Abstract
Metro passenger flow prediction plays an essential role in metro operation system. Due to characteristics of metro operation system, the station operation state is difficult to be described by the passenger flow at a single station. Thus, a novel attention mechanism based end-to-end neural network is presented to predict the inbound and outbound passenger flow to improve predictive effect. The novel model explores the latent dependency between flow of forecast target station and historical flows from surrounding stations by attention mechanism. The relation between variable length flow lists with respect to target station is represented as a fix length vector by the attention mechanism. Furthermore, a deep and wide structure is presented to deal with the inherent information of each station, which are discretized into high dimensional categorical features. Experiments on Beijing Subway line 5 with 1.8 million samples demonstrate the effectiveness of presented approach, which shown the performance on capturing latent dependency.
Highlights
In metro operation system, system management such as train operation plan is formulated by history flow data and predicted passenger flow data
We propose an architecture of attention based neural network(DNN-Attention) and apply it to predict the passenger flow for Beijing metro stations
Performance will be compared with three different baseline models: deep neural network (DNN) (Deep Neural Network): naive feed-forward neural network without any additional technique
Summary
System management such as train operation plan is formulated by history flow data and predicted passenger flow data. Various end-to-end neural network architecture have been proposed to handle passenger flow predicting problem. J. Yang et al.: Metro Passenger Flow Prediction Model Using Attention-Based Neural Network are considered in neural network architecture. To take advantage of external environmental features, temporal dependencies, and spatial characteristics a Deep Passenger Flow (Deep PF) model [21] is built, which embed external environmental features by fully connected layers and handle time series data by LSTM cells. We propose an architecture of attention based neural network(DNN-Attention) and apply it to predict the passenger flow for Beijing metro stations. The experimental result turns out that the flow variation characteristics of metro station can be formulated in a high accuracy using out architecture of attention based neural network.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
