Wavelet decomposition-based enhanced time delay awareness for traffic flow prediction

doi:10.11772/j.issn.1001-9081.2024111602

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (11): 3649-3657.DOI: 10.11772/j.issn.1001-9081.2024111602

• Advanced computing • Previous Articles

Wavelet decomposition-based enhanced time delay awareness for traffic flow prediction

Lihu PAN¹(), Menglin ZHANG¹, Guangrui FAN¹, Linliang ZHANG², Rui ZHANG¹

^1.School of Computer Science and Technology，Taiyuan University of Science and Technology，Taiyuan Shanxi 030024，China
^2.Shanxi Intelligent Transportation Institute Company Limited，Taiyuan Shanxi 030036，China

Received:2024-11-14 Revised:2025-03-27 Accepted:2025-04-08 Online:2025-04-22 Published:2025-11-10
Contact: Lihu PAN
About author:ZHANG Menglin， born in 2001， M. S. candidate. His research interests include traffic prediction， artificial intelligence.
FAN Guangrui， born in 1992， Ph. D. candidate. His research interests include deep learning， smart transportation， social networks， big data.
ZHANG Linliang， born in 1984， Ph. D.， senior engineer. His research interests include deep learning， machine learning， computer vision， big data mining.
ZHANG Rui， born in 1987， Ph. D.， associate professor. His research interests include intelligent information processing.
Supported by:
Shanxi Province Basic Research Program Project(202203021221145);Shanxi Province Graduate Joint Training Demonstration Base Project(2022JD11)

基于小波分解的增强时间延迟感知交通流量预测

潘理虎¹(), 张梦麟¹, 樊光瑞¹, 张林梁², 张睿¹

^1.太原科技大学计算机科学与技术学院，太原 030024
^2.山西省智慧交通研究院有限公司，太原 030036

通讯作者: 潘理虎
作者简介:张梦麟（2001—），男，山西太原人，硕士研究生，主要研究方向：交通预测、人工智能
樊光瑞（1992—），男，山西汾阳人，博士研究生，主要研究方向：深度学习、智慧交通、社交网络、大数据
张林梁（1984—），男，山东安丘人，高级工程师，博士，主要研究方向：深度学习、机器学习、计算机视觉、大数据挖掘
张睿（1987—），男，山西太原人，副教授，博士，CCF高级会员，主要研究方向：智能信息处理。
基金资助:
山西省基础研究计划项目(202203021221145);山西省研究生联合培养示范基地项目(2022JD11)

Abstract

Abstract:

Traditional traffic flow prediction models often fail to effectively account for temporal delays across regions and time periods， and struggle to capture both short-term fluctuations and long-term trends in traffic flow. To address these limitations， a Wavelet Transform and Attention-based Latency-Aware long short Graph Neural Network （WTA-LAGNN） was proposed. Firstly， wavelet decomposition was applied to separate traffic flow data into long-term trend and short-term fluctuation patterns. Key features in the short-term fluctuation pattern were enhanced using a feature enhancement module， improving the model's sensitivity to short-term variations. For the long-term trend， a sequence-enhanced multi-head self-attention was designed to capture sustained changes in flow. To address temporal delay effects， a time delay-aware layer was designed to optimize spatio-temporal dependencies in traffic flow propagation between regions. Finally， the fusion layer outputted the prediction results. Experiments were conducted on real highway traffic datasets including PeMS03， PeMS04， PeMS07 and PeMS08 for 60-minute flow prediction. The results showed that compared to Spatio-Temporal Graph Neural Controlled Differential Equation（STG-NCDE）， WTA-LAGNN reduced the Mean Absolute Error （MAE） and Root Mean Square Error （RMSE） by 5.14% and 2.69%， as well as 5.80% and 2.69% on the PeMS03 and PeMS07 datasets， respectively； compared to Traffic Flow Matrix-based Graph Convolutional Attention Mechanism （TFM-GCAM）， WTA-LAGNN reduced the MAE and RMSE by 9.28% and 3.32% on PeMS08； compared to Spatio-Temporal Fusion Graph Convolutional Network（STFGCN）， WTA-LAGNN reduced the MAE and RMSE by 3.53% and 2.72% on PeMS04， respectively. These results demonstrate that WTA-LAGNN outperforms comparison baseline models， and can effectively capture spatio-temporal dependencies， thereby improving traffic flow prediction precision.

