Traffic flow forecasting with multi-resolution trend period decoupling interaction

doi:10.3785/j.issn.1008-973X.2025.07.004

Journal of ZheJiang University (Engineering Science)

2025, Vol. 59

Issue (7): 1362-1372 DOI: 10.3785/j.issn.1008-973X.2025.07.004

Traffic flow forecasting with multi-resolution trend period decoupling interaction

Yue HOU(

),Tiantian WANG,Xin ZHANG,Jie YIN

School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China

Download:

HTML

PDF(1278KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A traffic flow prediction model with multi-resolution trend period decoupling interaction was proposed, aiming at the problems of traffic flow temporal characteristic transfer and insufficient trend period feature extraction in the real road network. The time domain decoupling module decoupled the time series data into multi-resolution trend and fluctuation components, ensuring that the trend characteristics did not change with the fluctuation characteristics, thereby addressing the issue of shifting temporal characteristics in traffic flow. The multi-resolution trend period interaction module integrated significant periodic features by applying even-odd downsampling to the trends and then completed the interaction with the original even-odd sequences. The time-frequency fluctuation feature extraction module effectively captured the instantaneous changes in fluctuation components by combining multi-resolution causal convolution. The frequency domain reconstruction module performed the traffic flow prediction task under time-frequency domain conversion by utilizing inverse discrete wavelet transform. Comparative experiments on model performance were conducted in the PeMSD4 and PeMSD8 traffic datasets. Results show that compared to the downsampled convolutional interaction model, the proposed model achieves a reduction in mean absolute error, rooted mean square error, and mean absolute percentage error by 26.21%, 30.49%; 25.97%, 32.51%; and 8.00%, 25.49%, respectively, demonstrating the superior performance of the proposed model.

Key words： traffic flow prediction multi-resolution trend characterization periodic characterization wavelet transform

Received: 01 July 2024 Published: 25 July 2025

CLC:

U 491.1

Fund: 国家自然科学基金资助项目（62063014, 62363020）；甘肃省自然科学基金资助项目（22JR5RA365）.

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Yue HOU
	Tiantian WANG
	Xin ZHANG
	Jie YIN

Cite this article:

Yue HOU,Tiantian WANG,Xin ZHANG,Jie YIN. Traffic flow forecasting with multi-resolution trend period decoupling interaction. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1362-1372.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2025.07.004 OR https://www.zjujournals.com/eng/Y2025/V59/I7/1362

多分辨率趋势周期解耦交互的交通流预测

针对现实路网交通流时序特性转移、趋势周期特征提取不充分的问题，提出多分辨率趋势周期解耦交互的交通流预测模型. 时域解耦模块将时序数据解耦为多分辨率趋势、波动分量，使趋势特性不随波动特性变化而变化，解决交通流时间特性转移问题. 多分辨率趋势周期交互模块利用趋势奇偶下采样的方式融合显著性周期特征，完成与奇偶原序列间的交互. 时频波动特征提取模块结合多分辨率因果卷积实现波动分量瞬时变化的有效捕捉，频域重构模块以逆离散小波变换的方式实现频时域转换下的交通流预测任务. 在交通数据集PeMSD4和PeMSD8中开展的模型性能对比实验结果表明，相较于下采样卷积交互模型，所提模型的平均绝对误差、均方根误差及平均绝对百分误差分别降低了26.21%、30.49%，25.97%、32.51%，8.00%、25.49%，所提模型的性能更优.

关键词： 交通流预测, 多分辨率, 趋势特性, 周期特性, 小波变换

Fig.1 Overall framework of traffic flow prediction model with multi-resolution trend period decoupling interaction

Fig.2 Two-level discrete wavelet transform

Fig.3 Process of constructing 2D significant period matrices

Fig.4 Structure of multi-resolution trend period interaction module

Fig.5 Traffic flow data and mutation points for one day at node of PeMSD8 dataset

Fig.6 Causal convolutional structure of 2D multi-resolution convolutional blocks

Tab.1 Traffic flow prediction accuracy of different models in two datasets

Tab.2 Traffic flow prediction accuracy of different models at time steps in two datasets

Fig.7 Comparison of ture values with predicted values of proposed model in two datasets

Tab.3 Ablation study results of proposed model on PeMSD8 dataset

Tab.4 Ablation study results of proposed model at different time steps

Fig.8 Output characteristic heat map of two modules of proposed model in PeMSD4 dataset

Fig.9 Output characteristic heat map of two modules of proposed model in PeMSD8 dataset

Tab.5 Traffic flow prediction accuracy of proposed model at different temporal scales

Fig.10 Multi-scale periodograms of MTPDI model on PeMSD4 dataset

Tab.6 Traffic flow prediction accuracy of different salient frequency parameters


[1]	崔建勋, 要甲, 赵泊媛基于深度学习的短期交通流预测方法综述[J]. 交通运输工程学报, 2024, 24 (2): 50- 64 CUI Jianxun, YAO Jia, ZHAO Boyuan Review on short-term traffic flow prediction methods based on deep learning[J]. Journal of Traffic and Transportation Engineering, 2024, 24 (2): 50- 64

