多分辨率趋势周期解耦交互的交通流预测

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

浙江大学学报(工学版)

2025, Vol. 59

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

土木与交通工程

多分辨率趋势周期解耦交互的交通流预测

侯越(

),王甜甜,张鑫,尹杰

兰州交通大学电子与信息工程学院，甘肃兰州 730070

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

全文: PDF(1278 KB) HTML

摘要：

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

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

收稿日期: 2024-07-01 出版日期: 2025-07-25

CLC:

U 491.1

基金资助: 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）.

作者简介: 侯越（1979—），女，教授，博士，从事大数据智能交通研究. orcid.org/0000-0002-8289-329X. E-mail：houyue@mail.lzjtu.cn

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	作者相关文章
	侯越
	王甜甜
	张鑫
	尹杰

引用本文:

侯越,王甜甜,张鑫,尹杰. 多分辨率趋势周期解耦交互的交通流预测[J]. 浙江大学学报(工学版), 2025, 59(7): 1362-1372.

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.

链接本文:

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

图 1 多分辨率趋势周期解耦交互的交通流预测模型整体框架图

图 2 二级离散小波变换

图 3 二维显著周期矩阵构造过程

图 4 多分辨率趋势周期交互模块结构

图 5 PeMSD8数据集某节点单天的交通流数据及突变点

图 6 二维多分辨率卷积块的因果卷积结构

表 1 不同模型在2个数据集中的交通流预测准确度

表 2 不同模型在2个数据集不同时间步长下的交通流预测准确度

图 7 所提模型在2个数据集中的预测值与真实值对比

表 3 所提模型在PeMSD8数据集中的消融实验结果

表 4 在不同时间步下所提模型的消融实验结果

图 8 所提模型2个模块在PeMSD4数据集中的输出特征热力图

图 9 所提模型2个模块在PeMSD8数据集中的输出特征热力图

表 5 所提模型在不同周期尺度的交通流预测准确度

图 10 MTPDI模型在PeMSD4数据集中不同尺度的周期频谱图

表 6 不同显著频率参数的交通流预测准确度

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]	项新建,袁天顺,何亚强,汪成立. 基于时序分解和软阈值时间卷积的交通流预测[J]. 浙江大学学报(工学版), 2025, 59(7): 1353-1361.
[2]	蒋沁诚,陶建峰,王洋洋,张宇磊,刘成良. 基于EWT-LSTM的工业机器人关节异常检测[J]. 浙江大学学报(工学版), 2025, 59(5): 982-994.
[3]	马莉,王永顺,胡瑶,范磊. 预训练长短时空交错Transformer在交通流预测中的应用[J]. 浙江大学学报(工学版), 2025, 59(4): 669-678.
[4]	朱炳洋,吴建锋,王柯,王章权,刘半藤. 基于单通道ECG信号与INFO-ABCLogitBoost模型的睡眠分期[J]. 浙江大学学报(工学版), 2024, 58(12): 2547-2555.
[5]	王殿海,谢瑞,蔡正义. 基于最优汇集时间间隔的城市间断交通流预测[J]. 浙江大学学报(工学版), 2023, 57(8): 1607-1617.
[6]	张灵维,周正东,许云飞,王嘉文,吉文韬,宋泽峰. 基于特征融合的语言想象脑电信号分类[J]. 浙江大学学报(工学版), 2023, 57(4): 726-734.
[7]	成宏达,骆海明,夏庆超,杨灿军. 基于改进γ-CLAHE算法的水下机器人图像识别[J]. 浙江大学学报(工学版), 2022, 56(8): 1648-1655.
[8]	温竹鹏,陈捷,刘连华,焦玲玲. 基于小波变换和优化CNN的风电齿轮箱故障诊断[J]. 浙江大学学报(工学版), 2022, 56(6): 1212-1219.
[9]	温佩芝,陈君谋,肖雁南,温雅媛,黄文明. 基于生成式对抗网络和多级小波包卷积网络的水下图像增强算法[J]. 浙江大学学报(工学版), 2022, 56(2): 213-224.
[10]	王浩远,梁煜,张为. 融合多分辨率表征的实时烟雾分割算法[J]. 浙江大学学报(工学版), 2021, 55(12): 2334-2341.
[11]	闫旭,范晓亮,郑传潘,臧彧,王程,程明,陈龙彪. 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.
[12]	费云,蒙涛,金仲和. 皮纳卫星姿控系统分层式故障检测[J]. 浙江大学学报(工学版), 2020, 54(4): 824-832.
[13]	张承志, 冯华君, 徐之海, 李奇, 陈跃庭. 图像噪声方差分段估计法[J]. 浙江大学学报(工学版), 2018, 52(9): 1804-1810.
[14]	陈学军, 杨永明. 采用经验小波变换的风力发电机振动信号消噪[J]. 浙江大学学报(工学版), 2018, 52(5): 988-995.
[15]	龚越, 罗小芹, 王殿海, 杨少辉. 基于梯度提升回归树的城市道路行程时间预测[J]. 浙江大学学报(工学版), 2018, 52(3): 453-460.

Viewed

Full text

Abstract

Cited

Shared

Discussed