Enhancing Traffic Flow Forecasting with Deep-Learning and Noise Reduction Techniques

Traditional short-term traffic volume forecasting approaches make it difficult to predict the highly spatiotemporally coupled short-time traffic. To tackle the problem, this paper first proposes a variational modal algorithm (GWO-VMD) based on the optimization of the gray wolf search algorithm. It a...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinqiu Zhao, Le Yu, Shuhua Wang, Zhonghao Zhang
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Discrete Dynamics in Nature and Society
Online Access:http://dx.doi.org/10.1155/2024/1928189
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846144750191640576
author Jinqiu Zhao
Le Yu
Shuhua Wang
Zhonghao Zhang
author_facet Jinqiu Zhao
Le Yu
Shuhua Wang
Zhonghao Zhang
author_sort Jinqiu Zhao
collection DOAJ
description Traditional short-term traffic volume forecasting approaches make it difficult to predict the highly spatiotemporally coupled short-time traffic. To tackle the problem, this paper first proposes a variational modal algorithm (GWO-VMD) based on the optimization of the gray wolf search algorithm. It aims to decompose and reduce the noise of short-time traffic flows. Meanwhile, it reduces the intricacy of data sequences and enhances the regularity pattern. To address the insufficient utilization of spatiotemporal features, this paper presents an innovative deep-learning traffic prediction framework based on the stacking of multiple temporal trend-aware graph attention (TGA) layers and gated temporal convolution (GTC) layers, which are called trend-aware temporal graph neural network (TTGAN). TGA dynamically models the space-time relationships of traffic data, and GTC models the temporal characteristics of traffic data. The experimental findings demonstrate that the MAPE model, as presented, achieves a reduction of 9% and 2% compared to the AGCRN and GWNET models, respectively, in the domain of deep spatiotemporal graph modeling. Data decomposition and noise reduction are necessary to achieve accurate results. This model has superior performance in terms of mean absolute error (MAE), coefficient of determination (R2), and explained variance score (EVAR).
format Article
id doaj-art-c9a398c3b6dd4a2982c42df429b45f2c
institution Kabale University
issn 1607-887X
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Discrete Dynamics in Nature and Society
spelling doaj-art-c9a398c3b6dd4a2982c42df429b45f2c2024-12-02T06:54:46ZengWileyDiscrete Dynamics in Nature and Society1607-887X2024-01-01202410.1155/2024/1928189Enhancing Traffic Flow Forecasting with Deep-Learning and Noise Reduction TechniquesJinqiu Zhao0Le Yu1Shuhua Wang2Zhonghao Zhang3School of ArchitectureShenzhen Technology UniversityCollege of Transport and CommunicationsCollege of Transport and CommunicationsTraditional short-term traffic volume forecasting approaches make it difficult to predict the highly spatiotemporally coupled short-time traffic. To tackle the problem, this paper first proposes a variational modal algorithm (GWO-VMD) based on the optimization of the gray wolf search algorithm. It aims to decompose and reduce the noise of short-time traffic flows. Meanwhile, it reduces the intricacy of data sequences and enhances the regularity pattern. To address the insufficient utilization of spatiotemporal features, this paper presents an innovative deep-learning traffic prediction framework based on the stacking of multiple temporal trend-aware graph attention (TGA) layers and gated temporal convolution (GTC) layers, which are called trend-aware temporal graph neural network (TTGAN). TGA dynamically models the space-time relationships of traffic data, and GTC models the temporal characteristics of traffic data. The experimental findings demonstrate that the MAPE model, as presented, achieves a reduction of 9% and 2% compared to the AGCRN and GWNET models, respectively, in the domain of deep spatiotemporal graph modeling. Data decomposition and noise reduction are necessary to achieve accurate results. This model has superior performance in terms of mean absolute error (MAE), coefficient of determination (R2), and explained variance score (EVAR).http://dx.doi.org/10.1155/2024/1928189
spellingShingle Jinqiu Zhao
Le Yu
Shuhua Wang
Zhonghao Zhang
Enhancing Traffic Flow Forecasting with Deep-Learning and Noise Reduction Techniques
Discrete Dynamics in Nature and Society
title Enhancing Traffic Flow Forecasting with Deep-Learning and Noise Reduction Techniques
title_full Enhancing Traffic Flow Forecasting with Deep-Learning and Noise Reduction Techniques
title_fullStr Enhancing Traffic Flow Forecasting with Deep-Learning and Noise Reduction Techniques
title_full_unstemmed Enhancing Traffic Flow Forecasting with Deep-Learning and Noise Reduction Techniques
title_short Enhancing Traffic Flow Forecasting with Deep-Learning and Noise Reduction Techniques
title_sort enhancing traffic flow forecasting with deep learning and noise reduction techniques
url http://dx.doi.org/10.1155/2024/1928189
work_keys_str_mv AT jinqiuzhao enhancingtrafficflowforecastingwithdeeplearningandnoisereductiontechniques
AT leyu enhancingtrafficflowforecastingwithdeeplearningandnoisereductiontechniques
AT shuhuawang enhancingtrafficflowforecastingwithdeeplearningandnoisereductiontechniques
AT zhonghaozhang enhancingtrafficflowforecastingwithdeeplearningandnoisereductiontechniques