Key words: traffic flow prediction, wavelet decomposition, time delay awareness, attention mechanism, spatio-temporal model

摘要：

传统交通流量预测模型未能有效考虑地区间和时段间的时间延迟效应，且难以同时捕捉交通流量的短期波动与长期趋势。为此，提出一种结合小波分解与时间延迟感知的时空预测模型（WTA-LAGNN）。首先，结合小波分解将交通流量数据分为长期趋势模式和短期波动模式：短期波动模式通过特征增强模块强化关键特征，提升对短期波动的敏感性；针对长期趋势，设计了序列增强的多头自注意力机制捕捉流量的长期变化。其次，为了处理时间延迟效应，设计了时间序列延迟感知层，优化区域间流量传播的时空依赖关系。最后，通过融合层生成最终预测结果。基于现实高速公路交通数据集PeMS03、PeMS04、PeMS07、PeMS08进行60 min流量预测，结果表明，在PeMS03和PeMS07数据集上，与时空图神经控制微分方程（STG-NCDE）相比，WTA-LAGNN的平均绝对误差（MAE）、均方根误差（RMSE）分别降低了5.14%、2.69%和5.80%、2.69%；在PeMS08数据集上，与交通流量矩阵-图卷积注意力模型（TFM-GCAM）相比，WTA-LAGNN的MAE、RMSE分别下降了9.28%、3.32%；在PeMS04数据集上，与时空融合图卷积网络（STFGCN）相比，WTA-LAGNN的MAE、RMSE分别降低了3.53%、2.72%。WTA-LAGNN的整体模型性能上优于对比模型，能更有效地捕捉时空依赖关系，提升流量预测精度。

关键词: 交通流量预测, 小波分解, 时间延迟感知, 注意力机制, 时空模型

CLC Number:

TP391

Lihu PAN, Menglin ZHANG, Guangrui FAN, Linliang ZHANG, Rui ZHANG. Wavelet decomposition-based enhanced time delay awareness for traffic flow prediction[J]. Journal of Computer Applications, 2025, 45(11): 3649-3657.

潘理虎, 张梦麟, 樊光瑞, 张林梁, 张睿. 基于小波分解的增强时间延迟感知交通流量预测[J]. 《计算机应用》唯一官方网站, 2025, 45(11): 3649-3657.

Figures/Tables 12

Fig. 1 Overall structure of WTA-LAGNN

Fig. 2 Structure of feature enhancement layer

Fig. 3 Structure of multi-head attention layer

Fig. 4 Structure of time-series delay-aware layer

Tab.1 Dataset summary

数据集	节点数	边数	时间步数	时间间隔/min	时间范围
PeMS03	358	547	26 208	5	2018-09-01 — 2018-11-30
PeMS04	307	340	16 992	5	2018-01-01 — 2018-02-28
PeMS07	883	866	28 224	5	2017-05-01 — 2017-08-31
PeMS08	170	295	17 856	5	2016-07-01— 2016-08-31

Tab. 2 Settings of WTA-LAGNN on four datasets

数据集	处理批次大小b	卷积核大小k	小波基函数	路网邻接矩阵阈值 $δ$
PeMS03	64	5	Symlet 2	0.12
PeMS04	64	5	Daubechies 1	0.12
PeMS07	32	5	Daubechies 1	0.13
PeMS08	128	9	Coiflet 1	0.10

