Automatic Vehicle Location Research Articles

Self-calibrated transit service monitoring using automated collected data

This paper proposes a self-calibrated transit service monitoring framework that aims to obtain the performance of a transit system using automated collected data. We first introduce an event-based transit simulation model, which allows the detailed simulation of passenger travel behavior in a transit system, including boarding, alighting, and transfer walking. To estimate passenger path choices, we assume the path choices can be modeled using a C-logit model, and propose a simulation-based optimization model to estimate the path choice parameters based on automated fare collection and automated vehicle location data. The path choices can be estimated on a daily basis, which enables the simulation model to adapt to dynamic passenger behavior changes, and output more accurate network performance indicators for regular service monitoring such as train load, passenger travel time, and crowding at platforms. The proposed system eliminates the need for conventional monitoring equipment such as cameras at platforms and scaling/weighing systems on trains. The Hong Kong Mass Transit Railway (MTR) system is used as the case study. Results show that the model can well estimate the path choice behavior of passengers in the system. The output passenger exit flows are closer to the actual one compared to the two benchmark models (shortest path and uniform path choice).

Characterizing spatiotemporal patterns of bus bunching frequency on a bus route network: A case study of Taipei city

Bus bunching is a critical issue in bus operation management. This study investigated the impacts of potential factors affecting bus bunching on a city-wide bus route network, using Taipei City as an example with its 267 bus routes and 4741 bus stops. Frequency of bus bunching was measured on an hourly basis using Automatic Vehicle Location data. Multilevel count models based on Conway-Maxwell Poisson distributions were developed, and the spatiotemporal distributions of random intercepts and residuals were examined. The results showed that the effects of bus lane design, bus route network and operation, and traffic characteristics were consistent with those reported in prior studies. However, a quadratic relationship between bus route length, best measured by number of stops, and bus bunching was identified, which explains the conflicts between the theories of bus bunching propagation and self-repair. Bus route design often faces a dilemma between extending route length to collect additional passengers and reducing in-vehicle travel time to enhance service quality. The findings of the study could be a useful reference for bus route design to minimize bus bunching.

Impact of Station Design and Passengers Flow on Urban Rail Dwell Time: A Systemwide Analysis Using APC and AVL Data

In this paper, we investigated the impact on dwell time of station design, train load, and passenger flow, considering boarding fraction. We employed system-wide automated data sources including automatic passenger counting and automatic vehicle location data in the rail transit system in Calgary, Canada. Regression analyses were conducted to achieve accurate dwell time estimation by calculating passenger load per car, boarding, and alighting passengers per door, and also identifying the critical door with the highest demand. Observations for each critical door were divided based on the fraction of boarding passengers with respect to the sum of boarding and alighting. Six stations with distinct geometric designs were selected for comparison to assess their impact on dwell time. The results indicate that, for dominant boarding or alighting, a longer time is needed per passenger to alight or board, respectively. Our findings indicate that a station with a middle platform and two entrances positioned in the middle performed better in terms of dwell time in the case of alighting-dominant and mixed passenger flow. For stations experiencing boarding-dominant passenger flows, side platforms with multiple entrances at the ends and middle outperformed. Narrower platforms experienced significantly longer dwell times than other selected stations under similar demand. While the conclusion about the station design may not be generic, the proposed model provides a consistent and adaptable approach to study the impact of station design and passenger flows on urban rail dwell times, facilitating better-informed decision-making for station design or modification and enhancement of the overall rail system performance.

Logistic model for pattern inference of subway passenger flows based on fare collection and vehicle location data

With large volume of passengers boarding and alighting through subway platforms, the stations are getting crowded, resulting in drops in the level of service and safety concerns, especially for subway systems operating at capacity during peak hours. Thus, it is crucial for subway agencies to sense changes in travel demand and adjust their management schemes accordingly. In this paper we propose a statistical approach to estimate dynamic passenger flows with automated data. First, we develop a dynamic logistic model for calculating passenger tap-out times, which can be employed to infer passenger flow characteristics at the aggregate level. In addition, a new passenger-to-train assignment model for any subway route is derived based on the dynamic model. Subsequently, we apply an expectation-maximization algorithm to estimate the model parameters with automated fare collection and automated vehicle location data. Finally, a cross-validation method is employed to validate our approach with data obtained from several routes in Beijing subway system in China. Results of 95% prediction intervals indicate the effectiveness of the models and the proposed estimation methods.

