Learning Dynamic Factors to Improve the Accuracy of Bus Arrival Time Prediction via a Recurrent Neural Network

Abstract

Accurate prediction of bus arrival times is a challenging problem in the public transportation field. Previous studies have shown that to improve prediction accuracy, more heterogeneous measurements provide better results. So what other factors should be added into the prediction model? Traditional prediction methods mainly use the arrival time and the distance between stations, but do not make full use of dynamic factors such as passenger number, dwell time, bus driving efficiency, etc. We propose a novel approach that takes full advantage of dynamic factors. Our approach is based on a Recurrent Neural Network (RNN). The experimental results indicate that a variety of prediction algorithms (such as Support Vector Machine, Kalman filter, Multilayer Perceptron, and RNN) have significantly improved performance after using dynamic factors. Further, we introduce RNN with an attention mechanism to adaptively select the most relevant input factors. Experiments demonstrate that the prediction accuracy of RNN with an attention mechanism is better than RNN with no attention mechanism when there are heterogeneous input factors. The experimental results show the superior performances of our approach on the data set provided by Jinan Public Transportation Corporation.

A review of bus arrival time prediction using artificial intelligence

“…Most of the studies considered factors which do not change in a short time but BAT is affected by dynamic factors as well like the number of passengers, weather, and so on. To improve accuracy, dynamic factors should be considered (Zhou et al, 2019).…”

“…Some authors have used GPS data with Google map data to get more input factors affecting BAT prediction like weather and traffic density (Jalaney & Ganesh, 2020). Some others have developed smartphone applications which collect information from passengers and also provide them beneficial information such as BAT (Wepulanon et al, 2017; Zhou et al, 2019).…”

“…Since, dynamic information changes with time, incorporating dynamic information can help in improving accuracy (Zhou et al, 2019). Numerous studies have investigated the effect of different factors on BAT.…”

Unavailable Transit Feed Specification: Making It Available With Recurrent Neural Networks

“…The network solves the bus-station arrival prediction problem by employing spatialtemporal feature vectors. Zhou et al [14] adopt an RNN that employs a set of dynamic factors, e.g., passengers number, dwell time, bus driving efficiency, to predict bus arrival times. Moreover, the authors introduce an attention mechanism to select the most relevant factors from heterogeneous information adaptively.…”

A Hybrid Deep Convolutional Neural Network Approach for Predicting the Traffic Congestion Index

“…Nevertheless, it is still difficult to collect comprehensive data, including travel speed, traffic density, and traffic volume. The Global Positioning System (GPS) has become an effective sequences by considering nonlinear traffic information and time-series datasets [22]. To deal with the vanishing gradient problems of long-term dependencies [23], many advanced RNNs have been proposed, including the gated recurrent unit (GRU) [24] and the stacked LSTM [25,26].…”