Bus Arrival Prediction Research Articles

Evaluation of urban bus service reliability on variable time horizons using a hybrid deep learning method

Unreliable transit services can negatively impact transit ridership and discourage passengers from regularly choosing public transport. As the most important content of bus service reliability, accurate bus arrival prediction can improve travel efficiency for enabling a reliable and convenient transportation system. Accordingly, this paper proposes a novel deep learning method, i.e. variational mode decomposition long short-term memory (VMD-LSTM), for bus travel speed prediction in urban traffic networks using a forecast of bus arrival information on variable time horizons. The method uses the temporal and spatial patterns of the average bus speed series. The results show that the VMD-LSTM model outperforms other models on forecasting bus link speed series in future time intervals, whereas the artificial neural network model achieves the worst prediction. In conclusion, the VMD-LSTM method can detect irregular peaks of transit samples from a series of temporal or spatial variations and performs better on major and auxiliary corridors.

Bus Arrival Time Prediction Based on LSTM and Spatial-Temporal Feature Vector

Bus arrival prediction has important implications for public travel, urban dispatch, and mitigation of traffic congestion. The factors affecting urban traffic conditions are complex and changeable. As the predicted distance increases, the difficulty of traffic prediction becomes more difficult. Forecast based on historical data responds quite slowly for changes under the short-term conditions, and vehicle prediction based on real-time speed is not sufficient to predict under long-term conditions. Therefore, an arrival prediction method based on temporal vector and another arrival prediction method based on spatial vector is proposed to solve the problems of remote dependence of bus arrival and road incidents, respectively. In this paper, combining the advantages of the two prediction models, this paper proposes a long short-term memory (LSTM) and Artificial neural networks (ANN) comprehensive prediction model based on spatial-temporal features vectors. The long-distance arrival-to-station prediction is realized from the dimension of time feature, and the short-distance arrival-to-station prediction is realized from the dimension of spatial feature, thereby realizing the bus-to-station prediction. Besides, experiments were conducted and tested based on the entity dataset, and the result shows that the proposed method has high accuracy among bus arrival prediction problems.

Learning to Predict Bus Arrival Time From Heterogeneous Measurements via Recurrent Neural Network

Bus arrival time prediction intends to improve the level of the services provided by transportation agencies. Intuitively, many stochastic factors affect the predictability of the arrival time, e.g. , weather and local events. Moreover, the arrival time prediction for a current station is closely correlated with that of multiple passed stations. Motivated by the observations above, this paper proposes to exploit the long-range dependencies among the multiple time steps for bus arrival prediction via recurrent neural network (RNN). Concretely, RNN with long short-term memory block is used to “correct” the prediction for a station by the correlated multiple passed stations. During the correlation among multiple stations, one-hot coding is introduced to fuse heterogeneous information into a unified vector space. Therefore, the proposed framework leverages the dynamic measurements ( i.e. , historical trajectory data) and the static observations ( i.e. , statistics of the infrastructure) for bus arrival time prediction. In order to fairly compare with the state-of-the-art methods, to the best of our knowledge, we have released the largest data set for this task. The experimental results demonstrate the superior performances of our approach on this data set.

Multi-output Deep Learning for Bus Arrival Time Predictions

Abstract Accurate and reliable predictions for bus arrival in public transport networks are essential for delivering an attractive service. This paper presents a multi-model approach for bus arrival prediction. The approach uses three distinct sub-models in an ensemble model. A multi-output, multi-time-step, deep neural network using Convolutional and Long short-term memory (LSTM) layers is used for travel time, and more simplistic models are used for dwell time and seasonal components. The method is empirically evaluated and compared to other popular approaches. We find that the proposed model saturations outperforms the other methods, while in other saturations performs similar.

Transit-hub: a smart public transportation decision support system with multi-timescale analytical services

Public transit is a critical component of a smart and connected community. As such, citizens expect and require accurate information about real-time arrival/departures of transportation assets. As transit agencies enable large-scale integration of real-time sensors and support back-end data-driven decision support systems, the dynamic data-driven applications systems (DDDAS) paradigm becomes a promising approach to make the system smarter by providing online model learning and multi-time scale analytics as part of the decision support system that is used in the DDDAS feedback loop. In this paper, we describe a system in use in Nashville and illustrate the analytic methods developed by our team. These methods use both historical as well as real-time streaming data for online bus arrival prediction. The historical data is used to build classifiers that enable us to create expected performance models as well as identify anomalies. These classifiers can be used to provide schedule adjustment feedback to the metro transit authority. We also show how these analytics services can be packaged into modular, distributed and resilient micro-services that can be deployed on both cloud back ends as well as edge computing resources.

