SCS-Net: Stratified Compressive Sensing Network for Large-Scale Crowd Flow Prediction

Large-scale crowd flow prediction is a critical task in urban management and public safety. However, achieving accurate and efficient prediction remains challenging. Most existing models overlook spatial heterogeneity, employing unified parameters to fit diverse crowd flow patterns across different...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyong Tan, Kaiqi Chen, Min Deng, Baoju Liu, Zhiyuan Zhao, Youjun Tu, Sheng Wu
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/10/1686
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126508395331584
author Xiaoyong Tan
Kaiqi Chen
Min Deng
Baoju Liu
Zhiyuan Zhao
Youjun Tu
Sheng Wu
author_facet Xiaoyong Tan
Kaiqi Chen
Min Deng
Baoju Liu
Zhiyuan Zhao
Youjun Tu
Sheng Wu
author_sort Xiaoyong Tan
collection DOAJ
description Large-scale crowd flow prediction is a critical task in urban management and public safety. However, achieving accurate and efficient prediction remains challenging. Most existing models overlook spatial heterogeneity, employing unified parameters to fit diverse crowd flow patterns across different spatial units, which limits their accuracy. Meanwhile, the massive spatial units significantly increase the computational cost, limiting model efficiency. To address these limitations, we propose a novel model for large-scale crowd flow prediction, namely the Stratified Compressive Sensing Network (SCS-Net). First, we develop a spatially stratified module that posterior adaptively extracts the underlying spatially stratified structure, effectively modeling spatial heterogeneity. Then, we develop compressive sensing modules to compress redundant information from massive spatial units and learn shared crowd flow patterns, enabling efficient prediction. Finally, we conduct experiments on a large-scale real-world dataset. The results demonstrate that SCS-Net outperforms deep learning baseline models by 35.25–139.2% in MAE and 26.3–112.4% in RMSE while reducing GFLOPs by 53–1067 times and shortening training time by 3.1–83.2 times compared to prevalent spatio-temporal prediction models. Moreover, the spatially stratified structure extracted by SCS-Net offers valuable interpretability for spatial heterogeneity in crowd flow patterns, providing deeper insights into urban functional layouts.
format Article
id doaj-art-98cf5fced30b433b9500f2e057b1b624
institution OA Journals
issn 2227-7390
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-98cf5fced30b433b9500f2e057b1b6242025-08-20T02:33:55ZengMDPI AGMathematics2227-73902025-05-011310168610.3390/math13101686SCS-Net: Stratified Compressive Sensing Network for Large-Scale Crowd Flow PredictionXiaoyong Tan0Kaiqi Chen1Min Deng2Baoju Liu3Zhiyuan Zhao4Youjun Tu5Sheng Wu6Department of Geo-Informatics, School of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaDepartment of Geo-Informatics, School of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaDepartment of Geo-Informatics, School of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaDepartment of Geo-Informatics, School of Geosciences and Info-Physics, Central South University, Changsha 410083, ChinaAcademy of Digital China (Fujian), Fuzhou University, Fuzhou 350108, ChinaAcademy of Digital China (Fujian), Fuzhou University, Fuzhou 350108, ChinaAcademy of Digital China (Fujian), Fuzhou University, Fuzhou 350108, ChinaLarge-scale crowd flow prediction is a critical task in urban management and public safety. However, achieving accurate and efficient prediction remains challenging. Most existing models overlook spatial heterogeneity, employing unified parameters to fit diverse crowd flow patterns across different spatial units, which limits their accuracy. Meanwhile, the massive spatial units significantly increase the computational cost, limiting model efficiency. To address these limitations, we propose a novel model for large-scale crowd flow prediction, namely the Stratified Compressive Sensing Network (SCS-Net). First, we develop a spatially stratified module that posterior adaptively extracts the underlying spatially stratified structure, effectively modeling spatial heterogeneity. Then, we develop compressive sensing modules to compress redundant information from massive spatial units and learn shared crowd flow patterns, enabling efficient prediction. Finally, we conduct experiments on a large-scale real-world dataset. The results demonstrate that SCS-Net outperforms deep learning baseline models by 35.25–139.2% in MAE and 26.3–112.4% in RMSE while reducing GFLOPs by 53–1067 times and shortening training time by 3.1–83.2 times compared to prevalent spatio-temporal prediction models. Moreover, the spatially stratified structure extracted by SCS-Net offers valuable interpretability for spatial heterogeneity in crowd flow patterns, providing deeper insights into urban functional layouts.https://www.mdpi.com/2227-7390/13/10/1686crowd flow predictionlarge scalecompressive sensingspatial heterogeneityspatially stratified structure
spellingShingle Xiaoyong Tan
Kaiqi Chen
Min Deng
Baoju Liu
Zhiyuan Zhao
Youjun Tu
Sheng Wu
SCS-Net: Stratified Compressive Sensing Network for Large-Scale Crowd Flow Prediction
Mathematics
crowd flow prediction
large scale
compressive sensing
spatial heterogeneity
spatially stratified structure
title SCS-Net: Stratified Compressive Sensing Network for Large-Scale Crowd Flow Prediction
title_full SCS-Net: Stratified Compressive Sensing Network for Large-Scale Crowd Flow Prediction
title_fullStr SCS-Net: Stratified Compressive Sensing Network for Large-Scale Crowd Flow Prediction
title_full_unstemmed SCS-Net: Stratified Compressive Sensing Network for Large-Scale Crowd Flow Prediction
title_short SCS-Net: Stratified Compressive Sensing Network for Large-Scale Crowd Flow Prediction
title_sort scs net stratified compressive sensing network for large scale crowd flow prediction
topic crowd flow prediction
large scale
compressive sensing
spatial heterogeneity
spatially stratified structure
url https://www.mdpi.com/2227-7390/13/10/1686
work_keys_str_mv AT xiaoyongtan scsnetstratifiedcompressivesensingnetworkforlargescalecrowdflowprediction
AT kaiqichen scsnetstratifiedcompressivesensingnetworkforlargescalecrowdflowprediction
AT mindeng scsnetstratifiedcompressivesensingnetworkforlargescalecrowdflowprediction
AT baojuliu scsnetstratifiedcompressivesensingnetworkforlargescalecrowdflowprediction
AT zhiyuanzhao scsnetstratifiedcompressivesensingnetworkforlargescalecrowdflowprediction
AT youjuntu scsnetstratifiedcompressivesensingnetworkforlargescalecrowdflowprediction
AT shengwu scsnetstratifiedcompressivesensingnetworkforlargescalecrowdflowprediction