Real-time prediction of traffic status based on clustering multivariate time series model

doi:10.11772/j.issn.1001-9081.2024070956

Journal of Computer Applications ›› 2025, Vol. 45 ›› Issue (7): 2253-2261.DOI: 10.11772/j.issn.1001-9081.2024070956

• Data science and technology • Previous Articles Next Articles

Real-time prediction of traffic status based on clustering multivariate time series model

Shujun GUO(), Weijun REN, Qianqian CHEN, Guangfei YOU

School of Information Engineering，Chang’an University，Xi’an Shaanxi 710064，China

Received:2024-07-09 Revised:2024-10-04 Accepted:2024-10-09 Online:2025-07-10 Published:2025-07-10
Contact: Shujun GUO
About author:GUO Shujun， born in 2000， M. S. candidate. Her research interests include intelligent transportation， traffic status recognition and prediction.
REN Weijun， born in 1973， Ph. D.， associate professor. His research interests include computer vision， data mining， intelligent transportation.
CHEN Qianqian， born in 2000， M. S. candidate. Her research interests include intelligent transportation， highway maintenance strategy.
YOU Guangfei， born in 2000， M. S. candidate. His research interests include intelligent transportation， traffic flow prediction.
Supported by:
Shaanxi Province Key Research and Development Program(2021GY-033);Technical Research Project of Xi’an Highway Research Institute(220224230915)

基于聚类多变量时间序列模型的交通状态实时预测

郭书君(), 任卫军, 陈倩倩, 游广飞

长安大学信息工程学院，西安 710064

通讯作者: 郭书君
作者简介:郭书君（2000—），女，四川达州人，硕士研究生，CCF会员，主要研究方向：智能交通、交通状态识别与预测 sjguo@chd.edu.cn
任卫军（1973—），男，陕西西安人，副教授，博士，主要研究方向：计算机视觉、数据挖掘、智能交通
陈倩倩（2000—），女，江苏扬州人，硕士研究生，主要研究方向：智能交通、高速公路维护养护策略
游广飞（2000—），男，陕西安康人，硕士研究生，主要研究方向：智能交通、交通流预测。
基金资助:
陕西省重点研发计划项目(2021GY-033);西安公路研究院技术研究项目(220224230915)

Abstract

Abstract:

To address the issues that the existing traffic status prediction models cannot handle the fuzziness of highway traffic status effectively and fail to utilize real-time data streams after model training， a real-time prediction method for traffic status based on clustering multivariate time series model was proposed. Firstly， traffic flow parameters were analyzed， and a classification model based on the improved Fuzzy C-Means （FCM） algorithm and entropy weight method was developed to define traffic status and establish classification standards， and a Status Index （SI） indicator was employed to address the issue of classification boundary fuzziness. Secondly， a multivariate time series prediction model was constructed on the basis of the classification model. By combining convolutional networks and attention mechanisms， this model was able to capture both long-term and short-term dependencies in time series data effectively. Thirdly， a back-propagation update mechanism was applied for online learning to realize real-time prediction. Finally， the model was tested on the California Traffic Management Center Performance Measurement System （PeMS） dataset， the dataset was divided into training， validation， and test sets in time order， and real-time data stream simulations were conducted for online learning and prediction. Experimental results show that with the prediction step of 6， compared to the classic LightTS （Light Sampling-oriented MLP Structures） model， the proposed model reduces the Mean Squared Error （MSE） by 22.81% and the Mean Absolute Error （MAE） by 14.64%. It can be seen that the proposed model distinguishes traffic status levels effectively and achieves real-time traffic status prediction.

Key words: highway, traffic status classification, traffic status prediction, fuzzy clustering, neural network, online learning

摘要：

针对现有的交通状态预测模型不能有效应对高速公路交通状态的模糊性以及模型训练后不能有效使用实时数据流的问题，提出基于聚类的多变量时间序列交通状态实时预测模型。首先，在分析交通流参数后，构建基于改进的模糊C均值（FCM）算法与熵权法的分类模型对交通状态进行模式定义并设定分类标准，并采用状态指数（SI）指标解决分类边界模糊问题；其次，在分类模型的基础上构建多变量时间序列预测模型，该模型结合卷积网络和注意力机制，能有效地捕捉时间序列数据的长短期依赖关系；然后，利用反向传播更新机制进行在线学习，从而实现预测过程的实时化；最后，将模型在加州交通管理中心性能监控系统（PeMS）数据集上进行测试，把数据集按时间顺序分为训练集、验证集和测试集，并模拟实时数据流进行在线学习和预测。实验结果表明，预测步长为6时，与经典的LightTS（Light Sampling-oriented MLP Structures）模型相比，所提模型的均方误差（MSE）和平均绝对误差（MAE）分别降低了22.81%和14.64%。可见，所提模型能够有效区分交通状态等级，并实现交通状态的实时预测。

关键词: 高速公路, 交通状态分类, 交通状态预测, 模糊聚类, 神经网络, 在线学习

CLC Number:

TP391

Shujun GUO, Weijun REN, Qianqian CHEN, Guangfei YOU. Real-time prediction of traffic status based on clustering multivariate time series model[J]. Journal of Computer Applications, 2025, 45(7): 2253-2261.

