSim. Both proposed methodological approaches are successfully used to generate transit schedules with vehicle circulations. Simulation experiments are carried out for the Greater Berlin area and reveal an overall minor impact on the public transit performance from the transport users’ perspective. The number of required public transit vehicles is significantly reduced compared to previous version of the GTFS data converter. Reducing the turnaround time leads to a further reduction in vehicles, however, provides reduced slack times to compensate for delays. The implementation of a disruption shows that the bunching phenomenon and delay propagation is now represented by the model. Thus, the proposed methodology allows for a more sophisticated investigation of transit schedules and delay management concepts. c (cid:30) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http: // creativecommons.org / licenses / by-nc-nd / 4.0 / ) Peer-review under responsibility of the Conference Program Chairs.

Traditional fixed-route public transit systems often struggle with inefficiency in suburban areas characterized by low population density and fluctuating demand. This paper presents and validates DynaRyde, a framework for optimizing suburban public transit by integrating dynamic route scheduling with on-demand passenger requests using well-established algorithms. Our approach utilizes the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm to group spatially and temporally proximate ride requests, generating "virtual stops" in real time. Routes are then dynamically computed using a Traveling Salesman Problem (TSP)-like optimization heuristic, incorporating both mandatory transit hubs and virtual stops. We implemented and evaluated the DynaRyde system using the Simulation of Urban MObility (SUMO) traffic simulation environment on a realistic suburban road network under various demand scenarios. Performance was benchmarked against an enhanced fixed-route system and a non-clustering on-demand model. Results demonstrate that our integrated system significantly improves service quality and efficiency, achieving up to a 19% increase in service coverage and a 15–35% reduction in average waiting times compared to a resource-equivalent fixed-route baseline. These findings highlight the substantial potential of integrating on-demand clustering and dynamic routing strategies to create more adaptable and passenger-centric public transit solutions.

The largest on-demand ridepooling (DRT; demand-responsive transport) service in a single European city has officially been part of Hamburg’s public transit system since 2023. Policy makers, practitioners, and planners aim to provide a holistic mobility offering and by doing so, reduce the dependency on private car usage. Against this background, an agent-based simulation is presented and deployed to investigate how various pricing schemes influence the ridership of DRT service, with a particular focus on connections to/from traditional public transit (PT). This involves a novel process that addresses a common problem of service overcrowding while simulating fixed-size DRT fleets with a low mode share in agent-based transport models. The results suggest that a DRT discount for PT season ticket holders significantly increased overall ridership, whereas the number of intermodal trips remained constant. Similar results were observed for PT-quality-dependent pricing schemes, in which DRT was surcharged if parallel PT connections were relatively good, or discounted if they were relatively poor or nonexistent. In contrast, a direct discount for intermodal trips increased the share and the absolute number of intermodal trips, which tended to replace direct DRT trips. Most importantly, the results indicated a tradeoff between operator revenue (or the need for subsidies) and the share of intermodal trips.

ABSTRACT The use of connected and autonomous buses (CABs) is growing, and surface public transit is being transformed into a mixture of manually driven buses (MDBs) and CABs. We aim to establish a hierarchical optimal control model to ensure the efficient operation of CABs in a mixed public transit environment. The first level outputs the planned speed to improve the headway uniformity. Considering the operational uncertainties of MDBs and the output parameters from the first level, the second level minimises the speed changes and the number of CABs entering the node queue and determines the speed control and signal priority schemes. We propose a solution algorithm based on rolling optimisation and establish simulation cases based on the bus lines in Beijing. Compared to both the uncontrolled scheme and the single-speed control scheme, this approach significantly reduces headway deviation and the number of CABs entering the node queue.

Urban public transportation systems are essential for sustainable mobility by mitigating traffic congestion, decreasing fuel consumption, and lowering greenhouse gas emissions. However, route design, scheduling, and passenger load management deficiencies often limit their efficacy. This research introduces a framework powered by Deep Q-Network (DQN) for optimizing metropolitan public transportation systems, utilizing reinforcement learning (RL) to dynamically and efficiently address these challenges. The proposed system incorporates IoT-enabled sensors, including GPS trackers, passenger counters, and traffic flow monitors, to gather real-time data. A DQN algorithm utilizes this data to acquire optimum transit plans via ongoing interaction with the urban environment. The framework emphasizes critical performance criteria, including reducing journey times, enhancing schedule adherence, minimizing operating expenses, and improving passenger happiness. Simulation results demonstrate the framework’s ability to adapt to changing urban conditions and enhance traditional optimization techniques. The system achieves substantial improvements in resource efficiency and ecological sustainability through the strategic rerouting of buses, optimized passenger distribution, and real-time schedule adjustments. This research highlights the potential of deep RL to revolutionize urban transportation systems into more intelligent, efficient, and environmentally sustainable networks. Future research will investigate the incorporation of multi-agent systems to address scalability and multimodal transportation challenges.

In this paper, we present a simulation modeling framework that can accommodate multiple classes of travelers and integrates several distinct features, which in turn can be associated with each of the traveler classes, thus providing flexibility and a so-called bird’s-eye view to any potential user. Concretely, we integrate into the multi-class region-based dynamic traffic model, called multi-class Network Transmission Model (McNTM), several features, including a public transit diversion component, as well as routing methods associated with different traveler classes. Three distinct traveler classes are defined, the 1st class of travelers equipped with autonomous vehicles, the 2nd traveler class comprising of RGIS-equipped, conventional vehicles and the 3rd traveler class comprising of unequipped, conventional vehicles. Certain assumptions are made for each traveler class. The gain in overall performance for the case where 1st and 2nd class travelers are present in the system, ranges from 0.78% - 23.43%. Region-based routing methods employed by the 1st and 2nd class respectively, not only benefit overall network performance, but with their respective market penetration rates exceeding certain thresholds, can prove beneficial to the individual performance of other traveler classes.

We simulate the introduction of shared, automated, and electric vehicles (SAEVs) providing on-demand shuttles service in a large-scale transport digital twin of the San Francisco Bay Area region (California, USA) based on transit supply and demand data, and using the mesoscopic agent-based Behavior, Energy, Autonomy, and Mobility beta software (BEAM) developed at the Lawrence Berkeley National Laboratory (LBNL). The main goal of this study is to test the operations of this novel mobility service integrated with existing fixed-route public transportation service in a mesoscopic simulation of a real case scenario, while testing the BEAM beta software capabilities. In particular, we test the introduction of fleets of on-demand vehicles bound to operate within circular catchment areas centered on high-frequency transit stops, with the purpose of extending the reach of fixed-route transit by providing an alternative first- and last-mile connection at high-frequency public transport stations. Results show that on-demand automated shuttles represent the best solution for some users, increasing the overall transit ridership by 3%, and replacing mostly ride-hail trips, especially those connecting to transit stops, but also some walking trips. This type of service has the potential to reduce overall vehicle miles traveled (VMT), increase transit accessibility, and save energy, but future research is needed to optimize this type of service and make it more attractive to travelers.

Transit systems have encountered a radical change in the recent past as a result of the digital disruption. Consequently, traditional public transit systems no longer satisfy the diversified demands of passengers and hence, have been complemented by demand responsive transit solutions. However, we identify a lack of simulation tools developed to test and validate complex scenarios for real-time demand responsive public transit. Thus, in this paper, we propose a simulation framework, which combines complex scenario creation, optimization algorithm execution and result visualization using SUMO, an open source continuous simulator. In comparison to a state-of-the-art work, the proposed tool supports features such as varying vehicle capacity and driving range, immediate and advance passenger requests and maximum travel time constraints. Further, the framework follows a modular architecture that allows plug-and-play support for external modules.

This study develops and applies a forecasting–simulation model for transport organization based on the Transit-Oriented Development (TOD) approach in the vicinity of railway stations. Grounded in an assessment of the current state of transport organization, the research integrates a macro-level travel demand forecasting model with a micro-level simulation to evaluate the effectiveness of TOD-based transport planning scenarios at urban rail and high-speed rail stations, with Thao Dien Station selected as a representative case study. The study formulates three simulation scenarios: (i) the 2025 baseline (current conditions), (ii) the year 2030 without TOD implementation, and (iii) the year 2030 with TOD-based transport planning. The application of TOD demonstrates improvements in the overall transport system by redistributing traffic flows, increasing public transit usage, and reducing trips made by private vehicles.

Excessive fluctuations in travel time between stops and demand at bus stops during bus operations can lead to operational instability in bus systems, such as bus bunching. To tackle this issue, this paper presents a dynamic bus holding control strategy leveraging multi-agent reinforcement learning to stabilize bus system operations and prevent bus bunching. First, bus motion system is constructed, and the rules for bus operation and passenger behavior are defined. Then, agent-based transit operation management is established, the elements of the multi-agent reinforcement learning framework are outlined, and a centralized training and decentralized execution method is proposed. Additionally, an event-driven simulation environment is developed for training and testing the agents. Finally, extensive numerical simulations are conducted to evaluate the proposed method against baseline approaches using various performance metrics. The results demonstrate that the proposed method effectively captures the dynamics of the bus system and accounts for the long-term impacts of current decisions, resulting in the most balanced bus trajectories, optimal passenger load distribution, and minimal total holding time.

Limited-stop service represents a paradigm for enhancing efficiency in transportation systems, with applications spanning public transit, logistics, and supply chain management. This service model operates along a designated route featuring a reduced number of stops in comparison to standard services, thereby facilitating expedited transportation. In this research, we utilize accumulated data from Intelligent Transportation Systems for the development and deployment of a simulation-driven framework tailored towards augmenting the operational efficiency of limited-stop services. To illustrate the practical application of this framework, we focus on the paradigm of limited-stop bus services, elucidating the intricate technical facets of the proposed system. The efficacy and viability of this framework have been validated through a series of empirical investigations conducted within the urban bus transit network of Shenzhen, a prominent metropolis situated in China.

By facilitating public buses' movement through traffic signal-controlled intersections, a Transit Signal Priority (TSP) strategy can contribute to the reduction of queuing time at intersections. However, the traditional TSP has a negative impact on non-prioritized movements and other transport modes. This research proposes new TSP strategies that also seek to optimize other performance measure such as the person-delay at an isolated intersection and along a corridor. This research focused on major arterials as well as on minor arterial roads, whereas the majority of the existing studies addressed only the major arterial approach. As part of this research, the bus schedule was also taken into consideration. The proposed method is described in detail and is implemented on an arterial corridor in VISSIM. The study area simulation results indicated that the proposed TSP methods performed better than the conventional TSP.

Many cities in the world have implemented Bus Rapid Transit (BRT) systems as a part of their public transportation networks. BRT systems are highly efficient and relatively low cost when compared to rail-based systems. In Colombia, BRT systems are the main public transportation solution in many cities such as Bogotá, Cali, Barranquilla or Pereira. One of the major challenges in BRT systems is the formation of bus queues at busy stations, which reduces the performance of the entire system. The modeling of these queues is challenging as they arise from the complex interaction between the station’s geometry, the service frequencies and the passenger demand. In this paper, we present a complete microsimulation framework for the Megabus BRT system in Pereira based on cellular automata. The simulation introduces two kinds of agents: buses and passengers, and they interact to reproduce realistic behavior. Our results show that the simulation can reproduce queues formation and delays arising from the interaction between buses and with traffic lights. Our framework allows the evaluation of different service frequency schemes from the operator’s and the passenger’s point of view, which makes it a suitable tool to solve the frequency optimization problem successfully accounting for bus delays.

Demand responsive transit (DRT) can provide an alternative to private cars and complement existing public transport services. However, the successful implementation of DRT services remains a challenge as both researchers and policy makers can struggle to determine what sorts of places or cities are suitable for it. Research into car-dependent cities with poor transit accessibility is sparse. This study addresses this problem, investigating the potential of DRT service in Wayne County, U.S.A., whose dominant travel mode is private car. Using an agent-based approach, DRT is simulated as a new mobility option for this region, thereby providing insights into its impact on operational, user, and system-level performance indicators. DRT scenarios are tested for different fleet sizes, vehicle occupancy, and cost policies. The results show that a DRT service in Wayne County has a certain potential, especially to increase the mobility of lower-income individuals. However, introducing the service may slightly increase the overall vehicle kilometers traveled. Specific changes in service characteristics, like service area, pricing structure, or preemptive relocation of vehicles, might be needed to fully realize the potential of pooling riders in the proposed DRT service. The authors hope that this study serves as a starting point for understanding the impacts and potential benefits of DRT in Wayne County and similar low-density and car-dependent urban areas, as well as the service parameters needed for its successful implementation.

When there are significant service disruptions in public transit systems, passengers usually need guidance to find alternative paths. This paper proposes a path recommendation model to mitigate congestion during public transit disruptions. Passengers with different origins, destinations, and departure times are recommended with different paths such that the system travel time is minimized. We model the path recommendation problem as an optimal flow problem with uncertain demand information. To tackle the lack of analytical formulation of travel times due to capacity constraints, we propose a simulation-based first-order approximation to transform the original problem into a linear program. Uncertainties in demand are modeled using robust optimization to protect the path recommendation strategies against inaccurate estimates. A real-world rail disruption scenario in the Chicago Transit Authority (CTA) system is used as a case study. Results show that even without considering uncertainty, the nominal model can reduce the system travel time by 9.1% (compared to the status quo), and outperforms the benchmark capacity-based path recommendation. The average travel time of passengers in the incident line (i.e., passengers receiving recommendations) is reduced more (-20.6% compared to the status quo). After incorporating the demand uncertainty, the robust model can further reduce system travel times. The best robust model can decrease the average travel time of incident-line passengers by 2.91% compared to the nominal model. The improvement of robust models is more prominent when the actual demand pattern is close to the worst-case demand.

Public transport network design deals with finding efficient network solution(s) from a set of alternatives that best satisfies the often-conflicting objectives of stakeholders like passengers and operators. This work presents a simulation-based optimization (SBO) model for designing public transport networks. The work’s novelty is in developing such a network design model that fully accounts for the stochastic behavior of commuters on the transit network. The SBO discipline solves decision-based problems like the transit network design problem (TNDP) by combining simulation and optimization models. The proposed model integrates a disaggregated activity-based travel demand simulation with a multi-objective network optimization algorithm. Trip-based travel demand models are commonly used to represent traveler behavior in the literature. The approach limits its ability to accommodate the stochastic realities of traveler behavior in a transit network design solution. Using activity-based simulation instead makes it possible to account for a more realistic traveler behavior, especially real-time decisions made in response to changing network dynamics which ultimately affect the distribution of demand over time on the network. The proposed model is applied to the improved design of the integrated public transport network in the City of Cape Town, South Africa. The results show SBO can design efficient network solutions that reflect the objectives of network stakeholders.

COVID-19 has raised new challenges for transportation in the post-pandemic era. The social distancing requirement, with the aim of reducing contact risk in public transit, could exacerbate traffic congestion and emissions. We propose a simulation tool to evaluate the trade-offs between traffic congestion, emissions, and policies impacting travel behavior to mitigate the spread of COVID-19 including social distancing and working from home. Open-source agent-based simulation models are used to evaluate the transportation system usage for the case study of New York City. A Post Processing Software for Air Quality (PPS-AQ) estimation is used to evaluate the air quality impacts. Finally, system-wide contact exposure on the subway is estimated from the traffic simulation output. The social distancing requirement in public transit is found to be effective in reducing contact exposure, but it has negative congestion and emission impacts on Manhattan and neighborhoods at transit and commercial hubs. While telework can reduce congestion and emissions citywide, in Manhattan the negative impacts are higher due to behavioral inertia and social distancing. The findings suggest that contact exposure to COVID-19 on subways is relatively low, especially if social distancing practices are followed. The proposed integrated traffic simulation models and air quality estimation model can help policymakers evaluate the impact of policies on traffic congestion and emissions as well as identifying hot spots, both temporally and spatially.

No abstract available

Mobility is an indispensable part of modern human societies, but the dominance of motorized individual traffic (MIV, i.e., the private car) leads to a prohibitive waste of energy as well as other resources. Here we show that by combining a line service (e.g., railway) system with a fleet of ride-pooling shuttles connecting line stops to desired pick-up and drop-off points, a bi-modal public transport system may result which provides on-demand door-to-door service at a service level (in terms of transit times) superior to current public transport, and with an overall comfort level comparable to MIV. We identify the conflicting objectives for optimization, i.e., user convenience and energy consumption, and evaluate the system performance in terms of Pareto fronts. By means of simulation and analytical theory, we find that energy consumption can be as low as 20% of MIV, at line service densities typically found in real settings. Surprisingly, we find favorable performance not only in urban, but also in rural settings.

Driven by increasing urbanization and traffic congestion challenges, efficient and cost‐effective public transportation solutions have become essential, positioning bus rapid transit (BRT) systems as an attractive alternative to conventional modes. This study presents a comprehensive discrete‐event simulation (DES) model developed to optimize scheduling in BRT systems, focusing on the recently implemented BRT line in Amman, Jordan. The model integrates real‐world operational constraints—including dynamic passenger arrivals modeled as Poisson processes, boarding and alighting behaviors, and signaling for departures—with detailed representations of both peak and off‐peak conditions. By generating multiple what‐if scenarios, the simulation investigates critical trade‐offs between minimizing passenger waiting times and maximizing fleet utilization, demonstrating that under the current publicly funded model, reducing the number of buses during off‐peak hours effectively lowers operational costs while maintaining service quality. Furthermore, the flexibility of the simulation framework permits adaptation to alternative funding models, where increased off‐peak frequencies may be prioritized to enhance ridership. Validated against empirical operational data, the model serves as a robust decision‐support tool that provides valuable insights for urban planners and transit operators seeking to improve resource allocation and service design in modern urban transit systems.

Public transport is a travel mode that plays an essential role in the transportation system to alleviate congestion and reduce carbon emissions in urban networks. Recently, introducing a new travel mode requires route adjustment in the existing public transport system. Route adjustment of public transport has become an important policy task for the efficiency of the urban transportation system. This study develops the TRIPS (Travel Record based Integrated Public transport operation System) program to evaluate the effect of public transport route adjustment. An optimization-based travel assignment model using generalized costs is established to analyze the travel patterns of public transport users. This study employs smartcard and GIS data to identify public transport travel behaviors. A travel pattern-based analysis compares the travel demand for the existing and the adjusted public transit routes. We quantitatively analyze the travel volume and revenue changes for each transit line after adjusting public transit routes. It is expected to analyze the policy improvement effects of introducing new travel modes in the future.

