T-LSTM: A Long Short-Term Memory Neural Network Enhanced by Temporal Information for Traffic Flow Prediction

Luntian Mou,Pengfei Zhao,Haitao Xie,Yanyan Chen

doi:10.1109/access.2019.2929692

Abstract

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transportation systems. It plays an important role in traffic information service and traffic guidance. However, complex traffic systems are highly nonlinear and stochastic, making short-term traffic flow prediction a challenging issue. Although long short-term memory (LSTM) has a good performance in traffic flow prediction, the impact of temporal features on prediction has not been exploited by existing studies. In this paper, a temporal information enhancing LSTM (T-LSTM) is proposed to predict traffic flow of a single road section. In view of the similar characteristics of traffic flow at the same time each day, the model can improve prediction accuracy by capturing the intrinsic correlation between traffic flow and temporal information. The experimental results demonstrate that our method can effectively improve the prediction performance and obtain higher accuracy compared with other state-of-the-art methods. Furthermore, we propose a novel missing data processing technique based on T-LSTM. According to the experimental results, this technique can well restore the characteristics of original data and improve the accuracy of traffic flow prediction.

Highlights

In the field of Intelligent Transportation Systems (ITS), traffic control and guidance systems are the core topics and to which traffic flow prediction is the key
The main contributions of this paper are as follows: 1) For the first time, we propose a Temporal information enhancing Long Short-Term Memory neural networks (T-long short-term memory (LSTM)) that combines recurrent time labels with recurrent neural networks, which makes the best use of the temporal features to improve the accuracy of short-term traffic flow prediction
The prediction results for August 2014 demonstrate that temporal information enhancing LSTM (T-LSTM) has the highest prediction accuracy and the MAPE is reduced to 6.09%

Summary

INTRODUCTION

In the field of Intelligent Transportation Systems (ITS), traffic control and guidance systems are the core topics and to which traffic flow prediction is the key. The main contributions of this paper are as follows: 1) For the first time, we propose a Temporal information enhancing Long Short-Term Memory neural networks (T-LSTM) that combines recurrent time labels with recurrent neural networks, which makes the best use of the temporal features to improve the accuracy of short-term traffic flow prediction. Wu et al proposed a CNN-RNN model to improve prediction accuracy, which makes full use of weekly/daily periodicity and spatial-temporal characteristics of traffic flow [37]. We propose the T-LSTM model that makes the best use of the temporal characteristics to improve the accuracy of short-term traffic flow prediction. It is worth mentioning that the expressions of functions σ and tanh will be given below

RECURRENT TIME LABEL

EXPERIMENTAL RESULTS AND ANALYSIS

1) RESULTS OF TRAFFIC FLOW PREDICTION