郭书君, 任卫军, 陈倩倩, 游广飞. 基于聚类多变量时间序列模型的交通状态实时预测[J]. 《计算机应用》唯一官方网站, 2025, 45(7): 2253-2261.

Figures/Tables 11

References 37

[1]	陈钊正，吴聪.多变量聚类分析的高速公路交通流状态实时评估［J］.交通运输系统工程与信息，2018， 18（3）： 225-233.
	CHEN Z Z， WU C. A method of traffic state estimation for expressway based on multivariate clustering analysis ［J］. Journal of Transportation Systems Engineering and Information Technology， 2018， 18（3）： 225-233.
[2]	YUAN Y， ZHANG W， YANG X， et al. Traffic state classification and prediction based on trajectory data ［J］. Journal of Intelligent Transportation Systems， 2021（Latest Articles）： 1-15.
[3]	ZHANG L， JIA Y， SUN D， et al. A fuzzy weighted c-means classification method for traffic flow state division ［J］. Modern Physics Letters B， 2021， 35（20）： No.2150341.
[4]	TIŠLJARIĆ L， RIBIĆ F， MAJSTOROVIĆ Ž， et al. Speed transition matrix feature extraction for traffic state estimation using machine learning algorithms ［M］// PETROVIĆ M， NOVAČKO L， BOŽIĆ D， et al. The science and development of transport — ZIRP 2021. Cham： Springer， 2022： 61-74.
[5]	REZA S， FERREIRA M C， MACHADO J J M， et al. Traffic state prediction using one-dimensional convolution neural networks and long short-term memory ［J］. Applied Sciences， 2022， 12（10）： No.5149.
[6]	KHAJEH HOSSEINI M， TALEBPOUR A. Probabilistic traffic state prediction based on vehicle trajectory data ［J］. Data Science for Transportation， 2023， 5： No.22.
[7]	USAMA M， MA R， HART J， et al. Physics-Informed Neural Networks （PINNs）-based traffic state estimation： an application to traffic network ［J］. Algorithms， 2022， 15（12）： No.447.
[8]	GUPTA A， MAURYA M K， GOYAL N， et al. ISTGCN： integrated spatio-temporal modeling for traffic prediction using traffic graph convolution network ［J］. Applied Intelligence， 2023， 53（23）： 29153-29168.
[9]	陈德望.基于模糊聚类的快速路交通流状况分类［J］.交通运输系统工程与信息，2005， 5（1）： 62-67.
	CHEN D W. Classification of traffic flow situation of urban freeways based on fuzzy clustering ［J］. Journal of Transportation Systems Engineering and Information Technology， 2005， 5（1）： 62-67.
[10]	REILLY W. Highway capacity manual 2000 ［J］. TR News， 1997， 193： 22-23.
[11]	李相勇，蒋葛夫.城市道路服务水平的模糊综合评判［J］.交通运输系统工程与信息，2002， 2（3）： 48-50.
	LI X Y， JIANG G F. Fuzzy comprehensive assessment of service level for urban roads ［J］. Journal of Transportation Systems Engineering and Information Technology， 2002， 2（3）： 48-50.
[12]	MAITRA B， SIKDAR P K， DHINGRA S L. Modeling congestion on urban roads and assessing level of service ［J］. Journal of Transportation Engineering， 1999， 125（6）： 508-514.
[13]	National Academies of Sciences， Engineering， and Medicine. Highway capacity manual： a guide for multimodal mobility analysis ［M］. ‎7th ed. Washington： National Academies Press， 2022.
[14]	BAEK J. Highway regional classification method based on traffic flow characteristics for highway safety assessment ［J］. Sensors， 2022， 22（1）： No.86.
[15]	周涛，陆惠玲.数据挖掘中聚类算法研究进展［J］.计算机工程与应用，2012， 48（12）： 100-111.
	ZHOU T， LU H L. Clustering algorithm research advances on data mining ［J］. Computer Engineering and Applications， 2012， 48（12）： 100-111.
[16]	KRASNOV D， DAVIS D， MALOTT K， et al. Fuzzy c-means clustering： a review of applications in breast cancer detection ［J］. Entropy， 2023， 25（7）： No.1021.
[17]	DING W， CHANG S， BAO S， et al. Accurate RSS-based localization using an opposition-based learning simulated annealing algorithm ［EB/OL］. ［2024-05-19］. .
[18]	ALAM T， QAMAR S， DIXIT A， et al. Genetic algorithm： reviews， implementations， and applications ［EB/OL］. ［2024-05-22］. .