Development of information systems in road transportation

Nowadays, we face many problems in the field of transport. The application of intelligent transport systems should improve problems related to congestion management, road safety, access to data in the transport environment, and environmental protection. The paper presents two concepts that are key to the improvement and development of the transport sector. The development and application of automatic vehicle location since the 1960s has led to an improvement in the efficiency of transport companies’ operations and the quality of their services. This technology has led to improved efficiency of the transport service, better utilisation of resources and improved quality of service. However, the most modern concept that initiates the improvement of existing solutions and encourages the development of new solutions in the field of transport is the IoT (Internet of Things) concept. In freight transport, the application of IoT technology enables cost management, reduction of CO2 emissions and avoidance of congestion through the use of alternative routes.

Does Crowding Have a More Complicated Effect on Public Transport Users with Respect to Perceived Travel Time?

The issue of crowding in public transportation has long been of concern. Numerous studies have been conducted to address this issue. It has become increasingly common to convert crowding to something more tangible, such as cost and time, in recent years. As a result of converting crowding into time, the concept of perceived travel time (PTT) has been introduced. Viewing crowding from the perspective of PTT may provide new insights into crowding and its effects. Therefore, in this study the PTT was calculated using the data obtained from both automated fare collection and automated vehicle location systems for the most heavily populated bus rapid transit (BRT) line in Tehran, the capital of Iran. A total of 429,000 PTTs were calculated, and then cluster analysis was used to determine that crowding has a significant effect on the PTT, not only for those who travel during peak hours, but also for those who travel during non-peak hours. Crowding therefore appears to have a more complex effect that persists over time. We conducted a time series analysis for some selected origin stops to test this theory. For stops intersected by other BRT lines or metro lines, the results suggest that the difference between PTT and nominal travel time for each block (stop-to-stop distance) increases over time, despite the start travel time not being chosen during peak hours for these stops. Based on the findings of our study, crowding could even affect travelers traveling during low-demand hours if viewed from the point of view of PTT. This effect is referred to as the “dynamic effect of crowding” in this paper.

Unsupervised Learning for Public Transport Delay Pattern Analysis

To analyze inherent and diverse patterns within line-based public transport daily delay occurrences, we introduce a data-driven exploratory analysis focused on the spatial-temporal distribution of these delays. Our approach relies on the utilization of the image pattern recognition technique and k-means clustering algorithm. We extract daily punctuality information from the automatic vehicle location data for a singular public transport route. This information is then translated into a visual representation through aggregated daily delay distribution profile images, offering insights into the spatial and temporal distribution of delays. The delay distribution finds expression in the arrangement of pixels within these profile images. The essence of these images is further distilled through image pattern recognition using the neural network architecture of ResNet50. Employing the k-means algorithm, we cluster these images based on their similarity, revealing five distinct daily delay patterns. The analysis of these patterns offers insight into their unique characteristics, yielding noteworthy outcomes. These findings hold the potential to provide public transport operators with an enriched comprehension of the dynamics of delays occurring on a specific line.

Using Wi-Fi Connection Data to Analyze Performance of the Subway System in Toronto, Canada

Typical performance measurements of public transit operations make use of vehicle-based data such as automated vehicle location data or passenger-based data at specific fare collection points. Ideally, the performance of a transit system from a reliability perspective and according to passenger experience should be measured through individual passenger journeys. The growing prevalence of smartphones provides one potential source for this analysis, because passive data collection methods such as obtaining Wi-Fi, cellular, and Bluetooth connection data allow us to observe devices as they move throughout the system. In this study we present a collection of methods and performance measures for using Wi-Fi connection data to measure various aspects of customer experience and reliability, including methods for detecting train arrivals at platforms, estimating wait times, measuring origin–destination travel time variation, and developing profiles of various journey types for comparison. In contrast with many other advances toward passenger-based measures, these methods do not require the combination of diverse data sets to generate useful results. These methods are applied to data from the Wi-Fi service in the subway system in Toronto, Canada.

