A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow prediction

Traffic flow prediction remains a cornerstone for intelligent transportation systems (ITS), influencing both route optimization and environmental efforts. While Recurrent Neural Networks (RNN) and traditional Convolutional Neural Networks (CNN) offer some insights into the spatial–temporal dynamics...

Full description

Saved in:
Bibliographic Details
Main Authors: Karimeh Ibrahim Mohammad Ata, Mohd Khair Hassan, Ayad Ghany Ismaeel, Syed Abdul Rahman Al-Haddad, Thamer‎ Alquthami, Sameer Alani
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Ain Shams Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2090447924004209
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846117954043772928
author Karimeh Ibrahim Mohammad Ata
Mohd Khair Hassan
Ayad Ghany Ismaeel
Syed Abdul Rahman Al-Haddad
Thamer‎ Alquthami
Sameer Alani
author_facet Karimeh Ibrahim Mohammad Ata
Mohd Khair Hassan
Ayad Ghany Ismaeel
Syed Abdul Rahman Al-Haddad
Thamer‎ Alquthami
Sameer Alani
author_sort Karimeh Ibrahim Mohammad Ata
collection DOAJ
description Traffic flow prediction remains a cornerstone for intelligent transportation systems (ITS), influencing both route optimization and environmental efforts. While Recurrent Neural Networks (RNN) and traditional Convolutional Neural Networks (CNN) offer some insights into the spatial–temporal dynamics of traffic data, they’re often limited when navigating sparse and extended spatial–temporal patterns. In response, the CNN-GRUSKIP model emerges as a pioneering approach. Notably, it integrates the GRU-SKIP mechanism, a hybrid model that leverages the Gate Recurrent Unit’s (GRU) capabilities to process sequences with the ’SKIP’ feature’s ability to bypass and connect longer temporal dependencies, making it especially potent for traffic flow predictions with erratic and extended patterns. Another distinctive aspect is its non-standard 6-layer CNN, meticulously designed for in-depth spatiotemporal correlation extraction. The model comprises (1) the specialized CNN feature extraction, (2) the GRU-SKIP enhanced long-temporal module adept at capturing extended patterns, (3) a transformer module employing encoder-decoder and multi-attention mechanisms to hone prediction accuracy and trim model complexity, and (4) a bespoke prediction module. When tested against real-world datasets from California’s Caltrans Performance Measurement System (PeMS), specifically PeMS districts 4 and 8, the CNN-GRUSKIP consistently outperformed established models such as ARIMA, Graph Wave Net, HA, LSTM, STGCN, and APTN. With its potent predictive prowess and adaptive architecture, the CNN-GRUSKIP model stands to redefine ITS applications, especially where nuanced traffic dynamics are in play.
format Article
id doaj-art-1325b31f720e4ecfb85901e8210a30c0
institution Kabale University
issn 2090-4479
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Ain Shams Engineering Journal
spelling doaj-art-1325b31f720e4ecfb85901e8210a30c02024-12-18T08:48:13ZengElsevierAin Shams Engineering Journal2090-44792024-12-011512103045A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow predictionKarimeh Ibrahim Mohammad Ata0Mohd Khair Hassan1Ayad Ghany Ismaeel2Syed Abdul Rahman Al-Haddad3Thamer‎ Alquthami4Sameer Alani5Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra Malaysia, 43400, UPM Serdang, Selangor Darul Ehsan, Malaysia; Corresponding authors.Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra Malaysia, 43400, UPM Serdang, Selangor Darul Ehsan, Malaysia; Corresponding authors.Computer Technology Engineering, College of Engineering Technology, Al-Kitab University, IraqDepartment of Computer and Communication Systems Engineering, Universiti Putra Malasia, Seri Kembangan, Selangor 43400, MalaysiaElectrical and Computer Engineering Department, King Abdulaziz University, Jeddah 21589, Saudi ArabiaComputer Center, University of Anbar, IraqTraffic flow prediction remains a cornerstone for intelligent transportation systems (ITS), influencing both route optimization and environmental efforts. While Recurrent Neural Networks (RNN) and traditional Convolutional Neural Networks (CNN) offer some insights into the spatial–temporal dynamics of traffic data, they’re often limited when navigating sparse and extended spatial–temporal patterns. In response, the CNN-GRUSKIP model emerges as a pioneering approach. Notably, it integrates the GRU-SKIP mechanism, a hybrid model that leverages the Gate Recurrent Unit’s (GRU) capabilities to process sequences with the ’SKIP’ feature’s ability to bypass and connect longer temporal dependencies, making it especially potent for traffic flow predictions with erratic and extended patterns. Another distinctive aspect is its non-standard 6-layer CNN, meticulously designed for in-depth spatiotemporal correlation extraction. The model comprises (1) the specialized CNN feature extraction, (2) the GRU-SKIP enhanced long-temporal module adept at capturing extended patterns, (3) a transformer module employing encoder-decoder and multi-attention mechanisms to hone prediction accuracy and trim model complexity, and (4) a bespoke prediction module. When tested against real-world datasets from California’s Caltrans Performance Measurement System (PeMS), specifically PeMS districts 4 and 8, the CNN-GRUSKIP consistently outperformed established models such as ARIMA, Graph Wave Net, HA, LSTM, STGCN, and APTN. With its potent predictive prowess and adaptive architecture, the CNN-GRUSKIP model stands to redefine ITS applications, especially where nuanced traffic dynamics are in play.http://www.sciencedirect.com/science/article/pii/S2090447924004209Traffic Flow PredictionConvolutional Neural NetworkGRUSkip FunctionTransformerSpatial-temporal prediction
spellingShingle Karimeh Ibrahim Mohammad Ata
Mohd Khair Hassan
Ayad Ghany Ismaeel
Syed Abdul Rahman Al-Haddad
Thamer‎ Alquthami
Sameer Alani
A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow prediction
Ain Shams Engineering Journal
Traffic Flow Prediction
Convolutional Neural Network
GRU
Skip Function
Transformer
Spatial-temporal prediction
title A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow prediction
title_full A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow prediction
title_fullStr A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow prediction
title_full_unstemmed A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow prediction
title_short A multi-Layer CNN-GRUSKIP model based on transformer for spatial −TEMPORAL traffic flow prediction
title_sort multi layer cnn gruskip model based on transformer for spatial temporal traffic flow prediction
topic Traffic Flow Prediction
Convolutional Neural Network
GRU
Skip Function
Transformer
Spatial-temporal prediction
url http://www.sciencedirect.com/science/article/pii/S2090447924004209
work_keys_str_mv AT karimehibrahimmohammadata amultilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT mohdkhairhassan amultilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT ayadghanyismaeel amultilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT syedabdulrahmanalhaddad amultilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT thameralquthami amultilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT sameeralani amultilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT karimehibrahimmohammadata multilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT mohdkhairhassan multilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT ayadghanyismaeel multilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT syedabdulrahmanalhaddad multilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT thameralquthami multilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction
AT sameeralani multilayercnngruskipmodelbasedontransformerforspatialtemporaltrafficflowprediction