A estimação neural de tempos de viagens de ônibus sob regime de fretamento usando-se de dados de posicionamento por satélites (GPS)

ResumoO trabalho teve o objeto o desenvolvimento de um modelo de previsão de chegada de ônibus que fazem o transporte de empregados sob o regime de fretamento. Para tanto, utilizou-se um modelo matemático baseado em Redes Neurais Artificiais. As experiências anteriores de aplicação de RNA's para modelagem desse tipo de problema consideraram como dados de entrada, informações "estáticas" do percurso, como por exemplo, a posição dos pontos de paradas pré-estabelecidos, a distância entre os mesmos, a velocidade média de percurso previamente analisada. A contribuição do presente trabalho foi desenvolver um modelo de aprendizado considerando como dados de entrada, qualquer localização do veículo (longitude e latitude) ao longo do percurso bem como a hora em que o mesmo passou pela mesma coordenada, tornando o modelo mais dinâmico e simplificado para ser reproduzido e incorporado às ferramentas de rastreamento veicular que utilizam posicionamento global (GPS). Outra contribuição metodológica foi a estruturação de uma "árvore de testes" que considerou variações na tipologia, nos valores para Taxa de Aprendizagem e "Momentum". O resultado alcançado chegou a um modelo de previsão com erro relativo médio de menos de 1%.

Evaluating the added-value of online bus arrival prediction schemes

Online predictions of bus arrival times have the potential to reduce the uncertainty associated with bus operations. By better anticipating future conditions, online predictions can reduce perceived and actual passenger travel times as well as facilitate more proactive decision making by service providers. Even though considerable research efforts were devoted to the development of computationally expensive bus arrival prediction schemes, real-world real-time information (RTI) systems are typically based on very simple prediction rules. This paper narrows down the gap between the state-of-the-art and the state-of-the-practice in generating RTI for public transport systems by evaluating the added-value of schemes that integrate instantaneous data and dwell time predictions. The evaluation considers static information and a commonly deployed scheme as a benchmark. The RTI generation algorithms were applied and analyzed for a trunk bus network in Stockholm, Sweden. The schemes are assessed and compared based on their accuracy, reliability, robustness and potential waiting time savings. The impact of RTI on passengers waiting times are compared with those attained by service frequency and regularity improvements. A method which incorporates information on downstream travel conditions outperforms the commonly deployed scheme, leading to a 25% reduction in the mean absolute error. Furthermore, the incorporation of instantaneous travel times improves the prediction accuracy and reliability, and contributes to more robust predictions. The potential waiting time gains associated with the prediction scheme are equivalent to the gains expected when introducing a 60% increase in service frequency, and are not attainable by service regularity improvements.

Real-Time Bus Arrival Information System: An Empirical Evaluation

The provision of real-time information concerning bus arrival times could potentially reduce the uncertainty associated with public transport trips and improve the overall level of service. In addition, real-time predictions might enable operators to apply proactive control strategies. Even though considerable research efforts were devoted to the development of bus arrival prediction schemes, there is a lack of knowledge on the performance of real-world operational systems. This article aims to investigate the performance of a commonly deployed real-time information generation scheme. A conventionally used scheme is implemented and evaluated based on an empirical analysis. Performance metrics concerning the prediction error accuracy and reliability and their impact on expected waiting time were formulated from both passengers’ and operators’ perspectives. The real-time information generator was applied on the trunk line network in Stockholm, Sweden. The accuracy and reliability of the prediction scheme was analyzed by comparing the generated predictions against vehicle positioning data. This scheme was found to systematically underestimate the remaining waiting time by 6.2% on average. The provision of real-time information yields a waiting time estimate that is more than twice as close to the actual waiting times than the timetable. This difference in waiting time expectations is equivalent to 30% of the average waiting time.