No abstract available

With advances in emerging technologies, options for operating public transit services have broadened from conventional fixed-route service through semi-flexible service to on-demand microtransit. Nevertheless, guidelines for deciding between these services remain limited in the real implementation. An open-source simulation sandbox is developed that can compare state-of-the-practice methods for evaluating between the different types of public transit operations. For the case of the semi-flexible service, the Mobility Allowance Shuttle Transit (MAST) system is extended to include passenger deviations. A case study demonstrates the sandbox to evaluate and existing B63 bus route in Brooklyn, NY and compares its performance with the four other system designs spanning across the three service types for three different demand scenarios.

Public-transit systems face a number of operational challenges: (a) changing ridership patterns requiring optimization of fixed line services, (b) optimizing vehicle-to-trip assignments to reduce maintenance and operation codes, and (c) ensuring equitable and fair coverage to areas with low ridership. Optimizing these objectives presents a hard computational problem due to the size and complexity of the decision space. State-of-the-art methods formulate these problems as variants of the vehicle routing problem and use data-driven heuristics for optimizing the procedures. However, the evaluation and training of these algorithms require large datasets that provide realistic coverage of various operational uncertainties. This paper presents a dynamic simulation platform, called TRANSIT-GYM, that can bridge this gap by providing the ability to simulate scenarios, focusing on variation of demand models, variations of route networks, and variations of vehicle-to-trip assignments. The central contribution of this work is a domain-specific language and associated experimentation tool-chain and infrastructure to enable subject-matter experts to intuitively specify, simulate, and analyze large-scale transit scenarios and their parametric variations. Of particular significance is an integrated microscopic energy consumption model that also helps to analyze the energy cost of various transit decisions made by the transportation agency of a city.

Modelling the within-day dynamic of passenger flows is crucial to optimize the service quality of public transport systems when supporting real-time operations and providing predictive information, as well as for off-line planning. Recurrent and non-recurrent congestion phenomena are increasingly affecting densely connected transit networks. In particular, the measures adopted to contain the spread of the COVID-19 pandemic affect significantly public transport capacity. Therefore, transit operators require a tool that can quickly forecast real- time capacity issues in the transit system to perform service recovery (e.g. introducing new runs) and to inform passengers about crowding at stops (e.g. through real-time information panels or trip planners). This research proposes an innovative congested run-based macroscopic dynamic assignment model, which simulates service degradation for passengers mingling at stops and strict capacity constraints. Fail-to-board probabilities are introduced at the diversion nodes of a diachronic hypergraph to represent service performances and passenger volumes on each run, in the framework of an implicit route enumeration model. This last aspect, jointly with the careful containment of the space- time network dimension, makes the model suitable for real-time applications in terms of computation time.

Stop‐level ridership data serve as a basis for various studies toward increasing bus patronage and promoting sustainable land use planning. To address limitations found in previous studies, this study proposes a novel approach based on Geographically Weighted Principal Component Analysis (GWPCA) and Ordinary Kriging to predict the stop‐level boarding or alighting data along bus lines in São Paulo (Brazil), considering four different sampling methods. The main contributions are as follows: by accounting for the spatial heterogeneity of the predictor dataset, the GWPCA can identify the most important factor affecting transit ridership even in bus stops with no information on boarding and alighting; the spatial modeling of stop‐level ridership data using GWPCA components as explanatory variables allows visualizing the spatially varying effects from predictors on ridership, supporting the land use planning at a local level; GWPCA coupled with kriging simultaneously addresses the multicollinearity of predictor data, its spatial heterogeneity, and the spatial dependence of the stop‐level ridership variable, thus enhancing the goodness‐of‐fit measures of the transit ridership prediction in unsampled stops; and a balanced sample on predictor data and well‐spread in the geographic space might be preferred to accurately estimate missing stop‐level ridership data. In addition to solve the lack of stop‐level ridership data, supporting a reliable bus system planning, the proposed method indicates what predictors should be addressed by policymakers to stimulate a transit‐oriented development. The method can be successfully applied to other travel demand variables facing a lack of data such as traffic volume in road segments and mode choice at the household level.

No abstract available

As travel demand becomes more diversified and personalized, traditional bus operation struggles to meet the requirements of high-quality service. The customized bus (CB), with its flexibility, has garnered significant attention. However, optimizing CB lines involves multiple decision variables. As the scale of transportation networks continues to expand, traditional methods struggle to find the optimal solution within a limited time. In this article, we propose an innovative CB line optimization model and an efficient solving algorithm. In terms of modeling, we aim to maximize the number of passengers served by jointly optimizing bus routes, stop locations, departure time, and service capacity, while considering various constraints such as tolerance time to ensure the service efficiency of CBs. Since the problem is intractable by exhaustive search, we design a column generation-based algorithm to acquire the optimal solution efficiently. We compare the proposed algorithm with direct solving using the Gurobi solver in small-scale, medium-scale, and large-scale scenarios. The experimental results show that the proposed algorithm can effectively find the optimal solution, even in a large-scale scenario where the Gurobi solver fails to deliver a solution.

India's burgeoning population has led to an increased demand for transportation services, particularly in urban areas. To address the growing mobility needs and mitigate the adverse effects of personal vehicle usage, efficient public transit services are imperative. Several Indian cities have implemented bus rapid transit (BRT) systems to address this problem, but ridership for the majority of the BRT systems remains below breakeven (this refers to the point at which the revenue generated from ridership equals or surpasses the costs associated with operating and maintaining the transportation system). Thus, it is necessary to assess the determinants of commuter satisfaction with BRT. The present study aims to examine factors affecting travel satisfaction among BRT commuters. By using structural equation modeling (SEM), the effect of demographic (age and gender) and travel-related variables (fare price, travel time, trip frequency, reliability, ease of using bus service, and comfort level) on BRT commuters' satisfaction and usage of BRT services were analyzed. It was found that while ease of using the service, comfort level, and reliability positively affect BRT travel satisfaction, trip frequency is significantly affected by the ease of using the service only. Furthermore, demographic variables (age, and gender of respondents) were not found to have significant effect of travel satisfaction and trip frequency. The findings from this can study serve as a base for policymakers, city officials, and urban planners to identify commuters' priorities for a well-functioning BRT in India and formulate policies to attract riders by enhancing their preferences.

The development of multi-mode transportation systems, e.g., bus, metro, taxi, and bike-sharing, presents a fundamental challenge in forecasting demand across heterogeneous, noisy, and complexly interacting data streams. From a feature modeling perspective, this requires a shift from simple data fusion to a more principled approach. This paper introduces a novel end-to-end framework, Multi-mode Spatiotemporal Adaptive Fusion Network (MSTAFN), that systematically addresses this challenge through a two-stage process: 1) unsupervised shared feature selection, and 2) dynamic asymmetric feature interaction modeling. For the first stage, we design an Infomax module that employs an information-theoretic principle to obtain a clean low-dimensional shared latent representation from cross-mode data. This representation captures the underlying semantic drivers of demand, such as latent commuting patterns, while mitigating noise and redundancy. For the second stage, we propose a Multi-Flashback module to explicitly model the complex asymmetric interactions between heterogeneous features, particularly across different temporal granularities. Its Cross-Flashback mechanism is designed to allow low-frequency modes (e.g., metro) to be informed by the latest fine-grained dynamics of high-frequency modes (e.g., bike-sharing). Experiments on a large-scale real-world dataset from New York City demonstrate that our two-stage paradigm outperforms state-of-the-art baselines, especially on the mode with the coarsest time granularity. This validates the superiority of our proposed modeling framework, supporting the improvement of operational efficiency for multi-mode transportation systems.

The staggered work hours (SWH) policy is a practical strategy for managing travel demand, aiming to spread out the temporal distribution of travel volume by adjusting the schedules of travelers’ activities. The influence of the SWH policy on the commuting patterns of passengers using bus transit is not yet clear. We addressed this issue in a many-to-one bus line, treating commuters as Q-learning agents learning to minimize regrets by selecting appropriate bus runs. The learning outcomes reveal a SWH-induced equilibrium, where commuters departing from the same station with the same work start time experience identical minimal commuting costs, regardless of the chosen bus. Subsequently, we investigate the effectiveness of SWH policy by manipulating two key control variables: the division of travel demand between two categories of travelers and the staggered time interval. The results confirm that congestion during peak hours can potentially be mitigated by carefully selecting the above two key parameters. Correspondingly, we provide optimal control boundaries for these two parameters to design an effective SWH policy. Furthermore, we explore the combined impact of physical distancing and SWH policy on traffic flow patterns during an epidemic outbreak. Concurrently, we assess the infection risk through a surrogate index, revealing that the SWH policy has a positive effect in mitigating the risk of contact exposure.

No abstract available

For metropolises like Beijing, heavy congestions cause transit passengers’ unreliable travel time, including in vehicle time and waiting time. Comparing with other managerial measures, designing a lane for bus use only is an effective method to improve travel reliability, for it can eliminate the influence on bus-driving conditions. This paper proposes a reliable and practical method to determine exclusive bus lanes (EBL). A reliability-based optimization model is established, in which the tradeoff among bus and private car passengers’ travel time, reliability, and EBL construction cost are considered. Based on the actual network, a user equilibrium demand assignment model is applied to estimate the dynamic bus flow distribution. Since the model is nonlinear, a two-step method is proposed where tangent lines are introduced to constitute an envelope curve to linearize the model. This work conducts the statistical modeling and fitting analysis with actual bus trajectory data, collected on EBL in Beijing during peak hours. Passenger travel time distributions are fitted to estimate the statistical passenger travel time; Lognormal distribution and Gaussian distribution are the best fit. The optimization results indicate that the passenger travel time reliability can be improved by 5.5% by the optimized EBL location scheme. This study will provide a theoretical basis and methodological support for improving the service level of the public transportation system in large cities through the scientific planning of exclusive bus lanes.

No abstract available

No abstract available

No abstract available

In many moderately sized European cities, the public transport systems based on trams and buses are operating at their capacity limits. Ropeways have proved to be a suitable transit extension in several Latin American cities. Few travel demand models attempt to forecast the impact of urban ropeways. So far, all of these models do not consider the specific properties of a ropeway. This paper seeks to estimate a mode choice model that includes a ropeway as a separate transport system. Relative to bus operation in European cities, ropeways promise improved timetable keeping, with fewer delays at the start because of high service rates, and they also offer improved passenger comfort with higher capacities. These benefits must be reflected in the travel demand model by mode-specific parameter settings that are estimated based on a survey. A stated choice experiment was conducted, in which respondents compared realistic trip situations using a ropeway with traditional urban transport modes, with aspects including access and egress time, waiting time, travel time, travel costs, reliability, and crowding. The situations of choice were selected from observed trip data to be as realistic as possible. Using a mixed logit (ML) model, the parameter estimation indicates that crowding and reliability as well as the personal attitude of potential users have a statistically significant influence on the choice behavior of people in Graz, a moderately sized city in Austria.

No abstract available

Shuttle buses have been a popular means to move commuters sharing similar origins and destinations during periods of high travel demand. However, planning and deploying reasonable, customized service bus systems becomes challenging when the commute demand is rather dynamic. It is difficult, if not impossible to form a reliable, unbiased estimation of user needs in such a case using traditional modeling methods. We propose a visual analytics approach to facilitating assessment of actual, varying travel demands and planning of night customized shuttle systems. A preliminary case study verifies the efficacy of our approach.

The paper aims to assess bus accessibility considering the matching between supply and demand for effectively optimizing the level and fairness of urban public transport service, which realizes the quantification of regional balance and accurate positioning the area with the worst balance. We firstly employ hotspot detection procedure based on taxi trajectory data and kernel density analysis to identify the travel sensitive areas, the heat values of which are deployed to represent travel demand spatial-temporally and evaluate weight factors for bus accessibility modeling. Matter-element theory is selected to establish multi-parameter evaluation model of bus accessibility, which has potential for solving incompatibility problems by systematically considering all factors. The correlations between accessibility indexes and heat value are deployed to evaluate weight factors rather than analytic hierarchy process or expert assessment method to improve subjectivity and dynamic updating. An index called the Level Ratio of Accessibility to Demand (LRAD) is addressed finally to quantify the balance between accessibility supply and travel demand of travel sensitive areas, which identifies the regional imbalance to assist the public transport system assignment. Xi’an, a large city, is selected as a case study for methodology verification. Bus accessibility degree of the whole city as well as its travel sensitive areas is evaluated by the matter-element model. It is found the bus transport accessibility of Xi’an is moderate level $(M_{3})$ . The LRAD results identify the priority-processing area with the poor balance between accessibility supply and travel demand, which is cross referenced with local urban plans for verification.

No abstract available

As urbanization accelerates and populations grow, urban public transportation systems face unprecedented challenges. As a tourist and transportation hub city, Guilin experiences significant fluctuations in travel demand, and traditional scheduling and planning methods are no longer sufficient to meet the complex and dynamic transportation needs. By leveraging transportation big data and intelligent analysis technologies, this study utilized the NetworkX framework to construct a public transportation network model for Guilin City, and conducted a systematic analysis of network topology characteristics and data mining. By integrating multi-source data such as bus GPS trajectories, passenger card swipe records, and road traffic flow, data quality and consistency were ensured to achieve precise modeling. Based on the definition of node and edge attributes, this study conducted an in-depth analysis of key indicators such as node centrality, connectivity, shortest paths, and community structure, revealing the potential patterns and bottlenecks of the transportation network. At the same time, clustering analysis, association rule mining, and predictive modeling techniques were used to identify passenger travel patterns and transfer characteristics, and to detect potential abnormal behaviors. The research results indicate that complex network analysis can effectively identify system weaknesses and potential congestion risks, providing scientific basis for public transportation route optimization, transfer system design, and resource allocation. Through experimental verification and visualization analysis, this method demonstrates significant advantages in improving traffic operation efficiency, enhancing passenger experience, and promoting sustainable development, laying a solid foundation for the construction of an intelligent, efficient, green, and low-carbon urban transportation system.

No abstract available

Urban mobility is increasingly complex due to population growth, environmental concerns, and the diversification of transport needs. This paper proposes an optimized multimodal route planning adapted for urban transportation systems. By integrating various modes of transport, such as metro, bus, and taxi, into a unified planning framework, the proposed approach addresses the rising demand for sustainable, efficient, and user-centric mobility solutions. The model accounts for multiple conflicting objectives, including minimizing travel time and cost, as well as reducing carbon emissions within specified constraints. Unlike traditional single-mode or single-objective strategies, this model provides a flexible and scalable foundation to support intelligent decision-making in real-time urban environments. Through the accurate modeling of urban transport networks and the application of multi-objective optimization methods, the study aims to enhance resource utilization and support the development of smarter and more sustainable cities. Experimental results demonstrate the model’s capability to generate optimized, feasible routes that balance system-level efficiency with individual user preferences.

Urbanization places greater demand on the link between downtown areas and suburbs, due to commuters’ long-distance and diverse trips. As an emerging form of park-and-ride (PNR) services, remote PNR (RPR) facilities have proved to be more economical and environmentally friendly, allowing travelers to park in a suburban area and travel to a rail station via bus. In this regard, a generalized simulation-based bilevel model for optimizing the locations and capacities of RPR facilities is developed in this article. A hybrid algorithm integrating Bayesian optimization, branch and bound, and trust region sequential quadratic programming is proposed to achieve an optimal solution. The proposed integrated method balances the desired efficiency and accuracy through the combination of machine learning-based technology and mathematical optimization methodology. The validity of the proposed model is tested on a large-scale real-world transportation network in Halle, Germany. Modeling and analyzing RPR schemes using the proposed framework may provide new insights into improving social welfare.

No abstract available

This research identifies the needs and initial design of the development of Access Road Mode Public Transportation (Bus) West Java International Airport. To obtain recommendations for the development of public transport access (Bus) that are integrated with regional development plans / other infrastructure in order to increase airport utilization. In general, there are several main tasks to be carried out in the Bus/Shuttle Development Study at West Java International Airport, as follows Spatial Analysis, Airport Demand Analysis, Road Geometric Analysis, Public Transport Modeling, Public Transport Analysis, and Financial and Economic Analysis. From analysis, 5 priority bus routes were selected and proposed to improve airport airport utility by analyzing the route, demand, operational schedule, headway, fare, mode capacity, travel frequency, number of buses, and investment costs. Priority routes include Cipaku Terminal, DAMRI Pool Kebun Kawung, Leuwi Panjang Terminal, Curug Agung Terminal, and Harja Mukti Terminal to and from West Java International Airport.

No abstract available

No abstract available

Demand modeling is an important part of the setup of a traffic model for a city. All travel demand models rely on land use data as the demand for traveling fundamentally stems from activities occurring at different locations; however, many cities lack these data, or experience in estimating travel demand in their region. In response, this study develops a methodology for generating highly detailed land use data in the form of points of interest (POIs) specifically aimed at travel demand estimation purposes. The framework includes a procedure to extract, clean, enhance, and categorize freely available land use data from OpenStreetMap (OSM) into different POI categories, such as residences, schools, and shops. These residential and activity POIs, which are typical origins and/or destinations of trips, serve as the starting point for estimating travel demand. This paper demonstrates the framework’s utility through three case studies across different cities in Belgium. It validates the effectiveness of OSM-derived POIs for travel demand estimation by replicating Antwerp’s existing demand model, examines the POIs classification’s suitability for various travel demand purposes in Leuven, and assesses the transferability of correlations between OSM data and travel demand from Antwerp to Ghent. Beyond the applications illustrated in this paper, the framework provides opportunities for future research on the consistent disaggregation of existing zonal demand estimates and design-based research in which future demand is estimated given the development of POIs. The framework is openly available as a Python tool called Poidpy.

No abstract available

Abstract. Problem. Modern urban public transport systems face the challenge of ensuring schedule adherence and improving the efficiency of bus operations, particularly under conditions of variable traffic and complex infrastructure. A key issue remains the insufficient accuracy of forecasting bus travel time on individual route segments, even with the implementation of dedicated lanes. This necessitates the development of analytical tools that take into account the impact of both external and organizational factors on bus speed patterns. Goal. The objective of this study is to develop a set of analytical models for determining the temporal parameters of bus movement on segments of urban routes, considering the features of dedicated public transport lanes and characteristic traffic patterns. Methodology. The study is based on field observations of bus movement on the route, using the mobile application GalileoGPS Speedometer. A detailed analysis of changes in speed was conducted, leading to the identification of typical operating conditions on route segments. The conditions were classified into 6 levels of movement convenience, reflecting the interaction between the bus and the surrounding traffic environment. Based on the data collected, analytical dependencies were formulated to describe the travel time under varying conditions. Results. The developed analytical models account for speed variability and movement convenience levels, enabling precise modeling of bus travel times on different route segments. The models consider both delays and schedule advancements. Six typical interaction scenarios between buses and the traffic environment were identified, allowing for accurate predictions of speed changes and arrival times at stops. Originality. The scientific novelty of the study lies in the systematic and analytical description of bus movement regimes with a focus on dedicated lane operation. A new approach is proposed for classifying bus movement convenience levels based on objective environmental parameters, enhancing the accuracy of arrival time prediction and enabling the development of adaptive schedules. Practical value. The proposed models can be integrated into intelligent transportation systems to improve timetable accuracy, facilitate the creation of adaptive schedules, and optimize route planning. Their implementation enhances the reliability and stability of public transport operations, which is particularly relevant for large cities with high mobility demands.