A spatiotemporal analysis of metro‐stop based accessibility to bus services in Shanghai, China

AbstractGround‐level bus offers flexible services with relatively inexpensive fares and high‐level accessibility, thus is the dominant feeder mode for metro in the majority of metropolitan areas in China. Intermodal transfer between the metro and bus networks is therefore a crucial element in the successful operation of an integrated transit system. In this circumstance, a key challenge is lack of appropriate methodologies to evaluate the spatial–temporal disparities of intermodal transfers between metro and bus. To address this issue, this research aims to promote an existing two‐step floating catchment area (2SFCA) model by incorporating the temporal variability of service supply, demand, and travel time to provide a more realistic estimation of accessibility using smart card data and automatic vehicle location data. The proposed methodology was applied in a case study of the metropolitan area of Shanghai in the specific context of metro‐stop based accessibility to bus services. The results of the case study show that the daily fluctuations in output metro‐to‐bus transfer accessibility values are highly sensitive to temporal dynamics of transfer time, service supply, and demand. It is hoped the results output here could give planners and policymakers greater insight into spatiotemporal dynamics on transfer accessibility, and help to establish an effective and efficient integrated transit system.

Use of High-Resolution Signal Controller Data to Measure Transit Signal Priority Performance: A Case Study in the Boston Region

Automated traffic signal performance measures (ATSPMs) have been developed to organize data within a traffic signal, which will then be used to evaluate and monitor signal timing strategies. Past research has summarized the use of ATSPMs for performance-based management of a traffic signal system. The National Cooperative Highway Research Program Research Report 954 focused on many measures useful for general traffic, but did not consider transit agencies as specific stakeholders. ATSPMs do provide insights into measuring the number of preemption events, and the percentage of transit vehicles arriving on green, but additional information is needed to determine the effectiveness of transit signal priority or other transit preferential treatment strategies. This paper proposes a method for evaluating transit performance at signalized intersections more fully using the high-resolution data available within modern traffic signal controllers. The addition of transit-specific inputs within the ATSPM enumerations is used to produce transit-specific signal performance measures designed to be useful to practitioners. The methodology can be followed by other agencies seeking to enhance the capabilities of existing automatic vehicle location systems to further describe the performance at each signalized intersection. By incorporating transit into the ATSPM system, an agency can better assess the delay of buses, which can contribute to schedule adherence, on-time performance, and overall bus service. The methodology is presented as a prototype for further development and adaptation to individual agency objectives and data sources.

Application of Public Transit AVL Data for Evaluation of Delay Variability

The travel time is the significant factor in evaluating efficiency and performance of public transit system. A greater percentage of travel time is accounted by bus stop delays which depends on passenger count, bus stop characteristics, traffic condition, bus performance, etc. Many of the Indian transit agencies store the passenger details stage wise not stop wise, which makes it difficult to evaluate delay variability at bus stop level. In this connection, Automatic Vehicle Location (AVL) data from Intelligent Transport System (ITS) implemented at Mysore, India is considered for evaluating bus stop delay variability. The collected data is used for estimating delay at five stops by adopting trajectory-based formulation. The probability distributions have been utilized to model the variability in delay. The performance has been analysed using Kolmogorov-Smirnov (KS) test. The daily variability of delay at bus stops has been evaluated using Coefficient of Variation (COV). The results of the performance evaluation of delay distributions show that the Generalized Extreme Value (GEV) distribution is the best descriptor of the delay variability in terms of accuracy, robustness, and survival capacity. In the absence of passenger data collection systems, method of evaluation of delay using AVL data presented in this study is helpful.

Methodology to Detect Bus Stop Influence Zones Utilizing Facebook Prophet Changepoint Detection Method

Travel time of buses, a major part of the urban public transit system, is affected by various factors and foremost are the bus stops. In addition to the dwell time at the stop, the deceleration and acceleration zones reduce average speed, particularly in mixed traffic, and increase travel time. Several approaches are used in estimating the link-based travel time of public transit systems in transportation planning, but Bus Stop Influence Zones (BSIZs) are ignored. Moreover, fuel consumption and pollutant emissions increase in BSIZs, and this demonstrates the importance of BSIZs in measuring the performance of public transit systems as well as planning. Data obtained from the Automatic Vehicle Location system was used and visualized on Geographic Information System and data preprocessing steps were performed. Finally, changepoint detection method of Facebook Prophet (FBP-CDM) was exploited to identify changepoints in location-speed data on the selected route. Results were validated with real-life data and expert opinion, and then compared with the findings acquired by the K-means clustering. Based on the conclusions, FBP-CDM was found quite effective in detecting and predicting BSIZs accurately and the proposed methodology is useful for studies in transportation planning and operations.