Pattern identification based bus arrival time prediction

The provision of accurate bus arrival time information is one of the major components in advanced public transportation systems, which many of the metropolitan cities in developing countries are trying to implement to increase the public transit usage. The effectiveness of such a system largely depends on the reliability of the information provided to the public. For such reliable information to be generated, the prediction technique used should be able to make accurate predictions, which in turn depends on the input data used for prediction. The present study is an attempt to explore these two areas, namely the identification of suitable input data by analysing trip-wise, daily and weekly patterns of bus travel times through valid statistical tests and the development of an accurate bus arrival prediction model using a popular time series technique called exponential smoothing. The performance evaluation using 90 actual bus trip data shows that the use of suitable input data into the prediction model yields better results with mean absolute percentage error of 12, and for 77% of the time the deviation of predicted arrival time with respect to actual arrival time is within the user acceptable range of ± 5 min.

Collaborative prediction for bus arrival time based on CPS

To improve the accuracy of real-time public transport information release system, a collaborative prediction model was proposed based on cyber-physical systems architecture. In the model, the total bus travel time was divided into three parts: running time, dwell time and intersection delay time, and the data were divided into three categories of historical data, static data and real-time data. The bus arrival time was obtained by fusion computing the real-time data in perception layer together with historical data and static data in collaborative layer. The validity of the collaborative model was verified by the data of a typical urban bus line in Shanghai, and 1538 sets of data were collected and analyzed from three different perspectives. By comparing the experimental results with the actual results, it is shown that the experimental results are with higher prediction accuracy, and the collaborative prediction model adopted is able to meet the demand for bus arrival prediction.

基于动态交通信息的公交到站预测服务

公交到站时间(BAT)服务是提高公众交通吸引力的关键服务之一。服务给使用者提供实时车辆到站信息能够使用户更好的安排自己的公共交通行程。因此，实时公交到站时间预测技术在智能交通领域已经成为研究的热点。在本文中采用了新的公交到站时间预测模型。该模型提出了一套完整的算法来解决BAT预测中大规模的实时交通信息的计算，采用了高效的算法来实时纠正车辆的行驶方向。动态交通信息作为数据基础支撑BAT的计算。同时，采用虚拟预测来处理GPS数据丢失的情况保证了服务提供的稳定性。实验结果表明模型拥有较高的准确率(超过85.1%)和计算速度(最高处理5000条每秒)。 The bus arrival time (BAT) service is a key service to improve public transport attractiveness by providing users with real-time bus arrival information which can help them to arrange their bus travel schedule intelligently. Thus the technique of real-time bus arrival prediction has become a research hotspot in the community of Intelligent Transport Systems (ITS) nowadays. In this paper, a novel model on bus arrival time prediction is proposed. The model proposes a complete set of programs to solve BAT prediction for large-scale real-time traffic information calculating. It adopts an effective algorithm calculating vehicle’s driving direction real-timely. BAT is calculated based on dynamic traffic information and visual prediction is a way to complement when GPS information is not arrived as expected. Experimental results indicate that the model has considerable efficiency in accuracy (over 85.1%) and computational speed (max 5000 GPS records per second).

Service and Management Oriented Traffic Information Grid

Traffic information service plays an important role in one’s daily life. However, traffic information processing is very complicated because of its dynamic, cooperative and distributed features. This paper presents the Service and Monitoring Oriented Traffic Information Grid. In this system, it is a remarkable characteristic to provide real-time, dynamic information services for travelers and traffic managers by grid technology. The system provides travelers with services of optimized route scheme, bus arrival prediction based on real-time route status, and route status forecast. For traffic managers, the system can provide vehicle tracing, traffic monitoring, history data analysis, and decision making on traffic control strategy. In this regard, key research includes large multi-source traffic data integration, route status forecast, and optimum dynamic travel scheme implementation based on massive GPS data.

Development of a real-time bus arrival prediction system for Indian traffic conditions

The accuracy of Bus Traveler Information Systems (BTIS) depends on several factors such as accuracy of the input data, speed of data transfer, data quality control and performance of the prediction scheme. A majority of the existing BTIS in India does not take into account the real-time data and the quality control of data. Also, there is a scope for improving the performance of the underlying prediction schemes. There are several studies on real-time bus arrival time prediction under homogeneous traffic conditions. However, the traffic condition in India is different and direct implementation of those studies may not yield the best results. One of the main components of bus travel time is the delay time at bus stops, in addition to the other common delays. These delays need to be incorporated in the prediction scheme for better accuracy, which is not the case currently in most studies. Also, there is a need to develop an accurate automated bus arrival time prediction system using real-time data under heterogeneous traffic conditions. This study presents a model-based algorithm that uses real-time data from field and takes delays automatically into account for an accurate prediction of bus arrival time. The results obtained are compared with the currently adopted field method and show a clear improvement in the prediction accuracy.