No abstract available

Abstract The accurate prediction of travel demand by bus is crucial for effective urban mobility demand management. However, most models of travel demand prediction by bus tend to focus on the bus’s spatiotemporal dependencies, while ignoring the interactions between buses and other transportation modes, such as metros and taxis. We propose a Multiview Spatiotemporal Graph Neural Network (MSTGNN) model to predict short-term travel demand by bus. It emphasizes the ability to capture the interaction dependencies among the travel demand of buses, metros, and taxis. Firstly, a multiview graph consisting of bus, metro, and taxi views is constructed, with each view containing both a local and global graph. Secondly, a multiview attention-based temporal graph convolution module is developed to capture spatiotemporal and cross-view interaction dependencies among different transport modes. Especially, to address the uneven spatial distributions of features in multiview learning, the cross-view spatial feature consistency loss is introduced as an auxiliary loss. Finally, we conduct intensive experiments using a real-world dataset from Shenzhen, China. The results demonstrate that our proposed MSTGNN model performs better than the existing models. Ablation experiments validate the contributions of various modes of transportation to the improvement of the model’s performance.

ABSTRACT Pre-peak fare discount policies have become increasingly common in urban transit services and show potential to spread morning peak-hour demand. This study analyzes the departure time choice behavior of interregional bus passengers during morning hours. A mixed logit model is applied to estimate the probability of shifting departure time as a function of fare discount rate, in-vehicle congestion, and other influential factors, accommodating heterogeneity of passenger preferences. The analysis data are obtained through a stated preference survey, which is conducted to passengers who regularly use the interregional bus in Seoul metropolitan area. Choice models are segmented by departure time periods (peak, pre-peak, and post-peak) and occupation types (fixed time worker, flexible time worker, and student). Marginal utilities of the unobserved preferences are estimated to suggest policy implications. From the experimental analysis, target passengers for shifting departure time during peak hour are suggested as flexible time workers and students.

ABSTRACT Customized bus (CB) travel services present a promising solution for urban transportation, blending the convenience of private cars with the cost efficiency of public transit. This study proposes a comprehensive CB service system for urban commuting, optimizing both station locations and scheduling strategies. First, K-means clustering algorithm is applied to determine bus station locations based on the spatical distribution of commuting demand. The bus routing problem is then formulated as a mixed-integer nonlinear programming (MINLP) model, considering both system costs and passenger waiting times. To efficiently solve the MINLP model in urban scenarios, an adaptive large-scale neighborhood search (ALNS) algorithm is employed. Finally, the proposed system is validated using real-world data. Results indicate that the CB service notably reduces average passenger waiting time and vehicle travel time compared to traditional taxi services, while also achieving over a 30% reduction in operating costs.

Nowadays, urban traffic congestion is a serious issue, and the rise of demand responsive transit systems improves this problem to a certain extent. This paper delves into the route optimization, scheduling, and modeling of demand-responsive transit, exploring its seamless integration into urban transportation planning. This bus system aims to improve the efficiency of the transportation system, reduce congestion, and improve the urban environment, thus enhancing the quality of life of the residents. This study reveals the potential benefits of a demand responsive transit system in urban transportation planning, offering the possibility of increased flexibility and efficiency. Future research directions could further explore how demand responsive systems can be implemented in a targeted manner under different urban environments and demands to promote sustainable urban transport development. Considering the differences in cities, such as transportation structure, population density, and cultural characteristics, it will be crucial to develop appropriate implementation strategies. Meanwhile, combining emerging technologies, such as artificial intelligence and big data analytics, will provide strong support for further enhancement of the demand responsive transit system to better meet the travel needs of the residents and promote the development of urban transportation more sustainably. This study provides a valuable reference for urban planners and points out the direction for the improvement and development of urban transportation in the future.

With the importance of time and cost in today’s world, it is essential to solve problems in the best way possible. Optimization is a process used to achieve this goal and is applied in several areas, one of which is route planning. Route optimization minimizes the use of resources such as fuel, distance, and time. This study aims to optimize the traveler’s route, allowing the traveler to save money on fuel and visit more tourist attractions by utilizing the time saved. For this purpose, an application is developed that presents the attractions in a chosen province and then finds the acceptable route between the selected attractions. According to the obtained visit order, the bus or buses that will provide the fastest transportation between both locations are presented. The route is determined with a genetic algorithm (GA), which is known as one of the most effective optimization algorithms. In order to select the most appropriate crossover operator of the genetic algorithm, the performances of seven methods, namely One Point Crossover (OX1), Two Point Crossover (OX2), Position Based Crossover (PBX), Order Based Crossover (OBX), Partially Mapped Crossover (PMX), Cycle Crossover (CX) and Inversion Crossover (IX) are tested on the real-world problem in Konya/Türkiye. In addition, parameter tuning is performed for the values of the algorithm’s parameters such as population size, number of iterations, crossover rate, and mutation rate. As a result of the comparison, PBX is defined as the most suitable method for the problem. In addition, combinations of the four crossover methods (PMX, PBX, OX1, OX2) that obtained the best results according to the experimental analyses were compared. The comparison show that combinations of the PBX method are found to be the most suitable and the use of crossover techniques as ensemble is more effective than crossover techniques used separately. Furthermore, the best combination method named PBX + OX1 of GA was compared with ABC, ACO, SA, TSA, and PSO methods. This method is determined to find the maximum number of feasible solutions for a 14-stop real-world problem and it’s the shortest route in all trials and handling them in fewer iterations.

Abstract Covering path problems date from the pioneering work of Current et al. (1984, 1985). Two basic forms were defined in their work: the shortest covering path problem and the maximal covering shortest path problem. These two problems differ in that one requires complete coverage by the defined path and the other involves determining path alternatives which cover as much as possible while keeping the path length as short as possible. The latter of these two problems, the maximal covering shortest path problem, embodies the two major goals in transit planning: that is, finding efficient paths which serve as many people as possible. Often transit routes are restricted to major road segments, and when that occurs, routes do not compete with one another unless they overlap along a street segment or at an intersection. In addition, coverage distances can be quite small, barely extending to other streets. Given this type of situation, Curtin and Biba (2011) developed a model called TRANSMax (Transit Route Arc-Node Service Maximization), which maximizes node and arc service, where service coverage is defined for only those street and node segments that are part of a route. They based their model on a structure first proposed by Vajda (1961) in formulating and solving the traveling salesman problem. Because of this structure, we demonstrate that it is possible that a route generated by their original TRANSMax model may not be Pareto optimal with respect to both distance and access. In this paper, we develop a flexible TRANSMax model formulation that finds Pareto Optimal solutions when the original form does not. We also present computational experience in solving this new model on the same street network of Curtin and Biba involving Richardson, Texas. This application allows us to make comparisons between this work and the original work of Curtin and Biba. Overall, we show that this new model can identify new, improved routes over the existing TRANSMax model.

The integration of urban and rural transit networks is a prerequisite for the integration of urban and rural transportation systems. With the promotion of rural revitalization and new urbanization, the existing transit network operated separately in urban and rural areas is insufficient in meeting the travel demands of urban and rural residents. It is necessary to plan the urban and rural transit network rationally and to enhance the overall system performance of the urban and rural transit network. This paper proposes a biobjective model to optimize the integrated urban–rural transit network. The model minimizes both passengers’ and bus operators’ costs by optimizing the bus routes and frequencies simultaneously. Furthermore, we propose a subregional operations model and explore a performance comparison between the integrated and subregional optimization approaches. The genetic algorithm is developed to solve the proposed models. Finally, we conduct numerical experiments to identify the efficacy of the proposed models and algorithms. The results indicate that the integrated operation of the urban–rural transit network has more optimization space than the subregional operation, and can effectively reduce the number of transfers. Furthermore, under integrated operations, changes in operating costs have a more pronounced impact on total passenger travel time. When the demand is within a particular range, the integrated operation generates a shorter total passenger travel time than the subregional operation for the exact operating cost. In addition, the Pareto‐optimal solution generated under varying interregional demands provides a trade‐off between the total passenger travel time and the operating costs of the bus operator.

No abstract available

The efficient operation and intelligent upgrading of public transportation can effectively enhance the attractiveness of conventional public transportation. In order to improve the delicacy management level of bus operations, this study designed a new dynamic optimization model for single-line bus operations with the dual optimization objectives of the lowest passenger travel cost and lowest operation cost, using a combination of the strategy of stop-skipping control and local route optimization. Simulated annealing (SA) was introduced into the genetic algorithm (GA) to design a hybrid heuristic algorithm for model solving. The effectiveness of the optimization model and the hybrid algorithm were verified and evaluated by using the No. 115 bus line in Ganzhou City as an example. The results showed that the proposed optimization model had a good usability, which can effectively improve the average vehicle speed, shorten the overall waiting time of passengers, and enhance the operational efficiency of the line. The hybrid algorithm saw significant improvement in terms of the iteration speed and the quality of the optimal solution compared with the conventional genetic algorithm.

In this paper, to improve the operational service capability and attractiveness of the flex-route transit system, the real dynamic interaction scenario between passenger travel choice preference and system operation scheme in the post-pandemic era is described and quantified. The key technologies, operation mode, system framework, and interactive events required for dynamic interactive scheduling and route planning of flex-route transit are summarized. According to different choice preferences, the corresponding dynamic interaction scheduling strategies and route mixed integer programming model are proposed. An optimization scheme to improve the service capability of the system is introduced and analyzed. The computational results based on real-world cases show that the proposed strategy can better handle the relationship between requirements of transit system operation and requests of passengers without increasing operating costs, significantly improving the service performance of flex-route transit and the choice rate of passengers. We also find that the introduction of optimization schemes and the adjustment of passenger fares constitute a win-win strategy that benefits both passengers and transit operators.

The design and optimization of rail feeder routes has become a new focus of public transport operation in the face of the continuous expansion of rail transit in large cities and the shrinking of bus passenger flow. In the areas where feeder buses are lacking, bike sharing has become an important way of rail passenger feeder. This paper extracts the rail feeder travel demand based on shared bicycle orders, and establishes a multi-objective two-layer planning model for solving the feeder bus routes and frequencies in the dual-rail station area from the perspectives of bus operation revenue and passengers' travel mode selection. Combined with the actual road condition data, the designed bus line operation time is projected, and the optimized bus line design scheme is obtained by using the elite non-dominated sorting genetic algorithm. The effectiveness of this method is verified by applying it on the actual data of Shenzhen city area.

Given the distinct operational features of flex-route transit (FRT) compared to conventional fixed-route systems, this study integrates FRT with urban rail transit and proposes a collaborative optimization approach for feeder flex-route operations and scheduling. The model incorporates path planning, timetable design, and vehicle scheduling to minimize travel costs, enhance operational efficiency, and improve service quality. A mixed-integer nonlinear programming method is applied to optimize scheduling while aligning with rail timetables and passenger transfer behavior. Simulation experiments based on realistic urban transit scenarios are conducted to validate the model, optimizing key operational parameters such as departure intervals, vehicle deployment, and stop selection. The results demonstrate that the proposed approach effectively adjusts schedules and vehicle assignments to accommodate fluctuating passenger demand. This study offers both a theoretical foundation and a practical framework for integrated scheduling of feeder flex-route services, with potential applications for improving coordination and performance in multimodal public transit systems.

No abstract available

No abstract available

In this paper, we develop a multi-objective integrated optimization method for feeder buses of rail transit based on realistic considerations. We propose a bus stop selection method that considers the influence of shared motorcycles, which can score the importance of alternative bus stops and select those with the highest scores as objectives. The objective of the model in this paper is to minimize both the travel costs of passengers and the operating costs of the bus company. This is achieved by optimizing feeder bus routes, the frequency of departures, and interchange discounts to enhance the connectivity between feeder buses and rail transit. In addition, to ensure the feasibility of generated routes in the real road network, a genetic algorithm encoded with priority is used to solve this model. We use the Xingyao Road subway station in Kunming as an example, and the results show that the optimization method is effective.

Mass transit is a key aspect of urban planning and management. A vast network of mass transit provides various options for connectivity to individuals through extensive networks. On the other hand, a bigger network incurs a huge cost on the operator. Thus, striking a balance between the two is essential and challenging. Furthermore, with the transportation sector being a huge contributor to carbon emission, there is a pressing need to address this environmental impact. This paper presents Smart Route, an app which enables planning and optimization of mass transit for reduction in operating cost and fuel emission while maintaining high levels of passenger satisfaction with the network.

Real-time route optimization in public transit systems is essential for managing variable traffic conditions, changing passenger demand, and operational interruptions. This research presents a Multi-Agent Reinforcement Learning (MARL) framework in which each transit vehicle functions as an autonomous intelligent agent that adjusts its routes independently. Agents undergo training via a Proximal Policy Optimization (PPO) algorithm in a simulated urban environment that replicates actual traffic and passenger data. The system is assessed via a simulated dataset of 500 transit vehicles functioning across 100 routes with variable passenger volumes. The results indicate a 22.8% drop in average passenger wait time, a 17.4% enhancement in on-time arrival rates, and a 19.2% reduction in vehicle idle time relative to conventional static routing. Additionally, the MARL framework exhibits enhanced scalability and coordination, especially during peak periods, resulting in a 12.6% decrease in traffic congestion in high-density routes. The findings validate that MARL can proficiently facilitate decentralized, intelligent decision-making in public transport, hence improving overall service reliability and urban mobility. This approach offers a robust basis for implementing adaptive transportation systems in real-time, data-intensive settings.

A transit route network design problem is a vitally important problem in the area of public transit systems. Most of studies on this problem aim to design a new transit network, which is often an infeasible option in practice since it is highly challenging to replace an existing network with a completely new one. In this paper, we propose a Multi-objective Ant Colony System-based Approach (MACSA) to adjust routes of bus lines for an existing transit network, such that transit service quality is improved while making the smallest deviation of the adjusted network from the existing one. First, all the bus lines in a network are sorted according to their performance. Then, a multi-objective ant colony system is adapted to adjust the sorted bus lines one by one. Besides traditional optimization objectives to maximize direct passenger flow and minimize line repetition coefficient, a new optimization objective (metric), termed adjustment degree, is proposed to measure the difference between adjusted bus lines and existing ones. Needleman-Wunsch algorithm is introduced to calculate the adjustment degree. A multi-pheromone updating mechanism is suggested to guide ants to search for better bus lines for each objective. MACSA is applied to benchmark problem instances and a real-world problem and compared with six approaches. Experiments show that MACSA can achieve an adjusted network with higher direct passenger flow, lower repetition coefficient and smaller adjustment degree. The adjustment degree achieved by MACSA is 1.61-53.82% smaller than that of other comparative approaches.

As a promising on-demand transportation mode in low-demand areas, flex-route transit, has attracted much attention in the transportation research field. However, unexpectedly high demand levels caused by travel uncertainty impact the reliability and development of flex-route transit services. Although the meeting point strategy can deal with this problem effectively, selecting a location for the meeting points can substantially influence the performance of this strategy. In this study, meeting point location selection is modeled as a simulation-based optimization (SO) problem, and a Kriging-based global optimization method using a Pareto-based multipoint sampling strategy (KGO-PS) is proposed to solve this problem. Through comparison of several typical benchmark functions with other counterparts, the effectiveness of KGO-PS has been verified. Moreover, a real-life flex-route transit service is employed to construct the SO problem, and the optimization results show that the proposed algorithm can improve the performance of flex-route transit services under unexpectedly high demand levels.

No abstract available

Promoting demand-responsive transit (DRT) is crucial for developing sustainable and green transportation systems in urban areas, especially in light of decreasing transit ridership and increasingly varying demand. However, the effectiveness of such services hinges on their ability to efficiently match varying travel demand. This paper presents a data-driven framework for the joint optimization of customized bus routes and timetables, to enhance both service quality and operational sustainability. Our approach leverages large-scale taxi trip data to identify latent travel demand, applying a spatial–temporal clustering method to group trip requests and identify DRT stops by trip origin, destination, and direction. An adaptive large neighborhood search (ALNS) algorithm is improved to co-optimize passenger waiting times and bus operation costs, where an unbalanced penalty for early or late schedule deviations is developed to better reflect passengers’ discomfort. The framework’s performance is validated through a real-world case study, demonstrating its ability to generate efficient routes and schedules. The model manages to improve passenger experience and reduce operation costs. By creating a more appealing and efficient service, this model contributes directly to the goals of green transport in terms of reducing the total vehicle kilometers that are traveled, and demonstrating a viable, high-quality alternative to private car usage. This study offers a practical and robust tool for transit planners to design a next-generation DRT system that is both economically viable and environmentally sustainable.

Shared Autonomous Vehicles (SAVs) enable transit agencies to design more agile and responsive services at lower operating costs. This study designs and evaluates a semi-on-demand hybrid route directional service in the public transit network, offering on-demand flexible route service in low-density areas and fixed route service in higher-density areas. We develop analytically tractable cost expressions that capture access, waiting, and riding costs for users, and distance-based operating and time-based vehicle costs for operators. Two formulations are presented for strategic and tactical decisions in flexible route portion, fleet size, headway, and vehicle size optimization, enabling the determination of route types between fixed, hybrid, and flexible routes based on demand, cost, and operational parameters. Analytical results demonstrate that the lower operating costs of SAVs favor more flexible route services. The practical applications and benefits of semi-on-demand feeders are presented with numerical examples and a large-scale case study in the Chicago metropolitan area, USA. Findings reveal scenarios in which flexible route portions serving passengers located further away reduce total costs, particularly user costs, whereas higher demand densities favor more traditional line-based operations. Current cost forecasts suggest smaller vehicles with fully flexible routes are optimal, but operating constraints or higher operating costs would favor larger vehicles with hybrid routes. The study provides an analytical tool to design SAVs as directional services and transit feeders, and tractable continuous approximation formulations for planning and research in transit network design.

Bus transport is the backbone of delhies as over two thirds of the population depends on it as a mode of transit. Here is a pressing need to identify the baseline situation and recognize the issues with services offered and take immediate measures for reforms in the system. This paper examines the key issues with the blue lines that consist of improper operation and driving habits due to incorrect set of incentives for the owners as well as the crew. The Issues with the public provider of the bus facility, Delhi Transport Corporation are also determined which is facing incurred losses of over 6000 crore. Over the years, traffic volumes on roads have increased considerably. Henceforth, traffic congestion continues to worsen producing longer commute times, increased energy consumption and air pollution, besides robbing people of a precious commodity their time. ITS has emerged as a worldwide solution to handle these problems. Like any other transportation system, building a good intelligent transportation system requires considerable planning and financial resources.