Tab. 2 Settings of WTA-LAGNN on four datasets

数据集	处理批次大小b	卷积核大小k	小波基函数	路网邻接矩阵阈值 $δ$
PeMS03	64	5	Symlet 2	0.12
PeMS04	64	5	Daubechies 1	0.12
PeMS07	32	5	Daubechies 1	0.13
PeMS08	128	9	Coiflet 1	0.10

Tab. 3 Performance comparison of different models on four datasets

模型	PeMS03			PeMS04			PeMS07			PeMS08
模型	MAE	RMSE	MAPE/%	MAE	RMSE	MAPE/%	MAE	RMSE	MAPE/%	MAE	RMSE	MAPE/%
HA	31.58	52.39	33.78	38.03	59.24	27.88	45.12	65.64	24.51	34.86	59.24	27.88
VAR	23.65	38.26	24.51	24.54	38.61	17.24	50.22	75.63	32.22	19.19	29.81	13.10
DCRNN	17.99	30.31	18.34	21.22	33.44	14.17	25.22	38.61	11.82	16.82	26.36	10.92
STSGCN	17.48	29.21	16.78	21.19	33.65	13.90	24.26	39.03	10.21	17.13	26.80	10.96
STFGNN	16.76	28.33	16.31	19.82	31.87	13.03	23.43	36.57	9.20	16.89	26.01	10.57
Z-GCNETs	16.64	28.15	16.39	19.50	31.61	12.78	—	—	—	15.76	25.11	10.01
STG-NCDE	15.57	27.09	15.06	19.21	31.09	12.76	20.53	33.84	8.80	15.45	24.81	9.92
ST-CGCN	16.66	27.71	16.30	20.79	33.62	13.71	23.50	37.28	9.71	17.84	26.43	10.63
GSTPRN	—	—	—	19.45	31.91	12.96	—	—	—	15.68	24.96	10.09
GRAM-ODE	15.72	26.40	15.98	19.55	31.05	12.66	21.75	34.42	9.74	16.05	25.17	10.58
TFM-GCAM	—	—	—	—	—	—	—	—	—	14.54	23.76	9.65
TPLLM	—	—	—	19.53	31.93	12.81	—	—	—	15.45	25.35	9.88
STFGCN	—	—	—	18.95	30.90	12.36	—	—	—	15.23	24.35	9.83
本文模型	14.77	26.36	15.19	18.28	30.06	12.43	19.34	32.93	8.08	13.19	22.97	8.84

Tab. 4 Ablation experimental results of WTA-LAGNN

模型	MAE	RMSE	MAPE/%
w/o wavedec	13.53	23.77	9.04
w/o T-D-S	13.60	23.81	9.01
w/o D-S	13.50	23.53	8.98
w/o T-D	13.46	23.43	9.00
w/o T-S	13.38	23.49	8.92
w/o D	13.39	23.37	8.98
w/o S	13.33	23.21	8.85
w/o T	13.27	23.18	8.88
WTA-LAGNN	13.19	22.97	8.84

Fig. 5 Module contribution analysis of WTA-LAGNN in 12-step prediction

Tab. 5 Impact of the number of attention heads on model performance

注意力头数	MAE	RMSE	MAPE/%
2	14.45	23.56	9.65
4	13.71	23.13	9.05
8	13.19	22.97	8.84
16	13.68	23.21	8.99

Tab. 6 Impact of convolution kernel size on model performance

卷积核大小	MAE	RMSE	MAPE/%
5	13.37	23.19	8.95
7	13.25	23.03	8.98
9	13.19	22.97	8.84
11	13.52	23.75	8.91