[2]	AHMED M S, COOK A R Analysis of freeway traffic time-series data by using box-jenkins techniques[J]. Transportation Research Record, 1979, (722): 1- 9

[3]	SMITH B L, DEMETSKY M J Traffic flow forecasting: comparison of modeling approaches[J]. Journal of Transportation Engineering, 1997, 123 (4): 261- 266 doi: 10.1061/(ASCE)0733-947X(1997)123:4(261)

[4]	TONG J, GU X, ZHANG M, et al. Traffic flow prediction based on improved SVR for VANET [C]// Proceedings of the 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering. Changsha: IEEE, 2021: 402–405.

[5]	CHENG S, LU F, PENG P, et al Short-term traffic forecasting: an adaptive ST-KNN model that considers spatial heterogeneity[J]. Computers, Environment and Urban Systems, 2018, 71: 186- 198 doi: 10.1016/j.compenvurbsys.2018.05.009

[6]	ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization [EB/OL]. (2015–02–19)[2024–07–01]. https://arxiv.org/pdf/1409.2329.

[7]	HOCHREITER S, SCHMIDHUBER J Long short-term memory[J]. Neural Computation, 1997, 9 (8): 1735- 1780 doi: 10.1162/neco.1997.9.8.1735

[8]	ZHANG R, SUN F, SONG Z, et al Short-term traffic flow forecasting model based on GA-TCN[J]. Journal of Advanced Transportation, 2021, 2021 (1): 1338607

[9]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [EB/OL]. (2023–08–02)[2024–07–01]. https://arxiv.org/pdf/1706.03762.

[10]	WANG H, PENG J, HUANG F, et al. MICN: multi-scale local and global context modeling for long-term series forecasting [C]// The Eleventh International Conference on Learning Representations. Kigali: [s. n.], 2023: 1–22.

[11]	ZHANG X, HUANG K, LIU C, et al. Urban short-term traffic flow prediction algorithm based on CNN-LSTM model [C]// Proceedings of the 3rd International Conference on Consumer Electronics and Computer Engineering. Guangzhou: IEEE, 2023: 214–217.

[12]	史昕, 曹凤腾, 纪艺, 等基于多尺度时空特征与软注意力机制的交通流预测方法[J]. 计算机工程, 2024, 50 (12): 346- 357 SHI Xin, CAO Fengteng, JI Yi, et al Traffic flow prediction method based on multi-scale spatio-temporal features and soft attention mechanism[J]. Computer Engineering, 2024, 50 (12): 346- 357

[13]	WU H, HU T, LIU Y, et al. TimesNet: temporal 2D-variation modeling for general time series analysis [EB/OL]. (2023–04–12)[2024–07–01]. https://arxiv.org/pdf/2210.02186.

[14]	WANG X, WANG Z, YANG K, et al. MPPN: multi-resolution periodic pattern network for long-term time series forecasting [EB/OL]. (2023–06–12)[2024–07–01]. https://arxiv.org/pdf/2306.06895.

[15]	赵顗, 沈玲宏, 马健霄, 等综合小波分解和BP神经网络的交通小区生成交通短时预测[J]. 重庆交通大学学报: 自然科学版, 2021, 40 (11): 60- 66 ZHAO Yi, SHEN Linghong, MA Jianxiao, et al Traffic short-term prediction generated by wavelet decomposition and BP neural network of traffic zone[J]. Journal of Chongqing Jiaotong University: Natural Science, 2021, 40 (11): 60- 66

[16]	SASAL L, CHAKRABORTY T, HADID A. W-Transformers: a wavelet-based transformer framework for univariate time series forecasting [C]// Proceedings of the 21st IEEE International Conference on Machine Learning and Applications. Nassau: IEEE, 2022: 671–676.

[17]	博格斯, 马科维奇. 小波与傅里叶分析基础[M]. 2版. 芮国胜, 康健, 译. 北京: 电子工业出版社, 2010: 173–194.

[18]	LIU Y, ZHENG H, FENG X, et al. Short-term traffic flow prediction with Conv-LSTM [C]// Proceedings of the 9th International Conference on Wireless Communications and Signal Processing. Nanjing: IEEE, 2017: 1–6.

[19]	陈峰浩. 基于时空特征分析的多步交通流量预测研究[D]. 杭州: 浙江科技大学, 2024: 1–59. CHEN Fenghao. Research on multi-step traffic flow prediction based on spatio-temporal feature analysis [D]. Hangzhou: Zhejiang University of Science and Technology, 2024: 1–59.

[20]	COOLEY J W, TUKEY J W An algorithm for the machine calculation of complex Fourier series[J]. Mathematics of Computation, 1965, 19 (90): 297- 301 doi: 10.1090/S0025-5718-1965-0178586-1

[21]	FANG Y, QIN Y, LUO H, et al. When spatio-temporal meet wavelets: disentangled traffic forecasting via efficient spectral graph attention networks [C]// Proceedings of the IEEE 39th International Conference on Data Engineering. Anaheim: IEEE, 2023: 517–529.