Bus transit provides shorter-distance public transportation services, which are subject to various disability discrimination acts with various dedicated features. The Americans with Disabilities Act (ADA) requires that disabled individuals shall have equal rights to receive fare bus transit services, including fixed-route and door-to-door bus services. Most previous studies were mainly focused on policy aspects as part of the efforts of disability rights. The proper planning of demand requests from disabled individuals has been a critical issue but has gained insufficient attention. The existing methodologies in planning route for special transit buses for disabled individuals normally do not consider passengers’ waiting time, lack sufficient flexibility, and have strict restrictions on the total number of served destinations. This paper proposes a four-module based methodology for the planning of bus transit, including demand information collection, demand clustering, transit bus assignment, and a linear programming-based route planning with different objective functions. Houston MetroLift bus transit service was employed as an example to illustrate the proposed method. Three scenarios during the route planning module were designed in this case study: (1) planning for pre-timed shortest distance, (2) planning for the pre-timed shortest waiting time of passengers, and (3) flexible planning. Results showed that scenario 1 obtained the shortest total travel time and the highest benefit for bus providers, scenario 2 is with the shortest average waiting time, while scenario 3 is real-time based with longer total travel time and longer waiting time. Scenarios 2 and 3 consider the special needs of disabled passengers.

Nowadays, many passengers use transit systems to reach their destinations. By designing a well-integrated public transit system and improving the cost-effectiveness network, the public transport could play a crucial role in passenger satisfaction and reducing the operating cost. The main target of this paper is to present a new mathematical programming model and design an efficient transit system to increase the efficiency of integrated public transit services through the development of feeder bus services and coordination of major transportation services with the aim of maximizing the utility of operators and passengers. In this study, optimized transit services and coordinated schedules are developed using genetic algorithm. The data used and the coordination were obtained from a case study widely provided in the literature. Finally, obtained numerical results of the proposed model are discussed in detail using tables and figures.

No abstract available

As an emerging urban public transport mode, responsive feeder transit system is flexible and can offer door-to-door services between new districts at margins with low urban transit coverage and trunk bus station. In this study, a joint optimization of running route and scheduling for responsive feeder transit under mixed demand (i.e., reservation and real-time demands) of the time-dependent road network was investigated. A two-stage optimization method was designed together with considering the mixed demands. At the first stage, the initial running route and scheduling were determined according to all reservation demands. At the second stage, the running route and scheduling were continuously optimized based on the real-time demands. The real-time demand responsive strategy, which is built up by using quantitative batch treatment rather than immediate treatment and dynamic route updating strategy for global optimization, were designed by utilizing the submission order of real-time demands. A joint optimization model of running route and scheduling was constructed based on the quantitative batch decision points in the time-dependent road network together with combination of the actual road network. In this model, the minimum total system cost was used, which is composed of the vehicle running costs and passengers’ traveling time costs with constraints including vehicle capacity, passengers’ time window, and vehicle running time. A solving algorithm based on the adaptive genetic algorithm was designed by considering the characteristics of the joint optimization model.

Public transportation systems play a vital role in urban mobility, with Bus Rapid Transit (BRT) emerging as a cost-effective solution for medium-sized cities. This study aims to evaluate the operational performance of Trans Metro Deli BRT system in Medan, Indonesia, and propose optimization strategies for underperforming routes. The research employed a comprehensive data collection approach, combining on-board dynamic surveys and static terminal observations. Performance metrics were analyzed using standardized indicators from the Directorate General of Land Transportation guidelines, while Geographic Information System (GIS) analysis and mathematical demand modeling were utilized for route optimization assessment. The study revealed that while Corridors 1-4 maintained satisfactory performance metrics, Corridor 5 significantly underperformed with load factors of 48% during peak hours and 15% during off-peak hours. Route optimization analysis incorporating major educational institutions showed potential daily ridership of 26,190 passengers for Corridor 5, requiring 19 vehicles for optimal service. These findings demonstrate the importance of route alignment with major activity centers and provide transit planners with evidence-based recommendations for BRT system optimization in developing cities.

Under the present background, optimizing the existing urban rail transit network is the focus of urban rail transit construction at present. Based on DL, this paper constructs the optimization algorithm of urban rail transit network route planning. According to the current urban layout and urban planning, build a suitable rail transit network line form; according to the function, the types of urban rail transit stations are divided, and the optimization of urban rail transit network lines is realized. In addition, according to the K short path algorithm, this paper calculates the effective path between any stations of rail transit and, according to the model, allocates the passenger flow to each path. Experimental results show that the accuracy of real-time traffic flow prediction by this algorithm can reach 94.98%, which is about 9% higher than other methods. This algorithm can effectively optimize the route planning of urban rail transit network. This verifies the effectiveness of the route planning optimization algorithm proposed in this paper. Using the algorithm in this paper for line planning can get good real time, rationality, and optimality.

This study investigates the problem of joint optimization of transit network design, timetable, and passenger assignment with exact transfer behavior modeling. The problem is formulated as a bi-level mixed-integer bilinear program to capture passengers’ realistic path choice behavior. The upper-level model aims to minimize the weighted sum of the cost of bus route construction, bus route operation, bus station construction, travel time of passengers, the delay caused by failures in aboarding to the bus trips at the origin, the delay caused by failures in transfer between the bus trips, and the overflow delay when the bus trip operates at capacity. The lower-level model aims to minimize the travel time of passengers. The travel time of passengers is formulated as the sum of the waiting time for boarding, the transfer time, and the in-vehicle travel time. The passenger transfer time and the delay caused by failures in transfer between the bus trips are formulated with exact modeling of passenger transfer behavior. This bi-level mixed-integer bilinear program is transformed into an equivalent mixed-integer bilinear program with equilibrium constraints using Karush-Kuhn-Tucker conditions. To seek a solution of good quality to the proposed model while not requiring a large amount of computer memory, a Benders decomposition algorithm integrated with piecewise linearization is developed. A numerical application demonstrates that the proposed model is able to achieve 3.49% lower total cost than the baseline model assuming passenger transfer time to be half of the headway.

The accessibility, efficiency, and convenience of public transit in Hyderabad are significantly hindered by inadequate infrastructure, overcrowding, insufficient funding, inconsistent service, traffic congestion, and limited coverage. Urban engineers/urban planners widely recognize the Transit-Oriented Development (TOD) applications as an effective strategy for promoting maintainable urban growth. TOD focuses on situating populations near public transportation hubs to reduce dependence on private vehicles. Hyderabad's public transportation system (buses and trains) currently falls short of meeting commuter needs due to the absence of TOD principles, leading to increased private vehicle usage, traffic congestion, and air pollution. This study aims to evaluate commuter perceptions regarding transportation facilities' availability. It illustrates the service area coverage of the existing public Transit route network based on walkable distances converted to travel times using ArcGIS. Data was collected using an extensive questionnaire survey involving 400 respondents, selected using the Taro technique. Route information was gathered from the Regional Transportation Authority (RTA) and on-site surveys detailing the available public transportation routes. The collected data was analyzed using SPSS software, employing statistical methods such as Chi-Square tests, correlation analysis, normality checks, and ANOVA. The study identified the catchment areas for existing public transportation routes in Hyderabad, emphasizing regions where passengers have easy access to transit in alignment with TOD applications.

No abstract available

The electrification of traditional transit route networks has been a promising option for urban public transit. Compared with fast chargers, energy storage (ES) technology benefits the planner in relation to cost savings and avoiding high electricity demand charges. Although many studies ignored the potentiality of utilizing ES chargers, this study uses this concept with demand charges to design an electric transit route network by proposing a bi-level optimization model. The upper-level model aims to minimize the total travel times of passengers along with the total number of indirect trips. In comparison, the lower-level problem plans to minimize the total costs of purchasing two types of fast and ES chargers and demand charges for the transit network that entirely operates with battery electric buses (BEBs). Because of the NP-hard nature of the proposed model, the discrete multi-objective grey wolf optimizer algorithm is suggested in a discrete space to search for a feasible solution by providing the Pareto frontier of two objective functions. Also, the initial route set generation algorithm has been applied to generate a new set of transit routes. To validate the proposed model, our model has been tested on a benchmark network of Mumford0 in a small and a Fargo–Moorhead area in a medium size. Our results confirmed that considering ES chargers could save 4.8% and 76.5% (for the user cost), 2.3%, and 111.9% (for the operator cost) of the total network and demand charges.

The contradiction between transport capacity and passenger demand in urban rail transit is usually prominent during peak hours in some megacities of China, and some passenger flow control measures have been adopted to alleviate passenger congestion. To better save passengers’ travel time when taking passenger flow control measures, this paper proposes an integrated optimization method of bus route adjustment with network-level passenger flow control for urban rail transit, in which the controlled passengers can freely choose to shift to bus or to retain in urban rail transit for pursuing a lower travel cost. With the objectives of minimizing average additional travel time for all affected passengers and maximizing the operating revenue of urban rail transit, an integer non-linear programming model is formulated to determine the inbound passenger volumes and bus adjustment schemes. To solve this proposed model effectively, a multi-objective particle swarm optimization based on dual-population co-evolution is designed. Finally, three sets of numerical experiments, including an integrated optimization experiment and two independent optimization experiments of passenger flow control, are implemented to demonstrate the feasibility and benefits of the proposed method.

Efficient public transport systems are vital for urban mobility, yet many suffer from delayed schedules, inefficient routing, and poor user communication. This paper presents a smart public transport route optimization system that integrates machine learning and conversational AI to enhance commuter experience and operational efficiency. We employ a Long Short-Term Memory (LSTM) model to predict bus arrival times using historical schedule data, while Dijkstra's algorithm is utilized for optimal route selection across the network. A user-friendly interface is enabled through Dialogflow, allowing commuters to interact with the system via natural language queries regarding routes and bus schedules. The backend is powered by FastAPI, ensuring seamless integration between the prediction model, route optimization algorithm, and chatbot interface. Experimental results using the BMTC GTFS dataset demonstrate accurate arrival time predictions and effective route optimization, showcasing the potential of combining machine learning and conversational AI for smarter public transport solutions.

The transportation service system requires improvements to evolve into a smart and more efficient system. Passengers waiting at bus stops can create long queues, causing a lack of available shuttle bus capacity when arriving at the bus stop. This work proposes a genetic algorithm model to minimize passenger waiting time and schedule shuttle buses to stops with high capacity. The Genetic Algorithm works by searching for the optimal value to result in optimal waiting time by providing calling shuttle bus. After the method reaches the optimal solution, the simulation result will provide a minimum waiting time. In case studies of simulated design at either campus in Central Java, Indonesia. This method provides a simulated system shuttle bus on scheduling to raise a challenge in waiting time efficiency and passenger accumulation at campus transportation. The case studies of the application on passenger waiting time showcase the model's ability to improve transportation services in the unscheduled campus area. This system was designed to ensure that it was effective in addressing the transportation challenges faced by students and staff. Use the full potential of bus transportation in the campus area to ensure continuity between stops and city transportation. Therefore, this approach reduces waiting times and schedules to overcome challenges posed by passenger accumulation for structured campus transportation services. Keywords—Shuttle Bus; Genetic Algorithm; Campus Area; Minimize Waiting Time; Scheduling; Optimization.

This paper introduces the Smart Passenger Center (SPaCe), MerMec's solution for real-time optimization of urban public transport. The proposed system, based on cutting-edge artificial intelligence technologies, provides real-time vehicle status information and passenger activity monitoring. All of the information acquired from the vehicles is used to optimize the performance of the vehicle fleet for real-time traffic management.The purpose of the paper is to explain the reasons and benefits of such Intelligent Transport System (ITS) with a deep understanding of its architecture and advanced functionalities.Additionally, a practical application of the data collected by SPaCe is proposed for the task of bus timetable optimization.The goal is to schedule bus trips in a way that maximizes multiple conflicting goals such as service quality and operating costs, based on real time collected data.The reported results show how the developed optimization system can support the decision-making process to balance the interests between passengers and public transport agencies.

We study the complexity of the directed periodic temporal graph realization problem. This work is motivated by the design of periodic schedules in public transport with constraints on the quality of service. Namely, we require that the fastest path between (important) pairs of vertices is upper bounded by a specified maximum duration, encoded in an upper distance matrix $D$. While previous work has considered the undirected version of the problem, the application in public transport schedule design requires the flexibility to assign different departure times to the two directions of an edge. A problem instance can only be feasible if all values of the distance matrix are at least shortest path distances. However, the task of realizing exact fastest path distances in a periodic temporal graph is often too restrictive. Therefore, we introduce a minimum slack parameter $k$ that describes a lower bound on the maximum allowed waiting time on each path. We concentrate on tree topologies and provide a full characterization of the complexity landscape with respect to the period $\Delta$ and the minimum slack parameter $k$, showing a sharp threshold between NP-complete cases and cases which are always realizable. We also provide hardness results for the special case of period $\Delta = 2$ for general directed and undirected graphs.

No abstract available

With the continuing economic growth of developing countries, the populations of their urban areas are increasing dramatically. In view of this trend, the optimization of bus service scheduling has become an important task. The efficiency of a transport system depends on several different planning processes, and the balance between these elements is rather complex. In this paper, we consider timetabling and vehicle allocation as the bases for our work. With the aim of providing a reliable service to passengers at a reasonable cost, we focus on the optimization of a bus schedule using a method based on K-means and a genetic algorithm. Our approach starts with parameter setting and data preparation, using a dataset of real bus operating schedules. Three elements are identified from this dataset: the time zones in which the bus service operates, the number of stops made by each bus in each trip, and the dwell time at bus stops. K-means clustering is used to identify moderate operation conditions. The outcome of the K-means algorithm is used as the objective fitness value for optimization of the bus schedule using a genetic algorithm. The results of experiments show that the proposed optimization model can improve the dwell time while maintaining the operating cost at its current level or less, and a remarkable increase in the operation rate is achieved in the case study. The proposed model is able to both effectively optimize the financial outlay and enable bus operators to meet passenger demand in a mutually satisfactory way.

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

Transport accessibility and urban-rural connectivity are seen as critical aspects of rural economic development. In the transit network, passenger flow between urban-rural corridors demonstrates directional imbalances and low utilization of scarce resources. Freight transportation, on the other hand, lags due to poor geography, high operating costs, and scattered demand. This paper proposes a new mode of public transit that integrates passenger and freight transport, providing a carrier for logistics while compensating for the low utilization of passenger transport. In this mode, each timetabled round trip is divided into one dedicated passenger trip with high demand and one mixed-flow trip with on-demand requests. A space-time-state network is constructed considering the picking-up time window, loading/unloading service time, and electric bus energy replenishment. A mixed-integer linear programming model is developed to optimize the bus schedule that covers the travel demands and the charging requests with minimized travel costs. A Lagrangian relaxation framework with a dynamic programming algorithm and sub-gradient method is presented for problem-solving. The real-life rural-urban transport instance and a simulated network demonstrate the operation of the new mode and validate the efficiency of the proposed method. The innovative concept and the optimization framework are expected to serve as a reference for public administration to alleviate passenger and freight transportation bottlenecks in the urban-rural context.

Predicting public transport ridership trends accurately is crucial to schedule optimization, lowering the operational cost, and enhancing the passenger's experience. This research suggests a predictive framework based on AI that combines historical ridership with external contextual variables like weather, public holidays, and high-profile events. By employing a hybrid deep learning model incorporating Long Short-Term Memory (LSTM) networks and temporal feature embedding, the model embeds both short-term variation and long-term seasonal patterns of passenger demand. A case study involving multi-year metro and bus datasets illustrates the model's superior performance compared to conventional time- series forecasting techniques, which have substantial Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) improvements. The addition of exogenous attributes increases predictive resilience at unusual events, like weather conditions or disruptions. This paper makes a scalable and flexible AI solution available to transit agencies to facilitate data-driven decision-making and enhanced resilience in public transit.

Current route planning algorithms for public transport networks are mostly based on timetable information only, i.e., they compute shortest routes under the assumption that all transit vehicles (e.g., buses, subway trains) will incur in no delays throughout their trips. Unfortunately, unavoidable and unexpected delays often prevent transit vehicles to respect their originally planned schedule. In this paper, we try to measure empirically the quality of the solutions offered by timetabling routing in a real public transport network, where unpredictable delays may happen with a certain frequency, such as the public transport network of the metropolitan area of Rome. To accomplish this task, we take the time estimates required for trips provided by a timetabling-based route planner (such as Google Transit) and compare them against the times taken by the trips according to the actual tracking of transit vehicles in the transport network, measured through the GPS data made available by the transit agency. In our experiments, the movement of transit vehicles was only mildly correlated to the timetable, giving strong evidence that in such a case timetabled routing may fail to deliver optimal or even high-quality solutions.

No abstract available

No abstract available

The flexible transit service reflects a trend of demand on the flexibility and convenience in urban public transport systems, within which the vehicle scheduling and passenger insertion are two challenging issues. Especially, finding the optimal solution for a flexible transit system can be viewed as an extension of the traveling salesman problem which is NP-complete. Yet most of the existing research mainly focuses on one aspect, i.e. route planning, stop selection or vehicle scheduling, where a combined integration and optimization of the whole system is largely neglected. In this paper, we propose a data-driven flexible transit system that integrates the origin-destination insertion algorithm and the milp-based (mixed-integer linear programming) scheduling scheme. Specifically, stops are mined from the historical datasets and some stops act as $backbone$ stops that should be visited by the vehicles; and a heuristic backbone-based origin-destination insertion algorithm is proposed to schedule the routing path of vehicles, where the time loss caused by the optimal insertion positions is calculated for the vehicles to decide whether to accept the requests or not when constructing a path for the flexible routes. Moreover, a vehicle scheduling model based on milp is proposed to minimise the gap between the passenger flow and available seats. The proposed flexible transit systems are simulated in real-world taxi datasets, and experimental results show that the proposed flexible transit system can effectively increase the delivery ratio and decrease the passengers’ waiting time compared with existing methods.

After the widespread impact of the COVID-19 pandemic, all public transport, including urban rail transit, inevitably adopted a vigorous physical-distancing policy to prevent the disease from spreading among passengers. Adoption of this measure resulted in a substantial reduction in train service capability and required control of the risk contact exposure duration. Thus, this paper proposes the Skip-Stop Strategy Patterns (3S–P) decision-support model to incorporate social distancing constraints in train operations. The 3S–P model is a two-stage, multi-objective optimization model for scheduling train skip-stop patterns to satisfy the study's two main objectives of minimizing the average passenger travel time and unserved passengers. In the proposed model, the first optimization identifies the optimal train skip-stop patterns, while the second assigns these patterns to establish an hourly train schedule. The paper's case study uses data from the Bangkok Mass Transit System (BTS) SkyTrain Silom Line in Bangkok, Thailand and considers the 0.5, 1, 1.5, and 2 m social distancing schemes. The results reveal that the optimal train skip-stop patterns are superior to the all-stop alternative with, on average, a 13.4% faster travel time at the same level of unserved passengers. Furthermore, the non-dominated schedules from the second optimization decrease the numbers of unserved passengers given equal average passenger travel times.