Fig. 6 Traffic flow prediction visualization

References 37

[1]	WANG B， ZHENG H， QIAN K， et al. Edge computing and AI-driven intelligent traffic monitoring and optimization［J］. Applied and Computational Engineering， 2024， 77： 225-230.
[2]	FOULADGAR M， PARCHAMI M， ELMASRI R， et al. Scalable deep traffic flow neural networks for urban traffic congestion prediction［C］// Proceedings of the 2017 International Joint Conference on Neural Networks. Piscataway： IEEE， 2017： 2251-2258.
[3]	杨立宁，李艳婷.基于SVD和ARIMA的时空序列分解与预测［J］. 计算机工程，2021，47（3）：53-61.
	YANG L N， LI Y T. Spatio-temporal sequence decomposition and prediction based on SVD and ARIMA［J］. Computer Engineering， 2021， 47（3）： 53-61.
[4]	CHANDRA S R， AL-DEEK H. Predictions of freeway traffic speeds and volumes using vector autoregressive models［J］. Journal of Intelligent Transportation Systems， 2009， 13（2）： 53-72.
[5]	KIM Y， BANG H. Introduction to Kalman filter and its applications［M］// GOVAERS F. Introduction and implementations of the Kalman filter. London： IntechOpen Limited， 2019： 1-16.
[6]	JEONG S， BAEK Y， SON S H. Distributed urban platooning towards high flexibility， adaptability， and stability［J］. Sensors， 2021， 21（8）： No.2684.
[7]	ZHUANG W， CAO Y. Short-term traffic flow prediction based on a K-Nearest neighbor and bidirectional long short-term memory model［J］. Applied Sciences， 2023， 13（4）： No.2681.
[8]	SAYED S A， ABDEL-HAMID Y， HEFNY H A. Artificial intelligence-based traffic flow prediction： a comprehensive review［J］. Journal of Electrical Systems and Information Technology， 2023， 10： No.13.
[9]	CHO K， VAN MERRIËNBOER B， GULCEHRE C， et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg： ACL， 2014： 1724-1734.
[10]	CUI Z， KE R， PU Z， et al. Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values［J］. Transportation Research Part C： Emerging Technologies， 2020， 118： No.102674.
[11]	MA X， TAO Z， WANG Y， et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data［J］. Transportation Research Part C： Emerging Technologies， 2015， 54： 187-197.
[12]	杨鑫，陈雪妮，吴春江，等.结合变种残差模型和Transformer的城市公路短时交通流预测［J］.计算机应用，2024，44（9）：2947-2951.
	YANG X， CHEN X N， WU C J， et al. Short-term traffic flow prediction of urban highway based on variant residual model and Transformer［J］. Journal of Computer Applications， 2024， 44（9）： 2947-2951.
[13]	DO L N N， VU H L， VO B Q， et al. An effective spatial-temporal attention based neural network for traffic flow prediction［J］. Transportation Research Part C： Emerging Technologies， 2019， 108： 12-28.
[14]	CIRSTEA R G， YANG B， GUO C， et al. Towards spatio-temporal aware traffic time series forecasting［C］// Proceedings of the IEEE 38th International Conference on Data Engineering. Piscataway： IEEE， 2022： 2900-2913.
[15]	LIU H， ZHU C， ZHANG D， et al. Attention-based spatial-temporal graph convolutional recurrent networks for traffic forecasting［C］// Proceedings of the 2023 International Conference on Advanced Data Mining and Applications， LNCS 14176. Cham： Springer， 2023： 630-645.
[16]	ZHAO L， SONG Y， ZHANG C， et al. T-GCN： a temporal graph convolutional network for traffic prediction［J］. IEEE Transactions on Intelligent Transportation Systems， 2020， 21（9）： 3848-3858.
[17]	LI Y， YU R， SHAHABI C， et al. Diffusion convolutional recurrent neural network： data-driven traffic forecasting［EB/OL］. ［2024-07-17］. .
[18]	SONG C， LIN Y， GUO S， et al. Spatial-temporal synchronous graph convolutional networks： a new framework for spatial-temporal network data forecasting［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2020： 914-921.
[19]	LI M， ZHU Z. Spatial-temporal fusion graph neural networks for traffic flow forecasting［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2021： 4189-4196.