[22]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770–778.

[23]	闫旭, 范晓亮, 郑传潘, 等基于图卷积神经网络的城市交通态势预测算法[J]. 浙江大学学报: 工学版, 2020, 54 (6): 1147- 1155 YAN Xu, FAN Xiaoliang, ZHENG Chuanpan, et al Urban traffic flow prediction algorithm based on graph convolutional neural networks[J]. Journal of Zhejiang University: Engineering Science, 2020, 54 (6): 1147- 1155

[24]	SUN Y, ZHANG G, YIN H Passenger flow prediction of subway transfer stations based on nonparametric regression model[J]. Discrete Dynamics in Nature and Society, 2014, 2014 (1): 397154

[25]	LIVIERIS I E, PINTELAS E, PINTELAS P A CNN–LSTM model for gold price time-series forecasting[J]. Neural Computing and Applications, 2020, 32 (23): 17351- 17360 doi: 10.1007/s00521-020-04867-x

[26]	BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling [EB/OL]. (2018–04–19)[2024–07–01]. https://arxiv.org/pdf/1803.01271.

[27]	GUO S, LIN Y, FENG N, et al Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33 (1): 922- 929 doi: 10.1609/aaai.v33i01.3301922

[28]	LIU M, ZENG A, CHEN M, et al. SCINet: time series modeling and forecasting with sample convolution and interaction [C]// 36th Conference on Neural Information Processing Systems. New Orleans: [s. n.], 2022, 1–13.

[1]	Xinjian XIANG,Tianshun YUAN,Yaqiang HE,Chengli WANG. Traffic flow prediction based on time series decomposition and soft thresholding temporal convolution[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(7): 1353-1361.

[2]	Qincheng JIANG,Jianfeng TAO,Yangyang WANG,Yulei ZHANG,Chengliang LIU. EWT-LSTM based industrial robot joint anomaly detection[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(5): 982-994.

[3]	Li MA,Yongshun WANG,Yao HU,Lei FAN. Pre-trained long-short spatiotemporal interleaved Transformer for traffic flow prediction applications[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(4): 669-678.

[4]	Jinye LI,Yongqiang LI. Spatial-temporal multi-graph convolution for traffic flow prediction by integrating knowledge graphs[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1366-1376.

[5]	Bingyang ZHU,Jianfeng WU,Ke WANG,Zhangquan WANG,Banteng LIU. Sleep staging based on single-channel ECG signal and INFO-ABCLogitBoost model[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(12): 2547-2555.

[6]	Dian-hai WANG,Rui XIE,Zheng-yi CAI. Prediction of urban interrupted traffic flow based on optimal convergence time interval[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(8): 1607-1617.

[7]	Ling-wei ZHANG,Zheng-dong ZHOU,Yun-fei XU,Jia-wen WANG,Wen-tao JI,Ze-feng SONG. Classification of imagined speech EEG signals based on feature fusion[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(4): 726-734.

[8]	Hong-da CHENG,Hai-ming LUO,Qing-chao XIA,Can-jun YANG. Recognition of images for underwater vehicle based on improved γ-CLAHE algorithm[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(8): 1648-1655.

[9]	Zhu-peng WEN,Jie CHEN,Lian-hua LIU,Ling-ling JIAO. Fault diagnosis of wind power gearbox based on wavelet transform and improved CNN[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(6): 1212-1219.

[10]	Pei-zhi WEN,Jun-mou CHEN,Yan-nan XIAO,Ya-yuan WEN,Wen-ming HUANG. Underwater image enhancement algorithm based on GAN and multi-level wavelet CNN[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(2): 213-224.

[11]	Hao-yuan WANG,Yu LIANG,Wei ZHANG. Real-time smoke segmentation algorithm fused with multi-resolution representation[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(12): 2334-2341.

[12]	Jing HUANG,Shu-yuan ZHONG,Yuan-qiao WEN,Kun LUO. Adaptive graph generation jump network for traffic flow prediction[J]. Journal of ZheJiang University (Engineering Science), 2021, 55(10): 1825-1833.

[13]	Yun FEI,Tao MENG,Zhong-he JIN. Hierarchical fault detection for nano-pico satellite attitude control system[J]. Journal of ZheJiang University (Engineering Science), 2020, 54(4): 824-832.

[14]	ZHANG Cheng-zhi, FENG Hua-jun, XU Zhi-hai, LI Qi, CHEN Yue-ting. Piecewise noise variance estimation of images based on wavelet transform[J]. Journal of ZheJiang University (Engineering Science), 2018, 52(9): 1804-1810.

[15]	CHEN Xue-jun, YANG Yong-ming. De-noising for vibration signals of wind power generator using empirical wavelet transform[J]. Journal of ZheJiang University (Engineering Science), 2018, 52(5): 988-995.

Viewed

Full text

Abstract

Cited

Shared

Discussed