No abstract available

Bus rapid transit (BRT) as a valid means of public transportation for overpopulated country of China is an especial mode of travel to relieve traffic congestion. Despite utilizing exclusive bus line, BRT constantly experiences delay at intersections when encountering a red signal. Transit signal priority (TSP) considered as a promising control strategy to improve the operation efficiency of BRT has been widely used at isolated intersections or arterials to reduce travel delay. However, as a transport with schedule, the unexpected arrival time of transit vehicle at stop lines of consecutive intersections inevitably affects the operation reliability of the BRT system. To solve the problem, this study develops an optimization model of conditional TSP for bus rapid transit with the objective of improving the on-time performance of the BRT system while mitigating adverse impacts on private vehicles. A stop-to-stop segment is established with both road sections and intersections for the consideration of the transit operation reliability. The constraints on the degree of saturation and queue overflow were considered for mitigating adverse impacts of TSP. A mixed-integer non-linear programming procedure is adopted to formulate the optimization model. The mathematical model is linearized and solved by the branch-and-bound method. Extensive numerical analyses are conducted, and the proposed conditional TSP strategy is compared with unconditional TSP and no-TSP control to evaluate its performance under various traffic and signal conditions. A case study of a BRT line in Shanghai, China, was selected to illustrate the effectiveness of the proposed model. For the tested scenarios, the transit on-time performance was improved by 21%, with an incurred cost of 3.4% increase in the delay of private vehicles. This indicates that the proposed model performs well in maintaining the reliability of the transit system with the least impact on general traffic.

The wide integration of all battery electric buses (BEB) in the operation of public transit services is identified as one of the most promising means toward decarbonizing public transport systems. In response, public bus transit (PBT) and utility grid operators are currently in need of developing analytical techniques that enable them to conduct tradeoff analyses for the many available options of BEBs, charging infrastructure, and their associated system impacts. To that end, this article proposes a systematic and effective technique for feasibility check and configuration design of electrified PBT fleets without the need for the sophisticated optimization toolbox and high performance computing. The configuration design aims at determining the number of BEBs and their on-board battery capacities to meet the PBT prespecified schedule under different sizes of chargers. The proposed model is tailored for BEBs designed to either boost their batteries on-route at intermediate bus stations using fast chargers (opportunity charging) or charge while parked at the depot (in-depot charging). The developed model is also utilized to generate the aggregated power demand profiles of electrified PBT fleets under different charging practices. Based on the generated power demand profile, a lifecycle cost analysis is conducted to compare BEB-based PBT options to their diesel counterparts.

No abstract available

The transport sector is responsible for 25% of global CO 2 emissions. To reduce emissions in the EU, a shift from the currently 745,000 operating public buses to electric buses (EBs) is expected in the coming years. Large-scale deployments of EBs and the electrification of bus depots will have a considerable impact on the local electric grid, potentially creating network congestion problems and spikes in the local energy load. In this work, we implement an exact, offline, modular multi-variable mixed-integer linear optimization algorithm to minimize the daily power load profile peak and optimally plan an electric bus depot. The algorithm accepts a bus depot schedule as input, and depending on the user input on optimization conditions, accounts for varying time granularity, preemption of the charging phase, vehicle-to-grid (V2G) charging capabilities and varying fleet size. The primary objective of this work is the analysis of the impact of each of these input conditions on the resulting minimized peak load. The results show that our optimization algorithm can reduce peak load by 83% on average. Time granularity and V2G have the greatest impact on peak reduction, whereas preemption and fleet splitting have the greatest impact on the computational time but an insignificant impact on peak reduction. The results bear relevance for mobility planners to account for innovative fleet management options. Depot infrastructure costs can be minimized by optimally sizing the infrastructure needs, by relying on split-fleet management or V2G options.

Reorganizing bus frequency to cater for the actual travel demand can save the cost of the public transport system significantly. Many, if not all, existing studies formulate this as a bus frequency optimization problem which tries to minimize passengers' average waiting time. However, many investigations have confirmed that the user satisfaction drops faster as the waiting time increases. Consequently, this paper studies the bus frequency optimization problem considering the user satisfaction. Specifically, for the first time to our best knowledge, we study how to schedule the buses such that the total number of passengers who could receive their bus services within the waiting time threshold is maximized. We prove that this problem is NP-hard, and present an index-based algorithm with $(1-1/e)$ approximation ratio. By exploiting the locality property of routes in a bus network, we propose a partition-based greedy method which achieves a $(1-\rho)(1-1/e)$ approximation ratio. Then we propose a progressive partition-based greedy method to further improve the efficiency while achieving a $(1-\rho)(1-1/e-\varepsilon)$ approximation ratio. Experiments on a real city-wide bus dataset in Singapore verify the efficiency, effectiveness, and scalability of our methods.

Economic, technical and operational performance of passenger road transport is a crucial aspect in the planning of transport processes. The performance of passenger road transport for public transportation is primarily related to the quality of passenger services. The quality of transport services is determined by a set of properties and characteristics that must meet the needs of consumers: a clear schedule of vehicle stock; speed of connection, level of tariffs; comfort and reliability of buses, cabin filling, especially during rush hour and some others. The most important factors for transport operators are the cost of transport services. Improper organization of passenger transport leads to unjustified costs. The efficiency of transport depends on properly defined indicators – organizational, technical (type, quantitative composition, passenger capacity of vehicle stock etc.), operational (speed, intervals, trip time on the route etc.), as well as qualifications and responsibilities of drivers, along with other management measures. Therefore, research related to improving the efficiency of vehicle operation by reducing costs is appropriate and relevant. The article presents the results of research on the planning of the transport process in the performance of road transport for public transportation on urban and suburban routes. It is presented an algorithm which optimizes the quantitative composition of vehicles on the route, passenger capacity, traffic intervals depending on the capacity of passenger load, and also allows to calculate technical and economic indicators. The results of the survey of public transport passengers against the criteria of services' quality and their priority are presented. Thus, according to the results of research, the main purpose of which is to solve a multi-criteria problem of minimizing fixed and variable costs in the performance of passenger road transport, is the optimization of interconnection between quality indicators of vehicle stock and planning, organizational and production principles.

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

Reorganizing bus frequencies to cater for the actual travel demands can significantly save the cost of the public transport system. Many, if not all, previous studies formulate this as a bus frequency optimization problem that tries to minimize passengers’ average waiting time. On the other hand, many investigations have confirmed that the user satisfaction drops faster as the waiting time increases. Consequently, this paper studies the bus frequency optimization problem considering the user satisfaction. Specifically, for the first time to our best knowledge, we study how to schedule the buses such that the total number of passengers who could receive their bus services within the waiting time threshold can be maximized. We propose two variants of the problem, FAST and FASTCO, to cater for different application needs and prove that both are NP-hard. To solve FAST effectively and efficiently, we first present an index-based <inline-formula><tex-math notation="LaTeX">$(1-1/e)$</tex-math><alternatives><mml:math><mml:mrow><mml:mo>(</mml:mo><mml:mn>1</mml:mn><mml:mo>-</mml:mo><mml:mn>1</mml:mn><mml:mo>/</mml:mo><mml:mi>e</mml:mi><mml:mo>)</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="bao-ieq1-3036573.gif"/></alternatives></inline-formula>-approximation algorithm. By exploiting the locality property of routes in a bus network, we further propose a partition-based greedy method that achieves a <inline-formula><tex-math notation="LaTeX">$(1-\rho)(1-1/e)$</tex-math><alternatives><mml:math><mml:mrow><mml:mo>(</mml:mo><mml:mn>1</mml:mn><mml:mo>-</mml:mo><mml:mi>ρ</mml:mi><mml:mo>)</mml:mo><mml:mo>(</mml:mo><mml:mn>1</mml:mn><mml:mo>-</mml:mo><mml:mn>1</mml:mn><mml:mo>/</mml:mo><mml:mi>e</mml:mi><mml:mo>)</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="bao-ieq2-3036573.gif"/></alternatives></inline-formula> approximation ratio. Then we propose a progressive partition-based greedy method to further boost the efficiency while achieving a <inline-formula><tex-math notation="LaTeX">$(1-\rho)(1-1/e-\varepsilon)$</tex-math><alternatives><mml:math><mml:mrow><mml:mo>(</mml:mo><mml:mn>1</mml:mn><mml:mo>-</mml:mo><mml:mi>ρ</mml:mi><mml:mo>)</mml:mo><mml:mo>(</mml:mo><mml:mn>1</mml:mn><mml:mo>-</mml:mo><mml:mn>1</mml:mn><mml:mo>/</mml:mo><mml:mi>e</mml:mi><mml:mo>-</mml:mo><mml:mi>ɛ</mml:mi><mml:mo>)</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="bao-ieq3-3036573.gif"/></alternatives></inline-formula> approximation ratio. For the FASTCO problem, two greedy-based heuristic methods are proposed. Experiments on a real city-wide bus dataset in Singapore have been conducted to verify the efficiency, effectiveness, and scalability of our methods in addressing FAST and FASTCO respectively.

Congestion in urban cities is a significant problem due to increased private vehicle ownership. Bus rapid transit (BRT) is a principal strategy to alleviate traffic problems in large urban cities. This study will evaluate the implementation of the Bus Rapid Transit system along a congested corridor in Baghdad City to analyze its ability to alleviate congestion using VISSIM as a simulation tool. A Stated Preference (SP) survey was conducted to predict the feasibility of implementing this system and to understand the private vehicle users’ willingness and attitudes toward shifting to the BRT system. Three Bus Rapid Transit (BRT) scenarios were modeled to represent modal splits of 30:70, 50:50, and 70:30 between BRT and private vehicles. It was found that scenario 3 (70:30 split) offers better results in terms of average delay and queue length. The BRT system generally enhanced the way the transportation system operated and provided people with faster and more effective mobility services. The Bus Rapid Transit system is a significant development in public transport networks, enhancing quality of life in Baghdad and reducing reliance on private vehicles.

The first extensive Bus Rapid Transit (BRT) system in the Philippines, the EDSA Busway, was put into place as a result of Metro Manila’s ongoing traffic congestion. This study uses an integrated framework that combines cost–benefit analysis (CBA), commuter perception survey, and traffic simulation to assess its economic, social, and environmental implications. The operational viability and traffic impact of the planned Magallanes BRT station were evaluated through simulation using PTV VISSIM. A total of 385 commuters participated in a survey measuring their impressions of safety, accessibility, and satisfaction using a four-point Likert scale. The Busway’s excellent economic feasibility was confirmed by the CBA results, which showed a Benefit–Cost Ratio (BCR) of 15.38 and a Net Present Value (NPV) of ₱778.64 billion. Results from the simulation showed a 24% decrease in PM2 emissions, a 75% increase in throughput, and a 64% reduction in bus trip time. According to survey results, 61% of commuters said accessibility had improved and 62% said travel satisfaction had increased. The study supports the EDSA Busway’s status as a feasible model for future BRT expansion in Metro Manila and other emerging metropolitan regions by showing how it greatly improves environmental sustainability and mobility efficiency.

Under the background of implementing the "public transit priority" strategy, it is of great significance to study the traffic flow in the bus stop area to solve traffic problems. Based on the field research, this paper uses VISSIM simulation software to study the common influence of bus arrival frequency and nonmotor vehicle traffic volume on traffic flow in bus stop area under the premise of fixed motor vehicle traffic. Considering the actual situation that the amount of nonmotor vehicles grows rapidly, especially the sharing bicycles, the delay time of mixed traffic flow and service level of nonmotor vehicle lane are used as evaluation indicators. In this paper, three representative station types are selected for simulation research. They are the linear type stop placed next to the nonmotor vehicle lanes, the linear type stop that the nonmotor vehicle lane bypasses after the platform and the harbor type stop set next to the nonmotor vehicle lane. Finally, combined with the simulation results, a reasonable station type optimization plan is proposed for the Pengyuan Ximen Bus Station in Xuzhou to reduce the conflict of mixed traffic flow in the bus station area and improve the service level of the bus station.

Population growth and rapid urbanization have increased transportation demand and triggered traffic problems. Capacity-based approaches often exacerbate these conditions, highlighting the need for a sustainable transportation concept. The government has designated the development of public transportation as a national priority program, one of which is through bus rapid transit (BRT). To ensure the efficiency, reliability, and attractiveness of BRT, the implementation of bus signal priority (BSP) is essential. This study aims to evaluate the performance of passive and active BSP strategies at signalized intersections within a BRT system using VISSIM microscopic simulation. The strategies analyzed include cycle time adjustment, phase splitting, red truncation, green extension, and phase insertion. The simulation results indicate that the most effective strategies are cycle time adjustment with the early cut off concept for passive BSP and phase insertion for active BSP. The performance of BSP strategies is influenced by the number of phases, traffic movement patterns, and bus service frequency, which vary according to the applied strategy. This study recommends selecting BSP strategies through comprehensive simulation study to achieve both effective performance and cost efficiency before implementation.

In this study, we assess a cooperative bus-holding transit signal priority strategy (C-BHTSP) in a connected and automated vehicles (CAV) environment. The research objectives of this study are to quantify the benefits of C-BHTSP to transit, its impact on opposing non-transit traffic, and the CAV market penetration rate required to neutralize that impact. A simulation model was developed in VISSIM using detailed, high-quality, up-to-date data for transit, non-transit traffic, and signal control parameters. Our assessment shows that the proposed strategy results in about a 60% reduction in transit delay compared to the base scenario. The results also show that a CAV MPR of 32% was found sufficient to overcome the negative impact of C-BHTSP on the opposing non-transit traffic while maintaining transit benefits. Higher MPRs produce substantial improvements in the overall travel time, delay, fuel consumption, and greenhouse gas emissions. The framework and findings of this study provide a blueprint for the decision-making process of implementing transit priority under varying CAV MPRs.

Bus Rapid Transit (BRT) is one of the mass transportation solutions consisting of infrastructures integrating dedicated bus lanes and smart operational service with different ITS technologies like Transit Signal Priority (TSP). Delay at an intersection is among the major factors for poor transit performance. This study examines the performance of buses at intersections of BRT corridors, which are privileged with Signal Priority on the dedicated lane. Simulation models were developed for the selected intersection together with the real-time calibration and validation. Statistical comparisons were conducted to test the alternative scenarios aimed at visualizing the deployment advantages. TSP options were evaluated by using PTV VISSIM with VisVAP add-on simulation tool. Alternative scenarios with and without TSP were tested to measure the performance of BRT buses along with impact assessment on the general traffic. TSP reduces travel time and control delay, improves travel speed and the results depicted a reduction in average passenger delay by 10–20%. The improvement on travel speed at an intersection of BRT vehicles were determined to be 6–8%. Prioritizing buses has diminutive impact on the general traffic, nonetheless, it is the easiest way of improving transit

No abstract available

This research introduces a modeling framework that examines pedestrian movements toward a bus stop on the Virginia Tech campus. It considers Bus capacity and social distancing strategies, and compares the current normal situation with the potential implications in the event of a pandemic return. Employing pedestrian and bus movement simulations, the study develops a pedestrian modeling framework using Vissim to evaluate two scenarios. The pre-pandemic scenario represents the baseline conditions before the pandemic, characterized by the absence of social distancing measures and bus capacity protocols. Pandemic Scenario with Applied Protocols considers the application of pandemic-specific protocols, including social distancing and bus capacity measures. A study site on a College Campus (Virginia Tech in Blacksburg, VA, USA) has been selected to illustrate simulation for the study of pedestrian behavior at Burrus bus stop's waiting area during a certain time of a working day, assuming classes will continue in person during the pandemic. The results indicated that enhancing bus scheduling, particularly by increasing the frequency, has positive effects on pedestrian movements. This is evident in improvements in both travel time and pedestrian density, even when considering social distancing measures. The results of the simulation provide insights into the impacts that social distance and bus capacity regulations have on Pedestrians' Density and Travel Time.

No abstract available

Currently, 2 (two) infrastructure projects are under construction on the Jakarta – Cikampek Toll Road, they are the Light Rail Transit (LRT) and the Jakarta – Bandung Fast Train. The construction of the project is indicated to be one of the causes of congestion on the road segment. The provision of bus lane (LKAU) on toll roads is one part of the policy package. LKAU which should be used by buses is actually widely used by non-bus vehicles, this certainly affects the performance of roads. To describe the changes in the performance of these roads, it can be measured by conducting traffic simulations. One of the software to perform microscopic simulation is Vissim. Where one of the processes that must be carried out in the software is calibration and validation. This research was conducted to obtain a calibration model that is able to describe the condition of the driver's behavior in the field. The calibration process is carried out by trial and error on parameters including Following Behavior, Lane change behavior, and Lateral behavior. The results showed that the parameter adjustment in the tailing (following), the settings were made by changing the CC0 (standstill distance) value from 1.5 m to 0.50 m, changing the CC1 (headway time) value from 0.9 to 0.5 seconds, changing the the value of CC2 (following variation) from 4 m to 7.5 m and changing observed vehicles movement,lateral namely changing the “desired position at free flow” from the middle of lane to any.

No abstract available

No abstract available

Connected vehicle (CV) technologies enable safe and interoperable wireless communication among vehicles and the infrastructure with the possibility to run many applications that can improve safety, and enhance mobility. This paper develops CV-based algorithms which use transit vehicle speed and the estimated time that the vehicle needs to arrive at an intersection to trigger transit signal priority (TSP) initiation. This information is updated each second based on the traffic conditions such as speed, a current distance of a transit vehicle to the intersection, and queue conditions. The algorithm uses the actual speed of a transit vehicle and its latitude/longitude (lat/lon) coordinates to compute the time that the vehicle needs to reach the stop line. It was tested on a real-world network using VISSIM traffic simulation, but can easily be implemented in the field, since it is using world coordinates. The upgraded algorithm was applied to a future bus rapid transit (BRT) scenario, and included different levels of conditional TSP, which depend on three combined conditions: the time that a transit vehicle needs to reach the stop line, the number of passengers on board, and the lateness that the transit vehicle experiences. The test-case network used for model building is a corridor consisting of ten signalized intersections along State Street in Salt Lake City, UT. The CV algorithms coupled with TSP can yield notable delay reductions for both the regular bus and the BRT of 33% and 12%, respectively.