[20]	YU L， LIU W， WU D， et al. Spatial-temporal combination and multi-head flow-attention network for traffic flow prediction［J］. Scientific Reports， 2024， 14： No.9604.
[21]	CHEN Y， SEGOVIA-DOMINGUEZ I， GEL Y R. Z-GCNETs： time zigzags at graph convolutional networks for time series forecasting［C］// Proceedings of the 38th International Conference on Machine Learning. New York： JMLR.org， 2021： 1684-1694.
[22]	XIONG Y， WANG H. Spatio-temporal contextual conditions causality and spread delay-aware modeling for traffic flow prediction［J］. IEEE Access， 2024， 12： 21250-21261.
[23]	BAO Y， HUANG J， SHEN Q， et al. Spatial-temporal complex graph convolution network for traffic flow prediction［J］. Engineering Applications of Artificial Intelligence， 2023， 121： No.106044.
[24]	赵文竹，袁冠，张艳梅，等.多视角融合的时空动态GCN城市交通流量预测［J］.软件学报，2024，35（4）：1751-1773.
	ZHAO W Z， YUAN G， ZHANG Y M， et al. Multi-view fused spatial-temporal dynamic GCN for urban traffic flow prediction［J］. Journal of Software， 2024， 35（4）： 1751-1773.
[25]	MA Y， LOU H， YAN M， et al. Spatio-temporal fusion graph convolutional network for traffic flow forecasting［J］. Information Fusion， 2024， 104： No.102196.
[26]	HARROU F， ZEROUAL A， KADRI F， et al. Enhancing road traffic flow prediction with improved deep learning using wavelet Transforms［J］. Results in Engineering， 2024， 23： No.102342.
[27]	YANG S， QIAN S. Understanding and predicting travel time with spatio-temporal features of network traffic flow， weather and incidents［J］. IEEE Intelligent Transportation Systems Magazine， 2019， 11（3）： 12-28.
[28]	MA C， DAI G， ZHOU J. Short-term traffic flow prediction for urban road sections based on time series analysis and LSTM_BILSTM method［J］. IEEE Transactions on Intelligent Transportation Systems， 2022， 23（6）： 5615-5624.
[29]	WANG S， ZHANG M， MIAO H， et al. Multivariate correlation-aware spatio-temporal graph convolutional networks for multi-scale traffic prediction［J］. ACM Transactions on Intelligent Systems and Technology， 2022， 13（3）： No.38.
[30]	LI H， LV Z， LI J， et al. Traffic flow forecasting in the covid-19： a deep spatial-temporal model based on discrete wavelet transformation［J］. ACM Transactions on Knowledge Discovery from Data， 2023， 17（5）： No.64.
[31]	JANA J， TRIPATHI S， CHOWDHURY R S， et al. An area efficient VLSI architecture for 1-D and 2-D Discrete Wavelet Transform （DWT） and Inverse Discrete Wavelet Transform （IDWT）［C］// Proceedings of the 2021 International Conference on Devices for Integrated Circuit. Piscataway： IEEE， 2021： 378-382.
[32]	FOUMANI N M， TAN C W， WEBB G I， et al. Improving position encoding of transformers for multivariate time series classification［J］. Data Mining and Knowledge Discovery， 2024， 38（1）： 22-48.
[33]	WANG K， AN J， ZHOU M， et al. Minority-weighted graph neural network for imbalanced node classification in social networks of internet of people［J］. IEEE Internet of Things Journal， 2023， 10（1）： 330-340.
[34]	LEE-THORP J， AINSLIE J， ECKSTEIN I， et al. FNet： mixing tokens with Fourier Transforms［C］// Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies. Stroudsburg： ACL， 2022： 4296-4313.
[35]	CHOI J， CHOI H， HWANG J， et al. Graph neural controlled differential equations for traffic forecasting［C］// Proceedings of the 36th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2022： 6367-6374.
[36]	CHEN J， ZHENG L， HU Y， et al. Traffic flow matrix-based graph neural network with attention mechanism for traffic flow prediction［J］. Information Fusion， 2024， 104： No.102146.
[37]	REN Y， CHEN Y， LIU S， et al. TPLLM： a traffic prediction framework based on pretrained large language models［EB/OL］. ［2024-05-22］. .