Public Transport Commuting Analytics: A Longitudinal Study Based on GPS Tracking and Unsupervised Learning

This paper uses unlabelled GPS tracking data collected by a smartphone application, enriched by fusion with automatic vehicle location (AVL) data, to study commuting trips from home to work and vice versa. Such commuting trips play a significant part in public transport (PT), and in transport planning in general. This work investigates patterns of mobility, based on multiple thousands of recorded trips over a set of users in a longitudinal study by, first, determining unsupervised clustering algorithms to impute work and home locations, then analysing relevant characteristics, such as departure times, mode/line choice and trip duration. Finally, a heuristics algorithm is proposed to analyse the extent and frequency of similar trips. The results quantify amount and limits of the regularity of individual commuting behaviour in terms of repeatable travel choices. Commuters are quite consistent in their choices of departure times and lines used, even though differences are found among the two directions of the commuting trips, with work–home trips having a greater average duration and, in many cases, different choices of lines.

Data-Driven Multi-Criteria Assessment Framework for Analyzing the Reliability of Bus Services

Intelligent systems have been extensively used to improve the reliability of transport services as a result of technological advances. Despite the technical and methodological achievements, public transportation companies are still facing excessive challenges in assessing the performance and reliability of the system. This study establishes a data-driven multi-criteria decision-making model for prioritizing bus routes that illustrates both operator and consumer views on bus routes. The multi-criteria fuzzy outranking process is handled by ELECTRE III and Condorcet methods. The developed model utilizes alternative indices of bus travel-time reliability to fully capture the uncertain nature of the input data. The reliability assessment framework is based on automatic vehicle location (AVL) data which works as an effective evaluation system for enhanced service reliability on different routes network-wide. Using this model, bus transport companies can set a benchmark and a reliable ranking system for their bus routes. This hybrid prioritization framework is used for characterizing and enhancing transport network efficiency. The effectiveness of the model is examined by quantifying the reliability of eight bus routes controlled by the Qazvin public transportation system, in Iran. A wide range of AVL data sources is employed within an in-depth statistical analysis based on both user and operator preferences. According to the concordance matrix results, line 18 has been found to be superior to other bus routes, and the possibility of identifying less efficient bus routes has been fulfilled.

Data-Driven Real-Time Denied Boarding Prediction in Urban Railway Systems

Providing real-time crowding information in urban railways would enable informed travel decisions and encourage cooperative behavior of passengers, as well as improve operating efficiency and safety. However, the problem of real-time crowding prediction is not trivial because of the unavailability of ground-truth crowding data, particularly for the direct impact of crowding on passengers (e.g., denied boarding on platforms). This paper proposes a data-driven method for real-time denied boarding prediction in urban railway systems using automated fare collection (AFC) and automated vehicle location (AVL) data. It predicts the denied boarding probability distribution or its derived metrics as a function of explanatory variables, including demand, operations, and incident-related factors. The method is validated through a case study covering 18 months on Hong Kong Mass Transit Railways. The results highlight the model’s accurate and robust performance in predicting denied boarding on platforms using purely AFC and AVL data (e.g., an average of 6%–7% error) under both recurrent and non-recurrent situations, in which transfer demand-related factors contribute most to the prediction. The prediction model outputs can support proactive operations control and management, as well as provision of customer information without relying on expensive and time-consuming data collection efforts. Customer information, for example, can include the average number of trains to wait before boarding or the average waiting time on the platform.

Identifying the Spatiotemporal Metro-to-Bus Transfer Deserts in Shanghai, China

In the majority of metropolitan areas in China, the ground-level bus is the dominating feeder mode for metro systems. For enhancing the intermodal integration, it is necessary to evaluate the transfer accessibility between metro and bus considering the spatiotemporal dimensions with finer resolution. This study developed a methodology to identify the metro-to-bus transfer desert by considering the spatiotemporal dynamics on both service supply and passenger demand based on smart card data and automatic vehicle location data. In order to provide a more accurate and detailed depiction of results and stronger policy implications, this research aggregates to a higher spatial resolution (i.e., metro stops), instead of utilizing census tracts or administrative zones used in available research. The proposed methodology was implemented in the case study of the metropolitan area of Shanghai. Our empirical analysis highlights transfer service deficiency existing across the metropolitan area of Shanghai throughout the day, and varies both on spatially and temporally. Peak hours are characterized by better transfer accessibility levels on average but worse performances on metro stops with high transfer volume compared with off-peak hours. Because the developed methodology makes use of widely available input data, policymakers and transit agencies could replicate such gap analysis of local transit services in other contexts around the world.

