Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership prediction

Demand prediction plays a critical role in traffic research. The key challenge of traffic demand prediction lies in modeling the complex spatial dependencies and temporal dynamics. However, there is no mature and widely accepted concept to support the solution of the above challenge. Essentially,  ...

Full description

Saved in:
Bibliographic Details
Main Authors: Jiahui Zhao, Zhibin Li, Pan Liu, Mingye Zhang
Format: Article
Language:English
Published: University of Minnesota Libraries Publishing 2024-02-01
Series:Journal of Transport and Land Use
Subjects:
Online Access:https://www.jtlu.org/index.php/jtlu/article/view/2348
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849693073484808192
author Jiahui Zhao
Zhibin Li
Pan Liu
Mingye Zhang
author_facet Jiahui Zhao
Zhibin Li
Pan Liu
Mingye Zhang
author_sort Jiahui Zhao
collection DOAJ
description Demand prediction plays a critical role in traffic research. The key challenge of traffic demand prediction lies in modeling the complex spatial dependencies and temporal dynamics. However, there is no mature and widely accepted concept to support the solution of the above challenge. Essentially,  a prediction model combined with similar objects in temporal and spatial dimensions could obtain better performance. This paper proposes a concept called the Similarity-based Principle (SP), which is applied to improve the prediction performance of deep learning models in complex traffic scenarios. For the temporal components, the long-term temporal dynamics in contemporaneous historical data for ridership are extracted by the Stacked Autoencoder (SAE) method. For the spatial components, the activity-based spatial geographic information (ABG-information) is used to capture the spatial correlation of the traffic network, which is reflected in the daily activities of humans. Specifically, the SP is applied to a Spatio-temporal Graph Convolutional Neural Network (STGCNN) model. In the case study, the  Similarity-based Principle Spatio-temporal Graph Convolutional Neural Network (SP-STGCNN) model predicts demand for bicycle sharing in San Francisco. The results show that the SP effectively improves the model's performance. The prediction accuracy is enhanced by up to 10.34% compared with STGCNN. For spatial relationships, the model using the geographic information attribute performs better than that using the road information attribute and the distance attribute. It is proved that the construction of the Spatio-temporal model-based similarity principle can improve the performance.
format Article
id doaj-art-912c74dba63f4108b6301fb6d75dafd7
institution DOAJ
issn 1938-7849
language English
publishDate 2024-02-01
publisher University of Minnesota Libraries Publishing
record_format Article
series Journal of Transport and Land Use
spelling doaj-art-912c74dba63f4108b6301fb6d75dafd72025-08-20T03:20:32ZengUniversity of Minnesota Libraries PublishingJournal of Transport and Land Use1938-78492024-02-0117110.5198/jtlu.2024.2348Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership predictionJiahui Zhao0Zhibin Li1Pan Liu2Mingye Zhang3Southeast UniversitySoutheast UniversitySoutheast UniversitySoutheast University Demand prediction plays a critical role in traffic research. The key challenge of traffic demand prediction lies in modeling the complex spatial dependencies and temporal dynamics. However, there is no mature and widely accepted concept to support the solution of the above challenge. Essentially,  a prediction model combined with similar objects in temporal and spatial dimensions could obtain better performance. This paper proposes a concept called the Similarity-based Principle (SP), which is applied to improve the prediction performance of deep learning models in complex traffic scenarios. For the temporal components, the long-term temporal dynamics in contemporaneous historical data for ridership are extracted by the Stacked Autoencoder (SAE) method. For the spatial components, the activity-based spatial geographic information (ABG-information) is used to capture the spatial correlation of the traffic network, which is reflected in the daily activities of humans. Specifically, the SP is applied to a Spatio-temporal Graph Convolutional Neural Network (STGCNN) model. In the case study, the  Similarity-based Principle Spatio-temporal Graph Convolutional Neural Network (SP-STGCNN) model predicts demand for bicycle sharing in San Francisco. The results show that the SP effectively improves the model's performance. The prediction accuracy is enhanced by up to 10.34% compared with STGCNN. For spatial relationships, the model using the geographic information attribute performs better than that using the road information attribute and the distance attribute. It is proved that the construction of the Spatio-temporal model-based similarity principle can improve the performance. https://www.jtlu.org/index.php/jtlu/article/view/2348Keywords: Traffic demand prediction, Similarity-based Principle, Spatio-temporal Graph Convolutional Neural Network model; activity-based geographic information; prediction of bicycle sharing ridership.
spellingShingle Jiahui Zhao
Zhibin Li
Pan Liu
Mingye Zhang
Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership prediction
Journal of Transport and Land Use
Keywords: Traffic demand prediction, Similarity-based Principle, Spatio-temporal Graph Convolutional Neural Network model; activity-based geographic information; prediction of bicycle sharing ridership.
title Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership prediction
title_full Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership prediction
title_fullStr Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership prediction
title_full_unstemmed Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership prediction
title_short Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership prediction
title_sort spatial temporal deep learning model based on similarity principle for dock shared bicycles ridership prediction
topic Keywords: Traffic demand prediction, Similarity-based Principle, Spatio-temporal Graph Convolutional Neural Network model; activity-based geographic information; prediction of bicycle sharing ridership.
url https://www.jtlu.org/index.php/jtlu/article/view/2348
work_keys_str_mv AT jiahuizhao spatialtemporaldeeplearningmodelbasedonsimilarityprinciplefordocksharedbicyclesridershipprediction
AT zhibinli spatialtemporaldeeplearningmodelbasedonsimilarityprinciplefordocksharedbicyclesridershipprediction
AT panliu spatialtemporaldeeplearningmodelbasedonsimilarityprinciplefordocksharedbicyclesridershipprediction
AT mingyezhang spatialtemporaldeeplearningmodelbasedonsimilarityprinciplefordocksharedbicyclesridershipprediction