Automatic Vehicle Location Data 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.

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.

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.

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.

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.

Probability distributions analysis of travel time variability for the public transit system

Travel time variability (TTV) plays a significant role in analysing the reliability of public transit system. The research works carried out on travel time variability under Indian traffic conditions are very few and these studies did not analyse the performance of travel time distribution in detail, considering different temporal and spatial aggregations. In this study, travel time variability is analysed using travel time distributions considering different temporal and spatial aggregations. The Automatic Vehicle Location (AVL) data of four transit routes of Mysore City, Karnataka, India are used to evaluate travel time distributions with respect to temporal aggregations (peak period, off-peak period, 60 minutes, 30 minutes and 15 minutes) and spatial aggregations (route level and segment level). The performance of travel time distributions is analysed using the Anderson-Darling (AD) test. The segments with signalised intersections and different land-use types are analysed to evaluate the distribution fit for various conditions. The results of both route and segment level analysis report highest accuracy and robustness values for Generalised Extreme Value (GEV) distribution. The distribution is proved to be superior in describing travel time variability of public transit.

Identifying Spatial–Temporal Characteristics and Significant Factors of Bus Bunching Based on an eGA and DT Model

Bus bunching is a common phenomenon caused by irregular bus headway, which increases the passenger waiting time, makes the passenger capacity uneven, and severely reduces the reliability of bus service. This paper clarified the process of bus bunching formation, analyzed the variation characteristics of bus bunching in a single day, in different types of periods, and at different bus stops, then concluded twelve potential factors. A hybrid model integrating a genetic algorithm with elitist preservation strategy (eGA) and decision tree (DT) was proposed. The eGA part constructs the model framework and transforms the factor identification into a problem of selecting the fittest individual from the population, while the DT part evaluates the fitness. Model verification and comparison were conducted based on real automatic vehicle location (AVL) data in Shenzhen, China. The results showed that the proposed eGA–DT model outperformed other frequently used single DT and extra tree (ET) models with at least a 20% reduction in MAE under different bus routes, periods, and bus stops. Six factors, including the sequence of the bus stop, the headway and dwell time at the previous bus stop, the travel time between bus stops, etc., were identified to have a significant effect on bus bunching, which is of great value for feature selection to improve the accuracy and efficiency of bus bunching prediction and real-time bus dispatching.

Bus Passenger Origin-Destination Estimation and Related Analyses Using Automated Data Collection Systems

This research explores the application of archived data from Automated Data Collection Systems (ADCS) to transport planning with a focus on bus passenger travel behavior, including Origin-Destination (OD) inference, using London as a case study. It demonstrates the feasibility and ease of applying trip-chaining to infer bus passenger OD from smart card transactions and Automatic Vehicle Location (AVL) data and is the first known attempt to validate the results by comparing them with manual passenger survey data. With the inferred OD matrices, the variations of weekday and weekend bus route OD patterns are examined for planning purposes. Moreover, based on the inferred OD matrices and the AVL data, alighting times for bus passengers also can be estimated. Bus journey stages, therefore, can easily be linked. By comparing the interchange time and the connecting bus route’s headway, it provides a way to evaluate bus connections.

A general dynamic sequential learning framework for vehicle trajectory reconstruction using automatic vehicle location or identification data

Vehicle trajectory data derived from automatic vehicle location (AVL) and automatic vehicle identification (AVI) systems provide critical support for intelligent transportation systems. However, the field-obtained vehicle trajectories are usually incomplete due to sensor malfunction or communication issues. To recover the incomplete data, the existing reconstruction methods have to impose strong assumptions on driver route choice behaviors (network level) and/or traffic dynamics (link level). With the tremendous data available, leveraging data-driven approaches to address the vehicle trajectory reconstruction problem with minimal assumptions is promising. This paper proposes a general dynamic sequential learning framework to reconstruct vehicle trajectory points for both AVL and AVI data. First, an Isolation Forest based ensemble learning model is developed to extract trajectory sequences attributed to different trips in an entire trip chain of a vehicle. Second, the dynamic recurrent neural network (dynamic RNN) is tailored to learn the underlying patterns from the complete AVL and AVI trajectories, respectively. Third, a sequential prediction scheme is customized to reconstruct AVL and AVI trajectories based on the trained networks. To validate the proposed method, two experiments are conducted. One is a simulation experiment with AVL data gathered from a well-calibrated simulation model. The other is a field experiment with AVI data collected from a real-world automatic license plate recognition (ALPR) system. The results show that the proposed method achieves superior performance for both AVL and AVI data compared with the traditional methods. The impacts of different sampling rates and traffic conditions on the model performance are also discussed.

Bus travel time reliability incorporating stop waiting time and in-vehicle travel time with AVL data

Improving bus travel time reliability can attract more commuters to use bus transit, and therefore reduces the share of cars and alleviates traffic congestion. This paper formulates a new bus travel time reliability metric that jointly considers two stochastic processes: the in-stop waiting process and in-vehicle travel time process, and the bus travel time reliability function is calculated by the convolution of independent events’ probabilities. The new reliability metric is defined as the probability when bus travel time is less than a certain threshold and can be used in both conditions with and without bus transfer. Next, Automatic Vehicle Location (AVL) data of the city of Harbin is used to demonstrate the applicability of the proposed method. Results show that factors such as weather, day of the week, departure time, travel distance, and the distance from the boarding stop to the bus departure station can significantly affect the travel time reliability. Then, a case with low bus departure frequency is analyzed to show the impact of travelers’ arrival distribution on their bus travel time reliability. Further, it is demonstrated that the travel time reliabilities of two bus transfer schemes of the same Origin–Destination (O–D) pair can have significantly different patterns. Understanding the bus travel time reliability pattern of the alternative bus routes can help passengers to choose a more reliable bus route under different conditions. The proposed bus travel time reliability metric is tested to be sensitive to the effect of different factors and can be applied in bus route recommendation, bus service evaluation, and optimization.

Understanding urban bus travel time: Statistical analysis and a deep learning prediction

Travel time reliability plays a key role in bus scheduling and service quality. Owing to various stochastic factors, buses often suffer from traffic congestion, delay and bunching, which leads to disturbances of travel time. Automatic vehicle location (AVL) could record the spatiotemporal information of buses, making it possible to understand the status of bus service. In this paper, we specifically analyze the statistical characteristics of travel time based on historic AVL data. Moreover, a Kalman filter-LSTM deep learning is proposed to estimate bus travel time. Numerical tests indicate that the travel time of bus routes shows a left-skewed and right-tail pattern with a good fit of the lognormal distribution. The bus service reliability fluctuates largely in the peak hours, especially the morning peak. Bus bunching and large bus time headway easily occur, and once it occurs, it will continue until destination. The Kalman filter-LSTM model outperforms the ensemble learning methods to predict travel time. This study could provide implications for transit schedule optimization to improve the bus service quality.