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

Abstract

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 spatialtemporal 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. INDEX TERMS Artificial neural networks, bus arrival prediction, LSTM, spatial-temporal feature vector.

Traffic congestion prediction based on Estimated Time of Arrival

“…The proposed Dynamic Tensor Completion (DTC) makes active use of multi mode periodic cities such as spatial information, weekly and daily periodicity, along with chronological deviations of Traffic flow. Hongjie Liu et al [ 19 , 20 ]. propose an ANN and LSTM based prediction model and suggest time feature for long distance arrival to station prediction and spatial features for short distance arrival to station prediction.…”

Multistep Prediction of Bus Arrival Time with the Recurrent Neural Network

“…e temporal and spatial RNN network with ConvLSTM or a spatiotemporal property model (STPM) was originally used to predict the precipitation [13]. However, it was also used for predicting bus arrival times based on the total operation time of a bus on a route, waiting and on-board times, transfer location wait times [14][15][16], and multilane short-term traffic flow [17] and for creating the multitime step deep neural network [18]. e bus is running on fixed lines with fixed stations.…”

Online Bus Speed Prediction With Spatiotemporal Interaction: A Laplace Approximation-Based Bayesian Approach

“…The offline prediction approaches train the model using static data and conduct prediction without real-time adjustment. An extensive range of reported works on traffic state prediction falls into this category [4][5][6]. On the other hand, the online prediction approaches update the model recurrently when a new data stream is acquired throughout the prediction horizon, making the prediction models adaptive to the latest information.…”

“…In light of the propagation of congestion and the disturbance caused by traffic incidents, bus speeds can be both spatially and temporally correlated. The investigation of spatial and temporal effects in bus travel speed/time is gaining increasing attention recently [6,[9][10][11]. However, most existing studies address the spatial and temporal effects separately without modeling the spatiotemporal interaction (STI) effects [12].…”

“…Despite the superior predictive performance, machine learning models are criticized for the lack of interpretability [17]. Though spatial and temporal correlations can be captured to a certain extent by some machine learning models (e.g., deep neural network [6,18], attention network [5,19], convolutional neural network (CNN) [20,21]), it is challenging to (i) explicitly interpret these correlations, and (ii) quantify their impacts on outcomes and to make relevant inferences. Few studies have developed models considering both predictive performance and interpretability in the traffic state prediction domain when STI is concerned [12,17].…”