Spatially Varying Impacts of Built Environment on Transfer Ridership of Metro and Bus Systems

Public transport, especially bus and metro, are fundamental elements of sustainable transport systems. However, a dearth of research has been devoted to exploring the correlation between the built environment and the intermodal transfer modes that link bus and metro. To address this research gap, this study aims to explore the relationship between the built environment and transfer ridership by examining transfer ridership across different modes. First, this study uses Automatic Fare Collection (AFC) and Automatic Vehicle Location (AVL) data collected in the city of Chengdu to identify the ridership of Metro-to-Bus (M-B) and Bus-to-Metro (B-M) transfer passengers using dynamic transfer time thresholds. A multi-scale geographically weighted regression model (MGWR) is employed to examine the impact of the built environment on M-B and B-M transfer modes and their scale effects. The findings demonstrate that the MGWR model is effective in capturing the spatial heterogeneity and scale effects of the interrelationships between different built environment factors in the M-B and B-M modes. Furthermore, the impact of different built environment factors on transfer ridership varies. In particular, the number of bus stops and lines have a more pronounced positive effect on promoting transfer ridership, while the density of non-motorway lanes has a significant negative effect. This research provides valuable insights for public transportation management and supports the seamless integration of bus and metro systems to optimize transfer services.

Does the squeaky wheel get the complaint? Linking bus performance, sociodemographic characteristics, and customer comments

Public transit agencies rely on service operations performance measures to guide service improvement efforts. They also collect customer feedback on performance to measure levels of satisfaction among users. Connecting these two performance measures can help public transport agencies increase ridership satisfaction and loyalty. In this study, we link service performance measures obtained from automatic vehicle location (AVL) and automatic passenger count (APC) with customer complaints. This is done while controlling for the amount of ridership to understand if routes with worse service performance, as identified by operations measures, also have more service complaints. We also investigated if an area’s level of affluence affects the number of service complaints per rider that the route receives while controlling for route service performance and ridership. The AVL/APC and customer-feedback data were provided by Portland, Oregon’s TriMet transport agency for the period between August 2018 and January 2019. Descriptive statistics at the route level and a series of mixed-effect multilevel logistic regression models were used to quantify the relationship between route service performance, service complaints, and a service-area vulnerability index, at the route-day level. The likelihood of receiving a service complaint for a route in a day was found to increase based on service performance and the vulnerability of the neighborhood being served by that route, all else held equal. Findings from this research unmask the relationship between service complaints, bus operations and socioeconomic characteristics of the neighborhood a route is serving, offering insights to transport planners and researchers in the psychology behind bus performance complaints.

Dynamic Modeling for Metro Passenger Flows on Congested Transfer Routes

With the rapid development of urbanization, the metro becomes more and more important for people’s travel in big cities. To quantitatively describe metro passenger flows on congested transfer routes, this paper introduces a dynamic model based on automated data from the automatic fare collection (AFC) and automatic vehicle location (AVL) systems. An expectation maximization (EM) algorithm is proposed to compute the maximum likelihood estimates of unknown parameters in our model. Our model can yield a systematic analysis of one-transfer passenger flows on both population and individual aspects. Important characteristics, including transfer time, boarding probabilities, walking time, passenger-to-train assignment probabilities, and total travel time, can be inferred using only the AFC and AVL data. We provide a case study on the Beijing metro. Detailed analysis results based on our model are given. We also present a cross-validation method to validate our model with real data.

On the prediction of intermediate-to-long term bus section travel time with the Burr mixture autoregressive model

Travel time is an essential indicator for trip planning, transportation service planning, and operation. This study aims to propose a novel Burr mixture autoregressive (BMAR) model for the intermediate-to-long term period of bus section travel time prediction, which is useful for bus service and schedule planning. The BMAR model exhibits greater flexibility, allowing it to effectively capture the multi-peak and non-peak, non-linear with heteroscedasticity characteristics of travel time. The model is trained and well-validated with 6-month bus section travel time data collected via the automatic vehicle location system. Results show that the BMAR model gives promising results in travel time point and interval prediction, especially for the higher degree of variability and irregular pattern of travel time observed on urban roads and highways. The reliability ratio index derived from the BMAR model could be used to measure the bus service reliability and aid in the bus scheduling of maintenance activities.