Passenger Flow Prediction for Rail Transit Stations Based on an Improved SSA-LSTM Model

Accurate and timely passenger flow prediction is important for the successful deployment of rail transit intelligent operation. The Sparrow Search Algorithm (SSA) has been applied to the parameter optimization of a Long-Short-Term Memory (LSTM) model. To solve the inherent weaknesses of SSA, this pa...

Full description

Saved in:
Bibliographic Details
Main Authors: Xing Zhao, Chenxi Li, Xueting Zou, Xiwang Du, Ahmed Ismail
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/22/3556
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267038533025792
author Xing Zhao
Chenxi Li
Xueting Zou
Xiwang Du
Ahmed Ismail
author_facet Xing Zhao
Chenxi Li
Xueting Zou
Xiwang Du
Ahmed Ismail
author_sort Xing Zhao
collection DOAJ
description Accurate and timely passenger flow prediction is important for the successful deployment of rail transit intelligent operation. The Sparrow Search Algorithm (SSA) has been applied to the parameter optimization of a Long-Short-Term Memory (LSTM) model. To solve the inherent weaknesses of SSA, this paper proposes an improved SSA-LSTM model with optimization strategies including Tent Map and Levy Flight to practice the short-term prediction of boarding passenger flow at rail transit stations. Aimed at the passenger flow at four rail transit stations in Nanjing, China, it is found that the day of a week and rainfall are the influencing factors with the highest correlation. On this basis, we apply the proposed SSA-LSTM and four baseline models to realize the short-term prediction, and carry out the prediction experiments with different time granularities. According to the experimental results, the proposed SSA-LSTM model has a more effective performance than the Support Vector Regression (SVR) method, the eXtreme Gradient Boosting (XGBoost) model, the traditional LSTM model, and the improved LSTM model with the Whale Optimization Algorithm (WOA-LSTM) in the passenger flow prediction. In addition, for most stations, the prediction accuracy of the proposed SSA-LSTM model is greater at a larger time granularity, but there are still exceptions.
format Article
id doaj-art-3ca06f40995d41dabdf3cec636049508
institution OA Journals
issn 2227-7390
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-3ca06f40995d41dabdf3cec6360495082025-08-20T01:53:57ZengMDPI AGMathematics2227-73902024-11-011222355610.3390/math12223556Passenger Flow Prediction for Rail Transit Stations Based on an Improved SSA-LSTM ModelXing Zhao0Chenxi Li1Xueting Zou2Xiwang Du3Ahmed Ismail4College of Civil and Transportation Engineering, Hohai University, No. 1, Xikang Road, Nanjing 210098, ChinaCollege of Civil and Transportation Engineering, Hohai University, No. 1, Xikang Road, Nanjing 210098, ChinaCollege of Civil and Transportation Engineering, Hohai University, No. 1, Xikang Road, Nanjing 210098, ChinaJsti Group, No. 8, Fuchun Jiangdong Street, Jianye District, Nanjing 210019, ChinaCollege of Civil and Transportation Engineering, Hohai University, No. 1, Xikang Road, Nanjing 210098, ChinaAccurate and timely passenger flow prediction is important for the successful deployment of rail transit intelligent operation. The Sparrow Search Algorithm (SSA) has been applied to the parameter optimization of a Long-Short-Term Memory (LSTM) model. To solve the inherent weaknesses of SSA, this paper proposes an improved SSA-LSTM model with optimization strategies including Tent Map and Levy Flight to practice the short-term prediction of boarding passenger flow at rail transit stations. Aimed at the passenger flow at four rail transit stations in Nanjing, China, it is found that the day of a week and rainfall are the influencing factors with the highest correlation. On this basis, we apply the proposed SSA-LSTM and four baseline models to realize the short-term prediction, and carry out the prediction experiments with different time granularities. According to the experimental results, the proposed SSA-LSTM model has a more effective performance than the Support Vector Regression (SVR) method, the eXtreme Gradient Boosting (XGBoost) model, the traditional LSTM model, and the improved LSTM model with the Whale Optimization Algorithm (WOA-LSTM) in the passenger flow prediction. In addition, for most stations, the prediction accuracy of the proposed SSA-LSTM model is greater at a larger time granularity, but there are still exceptions.https://www.mdpi.com/2227-7390/12/22/3556passenger flow predictionlong-short-term memoryimproved sparrow search algorithmmachining learning
spellingShingle Xing Zhao
Chenxi Li
Xueting Zou
Xiwang Du
Ahmed Ismail
Passenger Flow Prediction for Rail Transit Stations Based on an Improved SSA-LSTM Model
Mathematics
passenger flow prediction
long-short-term memory
improved sparrow search algorithm
machining learning
title Passenger Flow Prediction for Rail Transit Stations Based on an Improved SSA-LSTM Model
title_full Passenger Flow Prediction for Rail Transit Stations Based on an Improved SSA-LSTM Model
title_fullStr Passenger Flow Prediction for Rail Transit Stations Based on an Improved SSA-LSTM Model
title_full_unstemmed Passenger Flow Prediction for Rail Transit Stations Based on an Improved SSA-LSTM Model
title_short Passenger Flow Prediction for Rail Transit Stations Based on an Improved SSA-LSTM Model
title_sort passenger flow prediction for rail transit stations based on an improved ssa lstm model
topic passenger flow prediction
long-short-term memory
improved sparrow search algorithm
machining learning
url https://www.mdpi.com/2227-7390/12/22/3556
work_keys_str_mv AT xingzhao passengerflowpredictionforrailtransitstationsbasedonanimprovedssalstmmodel
AT chenxili passengerflowpredictionforrailtransitstationsbasedonanimprovedssalstmmodel
AT xuetingzou passengerflowpredictionforrailtransitstationsbasedonanimprovedssalstmmodel
AT xiwangdu passengerflowpredictionforrailtransitstationsbasedonanimprovedssalstmmodel
AT ahmedismail passengerflowpredictionforrailtransitstationsbasedonanimprovedssalstmmodel