Wavelet decomposition-based enhanced time delay awareness for traffic flow prediction

基于小波分解的增强时间延迟感知交通流量预测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 37

Related Articles 15

Recommended Articles

Metrics

[1]	Jinggang LYU, Shaorui PENG, Shuo GAO, Jin ZHOU. Speech enhancement network driven by complex frequency attention and multi-scale frequency enhancement [J]. Journal of Computer Applications, 2025, 45(9): 2957-2965.
[2]	Weigang LI, Jiale SHAO, Zhiqiang TIAN. Point cloud classification and segmentation network based on dual attention mechanism and multi-scale fusion [J]. Journal of Computer Applications, 2025, 45(9): 3003-3010.
[3]	Xiang WANG, Zhixiang CHEN, Guojun MAO. Multivariate time series prediction method combining local and global correlation [J]. Journal of Computer Applications, 2025, 45(9): 2806-2816.
[4]	Haifeng WU, Liqing TAO, Yusheng CHENG. Partial label regression algorithm integrating feature attention and residual connection [J]. Journal of Computer Applications, 2025, 45(8): 2530-2536.
[5]	Chao JING, Yutao QUAN, Yan CHEN. Improved multi-layer perceptron and attention model-based power consumption prediction algorithm [J]. Journal of Computer Applications, 2025, 45(8): 2646-2655.
[6]	Jinhao LIN, Chuan LUO, Tianrui LI, Hongmei CHEN. Thoracic disease classification method based on cross-scale attention network [J]. Journal of Computer Applications, 2025, 45(8): 2712-2719.
[7]	Jin ZHOU, Yuzhi LI, Xu ZHANG, Shuo GAO, Li ZHANG, Jiachuan SHENG. Modulation recognition network for complex electromagnetic environments [J]. Journal of Computer Applications, 2025, 45(8): 2672-2682.
[8]	Yihan WANG, Chong LU, Zhongyuan CHEN. Multimodal sentiment analysis model with cross-modal text information enhancement [J]. Journal of Computer Applications, 2025, 45(7): 2237-2244.
[9]	Chen LIANG, Yisen WANG, Qiang WEI, Jiang DU. Source code vulnerability detection method based on Transformer-GCN [J]. Journal of Computer Applications, 2025, 45(7): 2296-2303.
[10]	Haoyu LIU, Pengwei KONG, Yaoli WANG, Qing CHANG. Pedestrian detection algorithm based on multi-view information [J]. Journal of Computer Applications, 2025, 45(7): 2325-2332.
[11]	Xiaoqiang ZHAO, Yongyong LIU, Yongyong HUI, Kai LIU. Batch process quality prediction model using improved time-domain convolutional network with multi-head self-attention mechanism [J]. Journal of Computer Applications, 2025, 45(7): 2245-2252.
[12]	Huibin WANG, Zhan’ao HU, Jie HU, Yuanwei XU, Bo WEN. Time series forecasting model based on segmented attention mechanism [J]. Journal of Computer Applications, 2025, 45(7): 2262-2268.
[13]	Weigang LI, Xinyi LI, Yongqiang WANG, Yuntao ZHAO. Point cloud classification and segmentation method based on adaptive dynamic graph convolution and parameter-free attention [J]. Journal of Computer Applications, 2025, 45(6): 1980-1986.
[14]	Sheping ZHAI, Yan HUANG, Qing YANG, Rui YANG. Multi-view entity alignment combining triples and text attributes [J]. Journal of Computer Applications, 2025, 45(6): 1793-1800.
[15]	Xiang WANG, Qianqian CUI, Xiaoming ZHANG, Jianchao WANG, Zhenzhou WANG, Jialin SONG. Wireless capsule endoscopy image classification model based on improved ConvNeXt [J]. Journal of Computer Applications, 2025, 45(6): 2016-2024.