No abstract available

No abstract available

This article develops a passenger-based priority for transit buses by balancing the trade-offs between the benefits at major streets and delays on side streets. A rule-based Transit Signal Priority (TSP) is set to assign priority to scheduled-based transit vehicles based on: their schedule adherence, passenger occupancy, and passengers waiting at downstream stops. The minimum number of bus passengers required to receive priority is obtained using deterministic queueing theory for the two cases of green extension and red truncation. VISSIM simulation software is used to evaluate the performance of the developed TSP approach, comparing it with: existing, unconditional, and no-TSP scenarios. This evaluation assessed performance measures for major streets, crossing streets, and the network level. The simulation demonstrated that a passenger-based TSP results in a significant decrease in travel time and side-street delay, compared to existing priority measures (buses will receive priority once every three minutes) on the corridor.

Planning for a transit-based evacuation presents many challenges for planners, particularly due to resource limitations. These limitations make it crucial to optimize the use of available transit vehicles. This study introduces the Paratransit- Transit Pick-Up and Delivery Problem (PTPDP), a variant of the traditional vehicle routing problem, designed to optimize the routing of available paratransit vehicles in a two-stage transit-based evacuation scenario. The PTPDP targets evacuation assistance at elderly, mobility-impaired, and homebound evacuees that are especially disadvantaged in this scenario type and uses paratransit vehicles to transport them from their individual locations to bus stops for further evacuation. The model uses a multi-objective approach that minimizes the initial wait time of evacuees, the travel time of paratransit vehicles, and the wait time of evacuees at bus stops for buses to arrive. VISSIM simulation software is used to collect input data for the model. This study applies the PTPDP model to a hypothetical evacuation scenario for the Virginia Tech campus and its surrounding areas in Blacksburg, Virginia to demonstrate the applicability of the PTPDP model.

Bus detector layout is essential for detecting reactive transit signal priority (TSP) at an intersection, and a single-step detection concerned in practice difficultly takes into account the fluctuation of operating speed and the flexibility of adjusting the timing scheme. Therefore, synthetically considering the two factors, a multi-step detector layout algorithm, involving two types of detectors, is proposed and the corresponding detection mechanism is performed for TSP. Based on the constraint of four bus arrival conditions and two priority strategies, a preview detector layout algorithm is established with a low fail-priority rate, which satisfies the premise of adjusting the scheme with certain flexibility for the worst condition. Then, in the near position, a confirm detector is installed to modify the deviation of travel time caused by the speed fluctuation and correct the priority scheme. Moreover, an intersection simulation scenario with TSP is carried out based on VISSIM and VAP, and four cases are established for the sensitivity analysis of the detectors’ positions. As the distance of the preview detector increases, the fail-priority rate decreases stepwise, and the efficiency is better at 450m, in Case ①. When the confirm detector is set at 150 m, the adverse efficiency caused by speed fluctuation is effectively alleviated, with the average vehicle delay reduced to 5.1 s/veh, in Case ③. Thus, the simulation result shows that the optimal detector distances are 450m, and 150m respectively, which verifies that the bus detector layout algorithm could effectively improve the bus operation efficiency and reliability.

This research aims to assess the impact of light buses on mobility and time delays. Extended wait times and unfavourable environmental factors lead to traffic jams and negative economic impacts. One suggestion is to relocate these minibuses to the bus rapid transit (BRT) lane. Three crossroads that are connected by a corridor were included in the analysis. The crossroads under consideration are the University of Jordan intersection, the Sweileh intersection, and the intersection of external patrols. Vissim simulation software is used for the evaluation and analysis, using data from detectors data at crossings. As a result of shorter wait times and shorter lines, both the simulation and the collected findings demonstrated an overall improvement in mobility. The environment would benefit from such an upgrade. The inclusion of light buses does, nonetheless, cause a little delay on the BRT lane; however, this is offset by an overall improvement in the mobility of all traffic at each crossing. Improved quantitative assessment of the dynamic traffic at each crossing was made possible based on simulation. The results generated by this study demonstrated intricate traffic interaction models (involving Sweileh, outside patrols, and the University of Jordan), which might be applied during the design phase of upcoming construction projects near these crossings.

No abstract available

No abstract available

No abstract available

One important objective of urban traffic signal control is to reduce individual delay and improve safety for travelers in both private car and public bus transit. To achieve signal control optimization from the perspective of all users, this paper proposes a platoon-based adaptive signal control (PASC) strategy to provide multimodal signal control based on the online connected vehicle (CV) information. By introducing unified phase precedence constraints, PASC strategy is not restricted by fixed cycle length and offsets. A mixed-integer linear programming (MILP) model is proposed to optimize signal timings in a real-time manner, with platoon arrival and discharge dynamics at stop line modeled as constraints. Based on the individual passenger occupancy, the objective function aims at minimizing total personal delay for both buses and automobiles. With the communication between signals, PASC achieves to provide implicit coordination for the signalized arterials. Simulation results by VISSIM microsimulation indicate that PASC model successfully reduces around 40% bus passenger delay and 10% automobile delay, respectively, compared with signal timings optimized by SYNCHRO. Results from sensitivity analysis demonstrate that the model performance is not sensitive to the number fluctuation of bus passengers, and the requested CV penetration rate range is around 20% for the implementation.

No abstract available

This study employs simulation-based analysis of passenger flow and bus operations at the Adam Malik transfer point within the TransJakarta BRT system. The findings from the analysis of the current system indicate that the average number of total passenger exits in corridors 13, 13B, 13C, and L13E were 618, 509, 1143, and 790, respectively. Additionally, the average time spent by passengers within the system for each corridor was 4.48 minutes, 6.12 minutes, 5.94 minutes, and 5.46 minutes, respectively. Through the development of 15 scenarios, the study demonstrates the impact of adjusting passenger boarding procedures and reducing interarrival time on waiting times and passenger processing efficiency, particularly during peak hours. The results emphasize the substantial influence of these variables on waiting times, total exits, and system duration for passengers and buses.

In response to the rapid spread of Covid-19 in Wuhan, China, the role of urban bus transit in accelerating epidemic transmission was investigated in this study. A modified susceptible–exposed–infective–removed model (F-SEIR) was developed to incorporate inter-regional population movements and in-vehicle transmission dynamics. The F-SEIR model leveraged detailed bus IC (integrated circuit) card data and GPS trajectories to simulate both passenger inter-region mobility and the epidemic transmission process within enclosed bus environments. The results showed that bus transit substantially accelerated the urban spread of the epidemic, as evidenced by the emergence of distinctive ‘fly dot’ clustering patterns. Importantly, the simulation indicated that restricting bus travel could have reduced the number of infections by approximately 18.6–28.3%, with earlier intervention strategies leading to even more significant declines in infection rates. The findings not only validate the F-SEIR model against the observed trends in Wuhan, but also provide executable insights for transportation managers and policy makers in optimising public transit operations during epidemics.

In this study, we evaluated the impact of introducing a new transportation system, bus rapid transit (BRT), on traffic congestion using a multi-agent simulation (MAS). The rapid urbanisation accompanying the development of cities worldwide, with a growing population of over one million people living in cities, is expected to result in increased traffic congestion. Therefore, addressing this problem has become increasingly urgent. One of the potential solutions is the BRT system, which has attracted considerable interest. However, research on its effectiveness in alleviating congestion has not been sufficiently conducted, which was the focus of this study.We conducted MAS using the tool Simulation of Urban MObility (SUMO), focusing on the Eastern Saitama region as a case study and evaluated the impact of congestion relief resulting from the introduction of BRT.We observed that the introduction of BRT had a positive impact on increasing the maximum traffic flow rate and contributed to congestion relief through the adjustment of BRT headways. Additionally, we obtained suggestions for further congestion relief by designing of dedicated BRT lanes. The outcomes of this study can be leveraged to provide strategic recommendations and decision-making support for road construction and BRT introduction plans.

The design of transit signal priority (TSP) systems requires knowledge of dwell-time distributions at bus stops within the block. Dwell-time trends are not well established in the literature despite the ubiquity of large sets of automated passenger count (APC) data. Additionally, the impact of dwell-time variability on TSP performance is not well studied, particularly with field-collected dwell-time data. This study first analyzes trends and distributions inherent in dwell-time data deduced from APC data. Dwell times vary from stop to stop and for each stop by time of day (TOD). Stops with the highest proportions of non-zero dwell time also had the highest dwell-time magnitudes and variability. For most stops, dwell-time data was closely fitted by inverse Gaussian, log-normal, power log-normal, Fisk (log-logistic), and Johnson’s SU distributions. The second part of the study used a simulation environment to evaluate the impact of dwell-time magnitude and variability on TSP performance at both far-side and near-side bus stops. For far-side bus stops, dwell time significantly impacted the bus arrival profile at the check-in detector and thus the selected TSP strategy. Higher dwell-time magnitudes and variability led to a higher share of an Early Green Phase (EG) which is not as effective as a Green Phase Extension (GE). At near-side bus stops, dwell-time variability induced more uncertainty in an estimated time of arrival (ETA) and significantly reduced TSP effectiveness especially for GE. TSP performance in terms of GE success, bus travel time, and side-street traffic delay was significantly better at far-side stops compared to near-side stops.

Linking urban bus transit analysis with traffic engineering contributes to safe and efficient movement of people. A simulation model capable of modelling passenger service at bus stops and traffic conditions around bus stops is an excellent tool in transit efficiency assessment. In the paper, the analysis focused on street segments between intersections with bus stops used by regular bus service, various other transit providers (private operators), and other users (taxis, passenger cars). Large numbers of minibuses of non-urban bus operators stopping at bus stops cause significant disruptions in the traffic flow. The apparent differences in the efficiency and operation of the stops designed for use by local buses and those used by other users required additional analyses. In the probabilistic and simulation models of bus stop operation developed so far, did not use car-following models for the modelling of the movement of buses and other vehicles at and in proximity of bus stops.  This theory is used in off-the-shelf traffic microsimulation software packages, but they do not allow a reliable representation of how bus stops operate under the deregulated service of passengers (oversaturated bus stops with a variable number of service channels). This study analyses the movement of buses and other vehicles at a bus stop area using a car-following model with fuzzy logic applied for parameter estimation. A microscopic simulation model was built and tested. The selection of the shape of fuzzy sets and membership functions was based on multiple simulation runs. The model simulates queuing and delays imparted on buses and traffic flow in lanes adjacent to bus stops used by city buses and other transit providers. The simulation results were compared with the real-world processes with the use of the author's two-stage method. Verification based on the PROC and SDDIST indicators showed that the simulated and observed distributions of travel time and delay were highly consistent, with maximum deviations below approximately 10%. The analysis also confirmed that the model accurately reproduces average delays caused by bus queues and vehicle interactions near shared-use stops. The analyses demonstrated that the fuzzy logic-based car-following model proposed in this study is suitable for planning, designing, and relocating urban bus stops used by various operators. The feasibility of the developed model and directions of its further development were evaluated.

This study aims to analyze the effectiveness of the integration of the Bus Rapid Transit (BRT) system with feeder transportation in improving the connectivity and accessibility of public transportation in Medan City. The research methods used include field surveys, interviews, and spatial analysis based on Geographic Information Systems (GIS) to map the transportation network and assess the scope of services. The analysis was carried out by comparing the existing conditions of the BRT (Corridors 2 and 3) and the results of the simulation after the integration of five feeder routes (A2, A3, A6, A7, and A8). The results show that the integration of feeder routes is able to increase service coverage from 57.84 km² to 128.84 km² (an increase of 122.8%), as well as expand the served area from 23 to 44 zones, with an increase in service ratio from 26% to 57%. In addition, the average distance to the bus stop decreased from 1.2 km to 0.6 km, and the route overlap was reduced by 40%. Spatially, areas with high accessibility (<500 m from bus stops) have increased significantly in city centers such as Merdeka Square and Petisah Market. This study concludes that the integration of BRT and feeder is an effective strategy to realize a sustainable, efficient, and inclusive transportation system in the city of Medan. The implementation of a rotating operating system is also recommended to optimize the fleet without the need for the addition of new vehicles.

No abstract available

No abstract available

With a surge in the number of vehicles, urban traffic congestion has increased in recent years. This has led to increased travel times and decreased accessibility and mobility. One option to mitigate this issue is to promote the use of public transport, including buses. To encourage the use of buses, there is a need to provide reliable travel time and arrival information to commuters.In this study, we propose and develop predictive models to predict bus journey and arrival times based on historical AVL/GPS data, bus route and bus stop information. There were two parts to this study. The first was to predict overall journey times and the second was to predict bus arrival times at bus stops.To estimate total bus journey times, three models were developed using Linear Regression, Artificial Neural Network (ANN) and Long Short Term Memory Network (LSTM). Evaluation on a ground-truth dataset shows that LSTM outperformed the Linear Regression model and its performance was comparable to that of ANN. To predict bus arrival times at bus stops, three different models, namely Historical Averaging, Linear Regression and Gradient Boosting are proposed. Experimental results show that Gradient Boosting outperformed the other models and is more robust in predicting arrival times.Our study supports the idea that it is possible to predict bus journey time with reasonable accuracy using historical GPS observations and bus route information only.

Efficient public transportation is essential for sustainable urban mobility and achieving the 20-minute city vision. This paper presents a deep learning-based framework for accurately predicting the Estimated Time of Arrival (ETA) of buses using real-world GPS data from Ulaanbaatar’s metropolitan transit system. The study evaluates multiple models—including Fully Connected Multi-Layer Perceptron (FCMLP), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Random Forest, and ensemble methods—on both single-route and city-wide (139-route) datasets. Results show that deep learning models trained on individual routes achieve high accuracy (R2 ≈ 0.93, MAE ≈ 18.5 seconds), effectively capturing localized spatiotemporal patterns. On the city-wide dataset, the FCMLP model achieves the best performance (R2 = 0.98, MAE = 20.54 seconds). In contrast, the GPS-sequence-based LSTM model yields lower performance (R2 = 0.66, MAE = 100.43 minutes). These findings highlight the effectiveness of route-specific modeling and structured feature engineering. The proposed approach offers practical insights for improving transit reliability, adaptive scheduling, and real-time passenger information, supporting data-driven planning for resilient and accessible urban transportation systems.

The use of buses for transportation is significant in contemporary life and is becoming more and more widespread. The usage of private automobiles, fuel consumption, and traffic congestion are reduced if the buses arrive on time. The capability to predict real-time arrival times is highly beneficial for both passengers and transportation authorities. It cuts down the amount of waiting time they have to endure while travelling and gives them the gratification of being aware of the bus timetable. This demands a model that can inform the passengers about the arrival time of the vehicles, so that they can make their transit plans. With the development of this model, more people could be attracted to the public transportation which then reduces the congestion of roads due to excess private vehicles. In recent times, the proliferation of wireless communication technologies and the widespread use of Global Positioning System (GPS) have resulted in the generation of vast amounts of vehicle trajectory data. This data opens up new possibilities for accurately predicting real-time vehicle arrival times. In this paper, we propose a modern public transportation with IoT enabled system to give an accurate prediction of arrival time and also the location of the transport or vehicle to the particular bus stops. In this context, the Long Short Term Memory (LSTM) neural network is being employed. It is trained using various traffic parameters and environmental conditions to enhance its prediction capabilities for real-time vehicle arrival times. Parameters that are considered in the proposed system include distance, waiting time at stops, traffic density and road junctions.

Public transport systems often face challenges related to reliability and efficiency, leading to inconvenience and uncertainty for passengers. Existing solutions for real-time bus monitoring typically rely on expensive Internet of Things (IoT) components. This paper presents Track N Go, a cost-effective alternative for real-time monitoring of public buses and taxis using mobile phone location data. The system utilizes a robust backend system built with Java and React.Js for the user interface. Integration of GPS via the Map Box API and Firebase database ensures accurate location tracking. Track N Go provides accurate real-time monitoring, addressing challenges associated with public transport and improving overall urban mobility. The system enhances convenience and peace of mind for passengers by delivering reliable and user-centric solutions. The evaluation of Track N Go demonstrates its effectiveness in improving urban mobility and transit services. By offering a reliable and cost-effective solution for real-time bus monitoring, Track N Go aims to streamline daily commutes and make public transport more efficient and predictable.

The ‘gps2gtfs’ package addresses a critical need for converting raw Global Positioning System (GPS) trajectory data from public transit vehicles into the widely used GTFS (General Transit Feed Specification) format. This transformation enables various software applications to efficiently utilize real-time transit data for purposes such as tracking, scheduling, and arrival time prediction. Developed in Python, ‘gps2gtfs’ employs techniques like geo-buffer mapping, parallel processing, and data filtering to manage challenges associated with raw GPS data, including high volume, discontinuities, and localization errors. This open-source package, available on GitHub and PyPI, enhances the development of intelligent transportation solutions and fosters improved public transit systems globally.

No abstract available

No abstract available

No abstract available

Accurate arrival time estimation and demand aware vehicle allocation are foundational for a dependable public transit experience. This paper presents Easiway, an end-to-end learning-based framework for stop level ETA prediction and near-term demand estimation aimed at for campus and urban bus fleets. The design is intentionally software first: models are trained on historical GPS traces and route metadata, while the architecture supports later integration with IoT telemetry (GNSS trackers, OBD-II, passenger counters). We evaluate Linear Regression, Support Vector Regression, Random Forest, and Gradient Boosting on a realistic synthesized dataset. Gradient Boosting (our proposed model) attains the best performance (MAPE 6.7%, RMSE 1.92 minutes, R2 = 0.95), demonstrates resilience against missing telemetry, and provides a practical path for field pilots. The manuscript follows the exact structure of the provided reference-style conference paper: problem identification, literature survey, proposed methodology, algorithmic details, results, and deployment considerations.

ABSTRACT The goal of this study is to create a dynamic model that can accurately forecast the estimated time of arrival of a bus at a specific bus stop using data obtained from the global positioning system (GPS) in Addis Ababa, Ethiopia. Both operators and customers use accurate and timely bus arrival information. In turn, it helps determine the correct placement of charging stations when green-energy vehicles are introduced in the urban mass transit system. A plethora of machine learning models have been used for prediction. Additionally, we tailored an ensemble method based on the average prediction. The performances of these machine learning methods were estimated and compared using conventional measures, such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R2) values. The results showed that the performance of the Random Forest technique used in this study was impressive, with MAE of 0.137, MSE of 0.054, RMSE of 0.233, and R2 value of 0. 999. The findings demonstrate that the proposed method is reliable for predicting the arrival times of urban and rural buses. Next, in order to position the charging points for Electric Vehicles (EV) along specific bus routes, self-organising map (SOM) is employed to optimise EV charging point placement locations, and the result signify better performance than the kNN and DBSCAN clustering approaches.

