Short-term prediction of passenger volume for urban rail systems: A deep learning approach based on smart-card data

2021 ◽  
Vol 231 ◽  
pp. 107920
Author(s):  
Xin Yang ◽  
Qiuchi Xue ◽  
Meiling Ding ◽  
Jianjun Wu ◽  
Ziyou Gao
Keyword(s):  
Deep Learning ◽  
Smart Card ◽  
Learning Approach ◽  
Short Term ◽  
Term Prediction ◽  
Rail Systems ◽  
Smart Card Data ◽  
Urban Rail ◽  
Passenger Volume ◽  
Short Term Prediction

A Deep Learning Approach for Short Term Prediction of Industrial Plant Working Status

2021 ◽  
Author(s):  
Pierfrancesco Bellini ◽  
Daniele Cenni ◽  
Luciano Alessandro Ipsaro Palesi ◽  
Paolo Nesi ◽  
Gianni Pantaleo
Keyword(s):  
Deep Learning ◽  
Industrial Plant ◽  
Learning Approach ◽  
Short Term ◽  
Term Prediction ◽  
Working Status ◽  
Short Term Prediction

Short-term prediction of lane-level traffic speeds: A fusion deep learning model

2019 ◽  
Vol 106 ◽  
pp. 1-16 ◽  
Author(s):  
Yuanli Gu ◽  
Wenqi Lu ◽  
Lingqiao Qin ◽  
Meng Li ◽  
Zhuangzhuang Shao
Keyword(s):  
Deep Learning ◽  
Learning Model ◽  
Short Term ◽  
Term Prediction ◽  
Short Term Prediction ◽  
Deep Learning Model

scholarly journals Capacity-Constrained Network Performance Model for Urban Rail Systems

2020 ◽  
Vol 2674 (5) ◽  
pp. 59-69 ◽  
Author(s):  
Baichuan Mo ◽  
Zhenliang Ma ◽  
Haris N. Koutsopoulos ◽  
Jinhua Zhao
Keyword(s):  
Smart Card ◽  
Network Performance ◽  
Performance Monitoring ◽  
Optimization Method ◽  
Performance Model ◽  
Railway Network ◽  
Rail Systems ◽  
Smart Card Data ◽  
Urban Rail ◽  
General Network

This paper proposes a general network performance model (NPM) for monitoring the performance of urban rail systems using smart card data. NPM is a schedule-based network loading model with strict capacity constraints and boarding priorities. It distributes passengers over the network given origin-destination demand, operations, route choice, and effective train capacity. A Bayesian simulation-based optimization method for calibrating the effective train capacity is introduced, which explicitly recognizes that capacity may be different at different stations depending on congestion levels. Case studies with data from the Mass Transit Railway network in Hong Kong are used to validate the model and illustrate its applicability. NPM is validated using survey data on left-behind passengers and exiting passenger flow extracted from smart card data. The use of NPM for performance monitoring is demonstrated by analyzing the spatial-temporal crowding patterns in the system and evaluating dispatching strategies.

Sign in / Sign up

Export Citation Format

Share Document