Delay prediction with spatial–temporal bi-directional LSTM in railway network
Ke Yu,
Chuiyun Kong,
Limin Zhong,
Junfeng Fu,
Jie Shao
Affiliations
Ke Yu
University of Electronic Science and Technology of China, Chengdu 611731, China; The Center of National Railway Intelligent Transportation System Engineering and Technology, Beijing 100081, China
Chuiyun Kong
The Center of National Railway Intelligent Transportation System Engineering and Technology, Beijing 100081, China; Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China
Limin Zhong
The Center of National Railway Intelligent Transportation System Engineering and Technology, Beijing 100081, China; Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China; Corresponding author at: Institute of Computing Technologies, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China.
Junfeng Fu
University of Electronic Science and Technology of China, Chengdu 611731, China; The Center of National Railway Intelligent Transportation System Engineering and Technology, Beijing 100081, China
Jie Shao
University of Electronic Science and Technology of China, Chengdu 611731, China; The Center of National Railway Intelligent Transportation System Engineering and Technology, Beijing 100081, China; Corresponding author at: University of Electronic Science and Technology of China, Chengdu 611731, China.
Train delay prediction is a vital part of railway system, but due to uncertain factors such as the complexity of the railway system and spatial–temporal features, it is often difficult to predict train delay in practice. In this paper, we propose a Spatial–Temporal and Bi-directional Long Short-Term Memory (ST-BiLSTM) model to deal with the train delay prediction problem. The model contains spatial–temporal blocks to capture spatial and temporal features and a bi-directional Long Short-Term Memory (LSTM) block to introduce bi-directional information through an attention mechanism. Experiments demonstrate that ST-BiLSTM outperforms the existing baselines in two evaluation metrics.