The real-time information services make the public transit system more user-friendly improving the quality and availability of information, supporting needs of passengers in single and multi-modal journeys. As part of a public transport arrival notification system currently ongoing in Severodonetsk, Ukraine, an experimental study has been conducted on forecasting the arrival time of the trolleybuses. This paper discusses the process of developing arrival time estimation algorithms, including remote access configuration, GPS data acquisition, route assigning, algorithm formulation, data processing and calculation of the predicted arrival time. To improve the results of the predicted arrival time of the vehicle to the city's stops the linear approximation of the routes has been performed. Three methods as haversine, Vincenty's method, and the Euclidean distance were used to calculate the distance and a comparison with the actual length of the route. Our results show that for IoT applications at the site where the study is being conducted, the haversine formula with route linearization is most applicable to the performance of an algorithm.

Automated Bus Announcement Systems play a vital role in improving public transportation by providing real-time information to passengers regarding bus arrivals, departures, and route changes. These systems enhance the overall passenger experience, particularly for individuals with disabilities, by offering audible and visual announcements in buses and at bus stops. ABAS relies on technologies such as GPS, wireless communication, and integrated software for real-time tracking and data processing. Artificial Intelligence (AI) and Machine Learning (ML) have been increasingly integrated into these systems, allowing for more accurate predictions of arrival times, route optimization, and dynamic updates in case of traffic delays or detours. Research in ABAS has focused on improving the system's responsiveness, accuracy, and integration with other smart city infrastructures. The use of advanced algorithms, realtime data fusion, and cloud-based solutions have demonstrated the potential to improve both operational efficiency and passenger satisfaction. Future innovations are aimed at increasing system scalability, enhancing accessibility features, and leveraging AIdriven solutions to anticipate and manage transportation needs dynamically, contributing to the future of smart public transport systems.

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

Improving travel time prediction for public transit effectively enhances service reliability, optimizes travel structure, and alleviates traffic problems. Its greater time-variance and uncertainty make predictions for short travel times (≤35min) more subject to be influenced by random factors. It requires higher precision and is more complicated than long-term predictions. Effectively extracting and mining real-time, accurate, reliable, and low-cost multi-source data such as GPS, AFC, and IC can provide data support for travel time prediction. Kalman filter model has high accuracy in one-step prediction and can be used to calculate a large amount of data. This paper adopts the Kalman filter as a travel time prediction model for a single bus based on single-line detection: including the travel time prediction model of route (RTM) and the stop dwell time prediction model (DTM); the evaluation criteria and indexes of the models are given. The error analysis of the prediction results is carried out based on AVL data by case study. Results show that under the precondition of multi-source data, the public transportation prediction model can meet the accuracy requirement for travel time prediction and the prediction effect of the whole route is superior to that of the route segment between stops.

No abstract available

No abstract available

No abstract available

Abstract— BharatRide is a General Transit Feed Specification (GTFS)–based smart bus tracking and route planning system designed to enhance the usability of public transportation in Indian cities. The system integrates real-time Global Positioning System (GPS)–based bus tracking, Estimated Time of Arrival (ETA) prediction, and intelligent route planning within a scalable cloudbased architecture. The proposed platform utilizes Flutter for cross-platform mobile application development, Node.js with Express for backend services, MongoDB and Firebase for data management, and OpenStreetMap for route visualization. Machine learning modules can be incorporated to enhance ETA accuracy and support crowd estimation using historical travel data. The system aims to improve commuter experience, operational transparency, and decision-making in urban public transportation systems. Keywords— Smart Transportation, General Transit Feed Specification (GTFS), Real-Time Bus Tracking, Estimated Time of Arrival (ETA), Route Planning, Intelligent Transportation System, Cloud-Based Architecture

Transit signal priority (TSP) has become an increasingly popular way to tackle bus operation issues. Many efforts have been conducted to design TSP strategies, yet challenges still exists in real-life applications due to the difficulty in realizing the control logics and the limitation of road infrastructures. This paper proposes a novel TSP strategy considering lane sharing and real-time bus arrival time prediction. First, a right-turn lane sharing method is presented, it shares the right-of-way of a dedicated right-turn lane with through buses at the approaches of a signalized intersection. Next, a control logic based on phase insertion is proposed, and the new signal plan for next signal cycle is generated by judging the requirement of an exclusive bus phase based on predicted bus arrivals. Finally, the Kalman filter is used to establish a bus arrival time prediction model by using RFID and GPS data. The proposed method was implemented on an arterial road of real-life traffic network in Kunshan, China. Test results show that the proposed TSP strategy can achieve satisfactory performances. Bus delay decreases significantly compared to the general traffic delay, especially in peak hours. Further investigation shows that the findings of sensitivity analysis can provide beneficial guidance for practical applications.

Accurate expected time of arrival (ETA) information is crucial in maintaining the quality of service of public transit. Recent advances in artificial intelligence (AI) has led to more effective models for ETA estimation that rely heavily on a large GPS datasets. More importantly, these are mainly cabs based datasets which may not be fit for bus based public transport. Consequently, the latest methods may not be applicable for ETA estimation in cities with the absence of large training data set. On the other hand, the ETA estimation problem in many cities needs to be solved in the absence of big datasets that also contains outliers, anomalies and may be incomplete. This work presents a simple but robust model for ETA estimation for a bus route that only relies on the historical data of the particular route. We propose a system that generates ETA information for a trip and updates it as the trip progresses based on the real-time information. We train a deep learning based generative model that learns the probability distribution of ETA data across trips and conditional on the current trip information updates the ETA information on the go. Our plug and play model not only captures the non-linearity of the task well but that any transit agency can use without needing any other external data source. The experiments run over three routes data collected in the city of Delhi illustrates the promise of our approach.

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

No abstract available

This article presents a part of the work being carried out under the Department of Science & Technology (DST)-funded project, titled Advanced Urban Public Transportation System. The solutions designed for real-time tracking of metro buses in urban areas of India, detecting bus-stops automatically, and predicting the arrival time of buses accurately are elaborated. The proposed system addresses the challenges related to GPS outage, unknown schedule and stoppages of buses, and unavailability of real time traffic information along the bus-route. The system is evaluated using multiple-trip data collected over a 32 kilometer long route during the peak and off-peak hour traffic conditions. The bus-stop detection accuracy of 75% (6 out of 8 bus-stops are accurately detected) could be achieved using an arbitrary set of trips conducted over the route. The arrival time prediction error of 7% (5 minutes) has been reported. The scalability assessment of the system shows that it can support the transit of more than ten thousand buses and over one million subscribers/commuters.

No abstract available

Developing countries suffer from traffic congestion, poorly planned road/rail networks, and lack of access to public transportation facilities. This context results in an increase in fuel consumption, pollution level, monetary losses, massive delays, and less productivity. On the other hand, it has a negative impact on the commuters feelings and moods. Availability of real-time transit information - by providing public transportation vehicles locations using GPS devices - helps in estimating a passenger’s waiting time and addressing the above issues. However, such solution is expensive for developing countries. This paper aims at designing and implementing a crowd-sourced mobile phones-based solution to estimate the expected waiting time of a passenger in public transit systems, the prediction of the remaining time to get on/off a vehicle, and to construct a real time public transit schedule.Trans-Sense has been evaluated using real data collected for over 800 hours, on a daily basis, by different Android phones, and using different light rail transit lines at different time spans. The results show that Trans-Sense can achieve an average recall and precision of 95.35% and 90.1%, respectively, in discriminating lightrail stations. Moreover, the empirical distributions governing the different time delays affecting a passenger’s total trip time enable predicting the right time of arrival of a passenger to her destination with an accuracy of 91.81%. In addition, the system estimates the stations dimensions with an accuracy of 95.71%.

No abstract available

This study investigates the optimization of passenger flow in high-density transit environments through discrete-event simulation, using BTS Siam station in Bangkok, Thailand, as a representative case. The Arena-based model simulated passenger movements across ticket vending machines, service counters, and fare gates under different operational conditions. The model was calibrated and validated using empirical data collected during peak and off-peak periods. Results indicate that modest infrastructure enhancements such as adding one vending machine, one manned counter, and one fare gate that can reduce waiting times by 28.6% on weekdays, 9.7% on weekends, and 11.6% during special events. These findings highlight the effectiveness of simulation tools for improving passenger flow efficiency within constrained urban transport hubs. Beyond the site-specific case, the study presents a scalable and adaptable framework for other multimodal or high-density transit systems, contributing to data-driven, cost-effective transport management and planning.

No abstract available

Accurate passenger flow forecasting is crucial in urban areas with growing transit demand. In this paper, we propose a method that combines advanced machine learning with rigorous time series analysis to improve prediction accuracy by integrating different datasets, providing a prescriptive example for passenger flow prediction in urban rail transit systems. The study employs advanced machine learning algorithms and proposes a novel prediction model that combines two-stage decomposition (seasonal and trend decomposition using LOESS–ensemble empirical mode decomposition (STL-EEMD)) and gated recurrent units. First, the STL decomposition algorithm is applied to break down the preprocessed data into trend terms, periodic terms, and irregular fluctuation terms. Then, the EEMD decomposition algorithm is employed to further decompose the irregular fluctuation terms, yielding multiple IMF components and residual residuals. Subsequently, the decomposed data from STL and EEMD are partitioned into training and test sets and normalized. The training set is utilized to train the model for optimal performance in predicting subway short-time passenger flow. The synthesis of these sophisticated methodologies serves to substantially enhance both the predictive precision and the broad applicability of the forecasting models. The efficacy of the proposed approach is rigorously evaluated through its application to empirical metro passenger flow datasets from diverse urban centers, demonstrating marked superiority in predictive performance over traditional forecasting methods. The insights gleaned from this study bear significant ramifications for the strategic planning and administration of public transportation infrastructures, potentially leading to more strategic resource allocation and an enhanced commuter experience.

No abstract available

Accurate short-term passenger flow prediction is critical for optimizing intelligent bus operations, yet it remains a challenging task due to the complex and dynamic nature of urban transit systems. Traditional statistical and machine learning approaches often struggle to capture nonlinear dependencies and spatial heterogeneity, leading to limited performance in real-world scenarios. To address these challenges, we propose a novel hybrid model—CNN-Transformer-ResLSTM-Attention—that integrates advanced deep learning architectures to enhance predictive capability. The model leverages Convolutional Neural Networks (CNNs) to extract land-use features surrounding bus stops, capturing spatial structures that significantly influence passenger demand. Historical passenger flow data is then incorporated to represent temporal dynamics, while the Transformer's multi-head attention mechanism enables effective modeling of intricate spatiotemporal dependencies. To further strengthen predictive accuracy and stability, the Transformer decoder is redesigned with residual Long Short-Term Memory (ResLSTM) layers combined with an attention mechanism, connected through residual pathways to ensure efficient gradient flow and feature preservation. Extensive experiments conducted on datasets from ten representative bus stations in Beijing demonstrate the superior performance of the proposed framework. The model achieves over 87% prediction accuracy, consistently surpassing six benchmark methods across multiple evaluation metrics. Beyond its empirical performance, the framework offers a robust and scalable solution adaptable to diverse urban contexts, providing valuable insights for the intelligent scheduling, resource allocation, and long-term optimization of public transportation systems.

No abstract available

No abstract available

To improve the accuracy of urban rail transit passenger flow prediction, this paper proposes a prediction model for urban rail transit passenger flow based on data mining. Firstly, factor analysis (FA) is used to model and analyze historical data affecting passenger flow to determine common factors and calculate scores. These common factor scores are then used as inputs, combined with the PSO-BP network prediction model for passenger flow forecasting. The forecast results of this model are compared with the prediction results of the PSO-BP model, and it is found that the forecast results of this model are closer to the actual passenger flow.

No abstract available

This paper aims to analyze the influence mechanism of built environment factors on passenger flow by predicting the passenger flow of Shenzhen rail transit in the morning peak hour. Based on the classification of built environment factors into socio-economic variables, built environment variables, and station characteristics variables, eight lines and one hundred sixty-six stations in Shenzhen Railway Transportation are taken as research objects. Based on the automatic fare collection (AFC) system data and the POI data of AMAP, the multiple regression model (OLS) and the geographically weighted regression (GWR) model based on the least squares method are established, respectively. The results show that the average house price is significantly negatively correlated with passenger flow. The GWR model considering the house price factor has a high prediction accuracy, revealing the spatial characteristics of the built-up environment in the administrative districts of Shenzhen, which has shifted from the industrial structure in the east to the commercial and residential structure in the west. This paper provides a theoretical basis for the synergistic planning of house price regulation and rail transportation in Shenzhen, which helps to develop effective management and planning strategies.

No abstract available

: Accurate prediction of short-term passenger flow in urban rail transit systems plays a crucial role in optimizing operations and enhancing passenger experience. This study presents a scientific approach to predict subway passenger flow by analyzing characteristic patterns, identifying key factors influencing passenger flow changes, and leveraging relevant data sources. The multi-source data used in this study are described and pre-processed to capture the spatial, temporal, and other factors that contribute to subway passenger flow distribution. Utilizing the extracted features as inputs, an improved Long Short-Term Memory (LSTM) method is employed for short-term passenger flow prediction. The performance of the improved LSTM method is compared and analyzed against traditional methods. The results demonstrate that the proposed approach outperforms traditional methods in terms of prediction accuracy for the same prediction target. Furthermore, the fusion of multi-source data and the inclusion of external factors significantly enhance the prediction accuracy. This research highlights the importance of considering various factors and data sources when forecasting short-term passenger flow in urban rail transit systems. By employing an improved LSTM method and integrating multiple data dimensions, the proposed approach offers superior prediction accuracy compared to traditional methods. The findings contribute to the development of efficient and reliable prediction models for optimizing urban rail transit operations and improving passenger services.

This study delves into the realm of urban rail transit systems, leveraging unsupervised learning techniques to analyze passenger flow characteristics and unearth travel patterns. Focused on the dynamic and complex nature of urban rail networks, the research utilizes extensive datasets, primarily derived from Automated Fare Collection (AFC) systems, to provide a comprehensive analysis of passenger behaviors and movement trends. Employing advanced algorithms like DBSCAN, the study categorizes passengers into distinct groups, including tourists, shoppers, thieves, commuters, and station staff. These classifications reveal intricate patterns in travel behaviors, significantly contributing to a deeper understanding of urban transit dynamics. The findings offer valuable insights into peak travel times, popular routes, and station congestion, highlighting potential areas for operational improvements and infrastructure development. The study’s application of unsupervised learning in analyzing vast, unstructured data sets a precedent in urban transportation research, showcasing the potential of artificial intelligence in enhancing the efficiency and sustainability of urban transit systems. The insights garnered are pivotal not only for optimizing current operations but also for shaping future expansion and adaptation strategies, ensuring urban rail systems continue to meet the evolving needs of growing urban populations.

With the progression of smart urbanization, passenger flow prediction has emerged as an in- 1 tegral component of urban rail transit. To comprehensively characterize the essence of passenger flow prediction in urban rail transit, this paper focuses on modeling short-term prediction issues. Firstly, mathematical definitions are given for line network and station passenger flow, Origin-Destination (OD) passenger flow, and sectional passenger flow. Based on this foundation, a comprehensive mathematical modeling of short-term passenger flow prediction is conducted. Finally, this paper 6 summarizes the advantages, disadvantages, and conducts a comparative analysis of methods for short-term passenger flow prediction. Through mathematical modeling and comparative analysis of methods, this paper presents a comprehensive modeling framework for short-term passenger flow prediction. It decomposes the problem into more specific components, facilitating a profound understanding of its complexity and offering clear directions for diverse research aspects.With the continuous expansion of subway construction and the rapid development of intercity railways in urban areas, the subway network is becoming increasingly complex and the operating entities are becoming increasingly diverse. It is becoming increasingly urgent to establish an objective, fair, and reasonable ticketing system. The core issue is the allocation of travel routes under various transfer modes. This paper propose a rail transit network model based on station, route, network topology, and line vehicle dispatch information, which includes in-station and out-station travel time, transfer travel time, waiting time, and driving time. Furthermore, the influencing factors of each part of the travel time were analyzed, and theoretical analysis and simulation experiments revealed the impact of the randomness of travel time on passenger travel time under the constraint of exact vehicle entry and exit times.

No abstract available

With the increasing frequency of precipitation events under global warming, understanding rainfall-induced disruptions to urban mobility has become increasingly important. While prior studies primarily focus on road traffic, the lagged and threshold effects of rainfall on urban rail transit (URT) passenger flow remain insufficiently explored. This study analyzes 109 days of automatic fare collection data from Tianhe District, Guangzhou, in combination with hourly meteorological records and station-level built environment attributes. A rainfall threshold-aware gradient boosting framework is proposed to capture nonlinear response regimes, and an explainable learning approach is used to quantify the relative importance of rainfall, temporal factors, and built environment characteristics. The proposed framework outperforms the baseline model, with the root mean squared error (RMSE) and mean absolute error (MAE) reduced by over 5.38% and 5.93%, respectively. Results further indicate that lagged rainfall intensity exerts the strongest influence on passenger flow variation, with impact magnitudes varying systematically across station types. These findings enhance understanding of the nonlinear, time-dependent effects of rainfall on URT demand and provide practical guidance for passenger flow management and operational planning under rainfall conditions.

To address insufficient accuracy in public transit station passenger flow prediction, this study proposes a hybrid deep learning approach based on station classification using EMD-GCN-BiGRU. The method incorporates Dynamic Time Warping distance measurement with K-means clustering to classify stations based on temporal flow characteristics; applies Empirical Mode Decomposition to mitigate noise interference in original flow data; and constructs a deep learning framework integrating Graph Convolutinal Networks and Bidirectional Gated Recurrent Units to effectively capture spatial topological relationships between stations and temporal dependency features for category-specific predictions. Validation using Beijing bus card data demonstrates that transit stations can be classified into four categories based on weekday and non-weekday flow patterns: commuter-dominated, low-flow steady-state, multi-functional mixed, and evening outbound-dominated. Compared to baseline models, the proposed method improves R² by 0.01-0.31, reduces MAE by 0.12%-11.77%, and reduces RMSE by 1.97%-12.43%. Prediction accuracy is significantly enhanced after station classification compared to non-classified predictions.

Passenger flow control and bus bridging are used widely in the operations and management of urban rail transit to relieve the pressure of urban rail transit passenger flow, especially in peak periods. This paper presents an optimization method based on time‐varying running time in links. We first develop a mixed integer nonlinear programming model seeking to achieve the minimum total passenger travel time and operation cost. An optimization network and an algorithm are then designed to solve the model. We use the developed method to solve both a small‐scale simulated case study and a real‐world case study involving the Chengdu Metro. The results obtained by the designed algorithm are comparable with those obtained by the CPLEX solver but with a shorter calculation time. The results show that parallel bus bridging can effectively reduce the number of waiting passengers. A sensitivity analysis of weight suggests that the algorithm successfully balances passenger travel cost and operating cost while incorporating time‐varying running times leads to more realistic and dynamic infrastructure planning. This work contributes to the development of intelligent urban rail and road infrastructure systems, promoting safer and more efficient public transport operations.

No abstract available

In the rapid development of public transportation led, the traffic flow prediction has become one of the most crucial issues, especially estimating the number of passengers using the Mass Rapid Transit (MRT) system. In general, predicting the passenger flow of traffic is a time-series problem that requires external information to improve accuracy. Because many MRT passengers take cars or buses to MRT stations, this study used external information from vehicle detection (VD) devices to improve the prediction of passenger flow. This study proposed a deep learning architecture, called a multiple-attention deep neural network (MADNN) model, based on historical MRT passenger flow and the flow from surrounding VD devices that estimates the weights of the vehicle detection devices. The model consists of (1) an MRT attention layer (MRT-AL) that generate hidden features for MRT stations, (2) a surrounding VD (SVD) attention layer (SVD-AL) that generate hidden features for SVD devices, and (3) an MRT-SVD attention layer (MRT-SVD-AL) that generate attention weights for each VD device in an MRT station. The results of the investigation indicated that the MADNN model outperformed the models without multiple-attention mechanisms in predicting the passenger flow of MRT traffic.

For sophisticated management, advertisement placement, and epidemic prevention control of urban rail transit (URT), accurate and real-time predictions of passenger flows at different levels are of great importance. Unlike traditional prediction tasks, hierarchical prediction (HP) requires that the hierarchical constraints be satisfied as much as possible (the sum of the predicted passenger flow of child nodes should nearly equal the parent node) to achieve realistic predictions. This article proposes a multiobjective HP (MOHP) framework with an error compensation (EC) mechanism for predicting URT passenger flow with a hierarchical structure. Three components are included: the initial prediction module, the EC module, and the hierarchical coordination module. In the initial prediction module, the initial passenger flow prediction of each layer is carried out. The EC model is developed based on proportional-integral-derivative control to compensate for the initial predicted value of every layer. As a final step, a trainable HP model is constructed based on deep learning to coordinate the prediction values of each layer. As examples, we construct three scenarios of passenger flow hierarchy based on the URT system in Wuxi, China. The constructed prediction framework is used to conduct experimental analyses. As a result, the MOHP-EC prediction framework could satisfy the hierarchical constraints and use the passenger flow hierarchical information to reduce prediction errors. The mean absolute error was reduced by 35%, and the root-mean-square error was reduced by 39%.

Accurate and real-time passenger flow prediction of rail transit is an important part of intelligent transportation systems (ITS). According to previous studies, it is found that the prediction effect of a single model is not good for datasets with large changes in passenger flow characteristics and the deep learning model with added influencing factors has better prediction accuracy. In order to provide persuasive passenger flow forecast data for ITS, a deep learning model considering the influencing factors is proposed in this paper. In view of the lack of objective analysis on the selection of influencing factors by predecessors, this paper uses analytic hierarchy processes (AHP) and one-way ANOVA analysis to scientifically select the factor of time characteristics, which classifies and gives weight to the hourly passenger flow through Duncan test. Then, combining the time weight, BILSTM based model considering the hourly travel characteristics factors is proposed. The model performance is verified through the inbound passenger flow of Ningbo rail transit. The proposed model is compared with many current mainstream deep learning algorithms, the effectiveness of the BILSTM model considering influencing factors is validated. Through comparison and analysis with various evaluation indicators and other deep learning models, the results show that the R2 score of the BILSTM model considering influencing factors reaches 0.968, and the MAE value of the BILSTM model without adding influencing factors decreases by 45.61%.

 In recent years, cities have been increasingly confronted with frequent and severe extreme weather events, such as heavy rainfall, high temperatures, and strong winds. These extreme weather conditions not only impact urban transportation operations but also directly affect passengers' travel patterns and behaviors. In this context, gaining a deeper understanding of the mechanisms through which weather factors influence urban subway passenger flow becomes crucial. This study aims to investigate the relationship between passenger flow and weather factors, and provide valuable insights for urban rail transit management to enhance proactive decision-making. To achieve this research objective, we first establish a framework for studying the impact of weather on passenger flow. Based on this framework, an analysis is conducted using passenger flow data and weather data from Beijing Metro Line 4. The findings of this study reveal significant effects of different weather factors on subway passenger flow. Increasing severity of weather conditions and higher wind speeds have a negative influence on passenger flow, leading to a decrease in ridership. Conversely, a significant positive correlation is observed between the highest temperature and subway passenger flow, indicating that as the highest temperature rises, the passenger volume also increases.

With the increasing economic development of China, the country encourages to develop public transport strongly, and urban rail transit has become a choice for more and more cities. But for rail transit operations, passenger flow prediction is becoming more and more important and has become a key issue in transportation planning. However, the effect of a single model on predicting short-term passenger flow is not ideal. Therefore, this study proposes a combined model based on GA-BP neural network and forecasts the passenger flow of Suzhou Urban Rail Transit Line 1 according to weather, holidays, and other factors. Meanwhile, the study compares with the ARIMA and BP neural network models. The results show that the accuracy of GA-BP model improved by 6.06% and 8.69% respectively which compared with the former, and the results have improved the accuracy of passenger flow prediction effectively. It is proved that the combined model has certain practical value.

Passenger flow forecasting is crucial for optimizing urban transit operations, especially in developing countries such as India, where congestion, infrastructure constraints, and diverse commuter behaviors pose significant challenges. Despite its importance, limited research explored forecasting models for Indian urban transit systems, particularly incorporating the effects of holidays and disruptions caused by the COVID-19 pandemic. To address this gap, we propose TBATS Boosting, a novel hybrid forecasting model that integrates the statistical strengths of trigonometric, Box–Cox, ARMA, trend, and seasonal (TBATS) with the predictive power of LightGBM. The model is trained on a five-year real-world dataset from e-ticketing machines (ETM) in Thane Municipal Transport (TMT), incorporating holiday and pandemic-related variations. While Route 12 serves as a primary evaluation route, different station pairs are analyzed to validate their scalability across varying passenger demand levels. To comprehensively evaluate the proposed framework, a rigorous performance assessment was conducted using MAE, RMSE, MAPE, and WMAPE across station pairs characterized by heterogeneous passenger flow patterns. Empirical results demonstrate that the TBATS Boosting approach consistently outperforms benchmark models, including standalone SARIMA, TBATS, XGBoost, and LightGBM. By effectively capturing complex temporal dependencies, multiple seasonalities, and nonlinear relationships, the proposed framework significantly enhances forecasting accuracy. These advancements provide transit authorities with a robust tool for optimizing resource allocation, improving service reliability, and enabling data-driven decision making across varied and dynamic urban transit environments.

No abstract available

With the expansion of urban rail transit network, the passenger demand becomes more uneven and complex. An accurate passenger flow forecasting of urban rail transit is important for both operation planning and service quality improvement. This paper proposes a passenger flow forecasting method based on prophet-GRU combined model. Firstly, Seasonal- Trend-Loss decomposition is used to decompose the urban rail transit passenger flow time series into trend, seasonal and residual terms. Then, on the basis of STL decomposition, prophet model is established for the trend and seasonal terms, GRU model is established for the residual terms as well. Taking the Nanjing Metro Line Network as the example, all the prediction results are obtained by linear integration. The results show that the weighted accuracy of passenger flow prediction reaches 96.13% for 159 stations. The root mean square error (RMSE) of the combined Prophet-GRU model is at least 49.69% lower and the mean absolute error is at least 19.00% lower compared to the ARIMA, GRU, and Prophet models.

Emergencies often lead to multi-modal and unbalanced distribution of urban rail transit passenger flows. Aiming at this problem, a emergency control method of multi-modal passenger flow is proposed under the premise of comprehensively considering the operation cost and passenger travel efficiency of urban rail transit(URTS).The main work includes: 1) From the perspective of train scheduling, designing and developing a contingency strategy for multi-modal passenger flow by combining the train operation plan based on full-length and short-turn routing, station passenger flow restrictions, and dynamic train departure intervals; 2) From the perspective of train operation and passenger travel synergy, the emergency control model of passenger flow is established with the objective of minimizing the total train operation time and average passenger waiting time; 3) A multi-agent deep reinforcement learning(MDRL) method with a new action selection, reward and double loop mechanism-ARDQMIX is proposed to realize emergency autonomous perception and control of passenger flow in urban rail transit. The simulation results show that the emergency control method of multi-modal proposed in this study has a good utility for improving passenger travel efficiency and reducing operation cost. Note to Practitioners—Urban rail transit system(URTS) is punctual, fast, safe and large capacity, and has gradually become the preferred means of transportation for passengers. However, due to the rapid growth of travel demand, the URTS in the morning and evening peak hours traffic problems are particularly serious, will produce a multi-modal passenger travel demand, such as can not be quickly alleviated, the traffic problem will be caught in a vicious circle, leading to the urban rail transit system service capacity decline, and even lead to the potential safety problems. Aiming at this problem, a emergency control method of multi-modal passenger flow is proposed under the premise of comprehensively considering the operation cost and passenger travel efficiency of URTS.

In the construction of urban rail transit, the space-time distribution of average daily passenger flow in the traffic network is analyzed based on important indicators such as average daily passenger flow, average passenger flow and congestion flow. Based on the data indicators, the organization and management of rail transit line connection should be planned, designed and operated more reasonably, which is to further enhance the technicality of the rail transit operation. It is one of the effective methods to predict the average daily passenger flow of the running track in some periods basing on the distribution characteristics of the average daily passenger flow and the variation model. The model established in this paper first sets the entrance and exit of the subway station as the space trajectory. Then, it regards the fixed parameters as the local function variables, and considers the real-time dynamic parameters as the external function. Considering the characteristics of the external function parameters in space, it fits with the time model accuracy, and dilutes the parameter function. Considering the driving effect of urban subway on the overall traffic environment, the genetic variation is carried out in the spatial and temporal trajectories. The local and global prediction variables are mixed with the change of time and geographical location, which has influenced the average daily commuting passenger flow. The research content of this paper can formulate rail transit travel plans suitable for passenger demand and formulate access management rules for subway stations. It also optimizes station traffic rate, thereby reducing operating costs, improving the return on investment in subway operation, and giving full play to the contribution of the urban rail transit construction.

Accurate prediction of passenger flow can provide an important basis for the operation and management of urban rail transit. Previous models are based on the learning of static graph structures and cannot achieve the distinction of network structures by attention mechanism. In order to realize the learning of dynamic spatio-temporal characteristics of passenger flow and improve the accuracy of passenger flow prediction, a neural network model based on attention mechanism is proposed in this paper. It consists of a spatial attention module and a temporal attention module. The model uses three different coding strategies to enhance the learning capability of the attention mechanism for spatial location and structural features. In the temporal attention module, bi-directional GRU and attention are combined to extract dynamic changes in the temporal dimension of passenger flow data. Experiments on the Hangzhou Metro dataset demonstrate that this model outperforms the classical model.

Accurate prediction of station passenger flow is crucial for optimizing rail transit efficiency, but peak passenger flow in urban rail transit (URT) is often disrupted by random events, making predictions challenging. In this paper, in order to solve this challenge, the Bi-graph Graph Convolutional Spatio-Temporal Feature Fusion Network (BGCSTFFN)-based model is introduced to capture complex spatio-temporal correlations. A combination of a graph convolutional neural network and a Transformer is used. The model separately inputs land use (point of interest, POI) and station adjacency information as features into the BGCSTFFN model, using the Pearson correlation coefficient matrix, which is evaluated on real passenger flow dataset from 1 to 25 January 2019 in Hangzhou. The results showed that the model consistently provided the best prediction results across different datasets and prediction tasks compared to other baseline models. In addition, in tasks involving predictions with different combinations of inputs and prediction steps, the model showed superior performance at multiple prediction steps. Its practical application is validated by comparing the results of passenger flow prediction for different types of stations. In addition, the impact of these features on the prediction accuracy and the generalization ability of the model were verified by designing ablation experiments and testing on different datasets.

This paper studies accurate short-term prediction of urban rail transit passenger flow in external passenger transport hub. Based on the conventional features that affect external rail transit passenger flows, we propose an innovative method of statistical features construction to make accurate prediction of frequently fluctuating passenger flow under the framework of machine learning. Firstly, by classifying the statistical features in time-series, we improve the previous long-short-term memory(LSTM) network model and establish a novel long-short-term memory(LSTM) network model that can deal with long-term dependent time-series data so as to accurately fit real-time passenger flow. Secondly, by introducing the lightweight implementation algorithm LightGBM based on the gradient decision boosting tree(GBDT), we build a short-term prediction model, which can reduce operation cost and improve accuracy so that accurate fitting of passenger flow peaks can be achieved. Thirdly, based on K-nearest neighbor algorithm, we select DRS as the dynamic regression device that can find a local optimal fusion method, and establish a LGB-LSTM-DRS local optimal fusion prediction model. Taking the AFC passenger flow data of Chengdudong Station as an example, we predict the short-term passenger flow. Compare with other commonly used models such as LR, RF, and GBDT, it’s proved that the LGB-LSTM-DRS model has the smallest error (MAPE and RMSE) and the best prediction performance.

Urban rail transit network is composed of static network physical structure and dynamic train working diagram, whose accessibility evaluation should include both spatial and temporal characteristics. This paper proposed a comprehensive dynamic accessibility evaluation model of urban rail transit network. Its spatial characteristics were determined by station passenger flow, path impedance etc., while its temporal characteristics were defined by train departure intervals, train carrying passenger flow etc. And the dynamic accessibility index can be calculated through these factors, OD path accessible set and passenger route preference. Finally, Shanghai metro network was used as a case study to show the calculation process and analysis result of the proposed model. Result showed that the model could remedy the shortcoming that some traditional accessibility index models did not take into account temporal characteristics (metro service frequency, service level et al), and it could also give a reasonable allocation for urban rail transport capacity by analyzing the whole day dynamic accessibility index.

A station closure is an abnormal operational situation in which the entrances or exits of a rail transit station have to be closed for some time due to an unexpected incident. A novel approach is developed to estimate the impacts of the alternative station closure scenarios on both passenger behavioral choices at the individual level and passenger demand at the disaggregate level in a rail transit network. Therefore, the contributions of this study are two-fold: (1) A basic passenger behavior optimization model is mathematically constructed based on 0–1 integer programming to describe passengers’ responses to alternative origin station closure scenarios and destination station closure scenarios; this model also considers the availability of multi-mode transportation and the uncertain duration of the station closure; (2) An integrated solution algorithm based on the passenger simulation is developed to solve the proposed model and to estimate the effects of a station closure on passenger demand in a rail transit network. Furthermore, 13 groups of numerical experiments based on the Beijing rail transit network are performed as case studies with 2,074,267 records of smart card data. The comparisons of the model outputs and the manual survey show that the accuracy of our proposed behavior optimization model is approximately 80%. The results also show that our model can be used to capture the passenger behavior and to quantitatively estimate the effects of alternative closure scenarios on passenger flow demand for the rail transit network. Moreover, the closure duration and its overestimation greatly influence the individual behavioral choices of the affected passengers and the passenger demand. Furthermore, if the rail transit operator can more accurately estimate the closure duration (namely, as g approaches 1), the impact of the closure can be somewhat mitigated.

Regional rail transit is a comprehensive rail transit system with multiple standards that is formed to meet the needs of urban agglomeration economic integration. With the continuous development of regional rail transit, the connection between different standards and between stations continues to increase, and the ripple effect of transportation risks is more prominent. Therefore, in order to reduce the impact of transportation risks on the safety of the road network, it is urgent to evaluate and predict the dynamic transportation risks of the regional rail transit network from a global perspective. In response to this problem, this paper proposes a method for evaluating and predicting regional rail transit dynamic capacity risk based on dynamic passenger flow monitoring, and establishes an SVM-based capacity risk assessment and prediction model, and finally takes the rail transit network in Chengdu as an example to verify the effectiveness of this method.

No abstract available

This study presents the design and validation of a closed-loop control platform for rail transit construction. The platform integrates multi-source data, enables real-time prediction, and supports AI-driven scheduling, with strategy execution and feedback implemented via digital twins. A three-layer architecture is constructed, comprising edge sensing, cloud computing, and intelligent interaction. The system incorporates data fusion middleware, an AI decision engine, and a 3D digital twins module. The operational workflow follows the perception–fusion–prediction/optimization–execution/feedback loop: edge devices collect on-site status, cloud middleware integrates and serves the data, the AI engine performs prediction and scheduling optimization, and the digital twins layer validates strategies and dispatches execution to the front end. At the data modeling level, a Transformer-Encoder-based multimodal temporal fusion model is designed, and graph attention networks are employed for heterogeneous structure modeling. Apache Kafka and Flink handle streaming data to achieve high-frequency, low-latency processing. The intelligent analysis layer integrates a Spatio-Temporal Graph Convolutional Network for passenger flow and construction period prediction, a Shifted Window Transformer for image recognition, and the Proximal Policy Optimization (PPO) algorithm for task scheduling optimization. Field tests in an urban rail construction project show that the platform maintains 91.6% accuracy in passenger flow prediction under high-concurrency conditions and achieves 98.2% accuracy in image recognition. PPO-based scheduling reduces average task completion time by 27.4%. The system sustains an average response latency of 280 ms, peak throughput of 27,000 messages per second, and over 95% closed-loop execution success rate. These results indicate that the platform meets its design targets in prediction accuracy, response latency, and scheduling efficiency under real-world conditions, providing a foundation for informatization and intelligent upgrading in urban rail transit.

At present, urban rail transit has become one of the important transportation modes for residents of big cities due to its advantages of safety and efficiency, convenience and reliability, environmental protection and low carbon. With the gradual increase of traffic demand, urban rail transit has been developed rapidly. As an important node in the urban rail transit network, rail transit hubs are often susceptible to safety hazards due to high passenger flow, complex building structure and unreasonable emergency disposal plan, which can cause huge casualties and property losses in case of fire and other emergency emergencies. In this paper, the emergency evacuation planning path of urban rail transit hub is studied, combined with traditional genetic algorithm, a multi-level gene coding technology is proposed, and the crossover and mutation operations of traditional genetic algorithm are improved, so that it can complete the evolution of multi-level genes. In order to improve the evacuation efficiency in the subway station, this paper proposes comprehensive management measures and suggestions which consist of perfecting the evacuation management method, perfecting the setting of evacuation facilities and perfecting the evacuation guidance system. Among them, the evacuation management method should clearly address evacuation training and drills and enhance the operability of relevant emergency plans. The evacuation facilities should make the evacuation capabilities of exits and stairs meet the evacuation needs, and the layout of evacuation routes should be intuitive and clear. The use of the evacuation guidance system should be On the basis of the currently used broadcasting system, the role of the real-time information guidance system has been continuously strengthened.

No abstract available