[19]	WU J， TSANG E C C. A new three-way multi-attribute decision making based on regret theory and TOPSIS model ［C］// Proceedings of the 2022 International Conference on Wavelet Analysis and Pattern Recognition. Piscataway： IEEE， 2022： 66-71.
[20]	杜崇.高速公路实时交通状态判别方法研究［D］.北京：北京交通大学，2017.
	DU C. Research on real-time highway traffic states identification ［D］. Beijing： Beijing Jiaotong University， 2017.
[21]	周如心.高速公路交通流状态辨识与拥堵预测方法研究［D］.南京：南京理工大学，2021.
	ZHOU R X. Research on the method of highway traffic flow identification and congestion forecast ［D］. Nanjing： Nanjing University of Science and Technology， 2021.
[22]	YANG Z， HAO L， LIU Y， et al. Identification of expressway traffic states based on the enhanced FCM algorithm ［C］// Proceedings of the 2022 International Conference on 3D Imaging Technology — 3D Imaging — Multidimensional Signal Processing and Deep Learning： Images， Augmented Reality and Information Technologies， Volume 1， SIST 349. Singapore： Springer， 2023： 167-179.
[23]	BHAGAT-CONWAY M W， ZHANG S. Rush hour-and-a-half： traffic is spreading out post-lockdown ［J］. PLoS ONE， 2023， 18（9）： No.e0290534.
[24]	KÁROLY A I， FULLÉR R， GALAMBOS P. Unsupervised clustering for deep learning： a tutorial survey ［J］. Acta Polytechnica Hungarica， 2018， 15（8）： 29-53.
[25]	ZHOU H， ZHANG S， PENG J， et al. Informer： beyond efficient transformer for long sequence time-series forecasting ［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2021： 11106-11115.
[26]	BELLO I， ZOPH B， LE Q， et al. Attention augmented convolutional networks ［C］// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE， 2019： 3285-3294.
[27]	CHEE K J， RAMLI D A. Electrocardiogram biometrics using Transformer’s self-attention mechanism for sequence pair feature extractor and flexible enrollment scope identification ［J］. Sensors， 2022， 22（9）： No.3446.
[28]	OH B D， KIM Y S. Lightweight text classifier using sinusoidal positional encoding ［C］// Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing. Stroudsburg： ACL， 2020： 63-69.
[29]	HAZAN E. Introduction to online convex optimization ［J］. Foundations and Trends in Optimization， 2016， 2（3/4）： 157-325.
[30]	KUMAR A， SHEN R， BUBECK S， et al. How to fine-tune vision models with SGD ［EB/OL］. ［2024-05-28］. .
[31]	RUDER S. An overview of gradient descent optimization algorithms［EB/OL］.［2024-05-30］..
[32]	HU J， YIN H， WEI G， et al. An improved FCM clustering algorithm with adaptive weights based on PSO-TVAC algorithm ［J］. Applied Intelligence， 2022， 52（8）： 9521-9536.
[33]	BEZDEK J C. Pattern recognition with fuzzy objective function algorithms， AAPR ［M］. New York： Springer， 1981.
[34]	PHAM Q， LIU C， SAHOO D， et al. Learning fast and slow for online time series forecasting ［EB/OL］. ［2024-06-10］. .
[35]	ZHANG T， ZHANG Y， CAO W， al e t. Less is more： fast multivariate time series forecasting with light sampling-oriented MLP structures ［EB/OL］. ［2024-06-13］. .
[36]	CAO D， WANG Y， DUAN J， et al. Spectral temporal graph neural network for multivariate time-series forecasting ［C］// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2020： 17766-17778.
[37]	LIU M， ZENG A， CHEN M， et al. SCINet： time series modeling and forecasting with sample convolution and interaction ［C］// Proceedings of the 36th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2022： 5816-5828.

聚类算法	轮廓系数	Davies-Bouldin指数	Calinski-Harabasz指数	目标函数
FCM	0.374 180 211	0.941 851 020	2 954.486 441	13.152 365 85
KMeans++-FCM	0.376 032 070	1.042 522 776	2 214.476 676	17.014 337 58
PSO-FCM^［32］	0.411321468	0.910256384	3060.856471	13.134 278 60
DE-FCM	0.374 475 615	0.938 586 652	2 957.567 658	13.152 172 09
AC-FCM	0.374 475 615	0.938 586 652	2 957.567 658	13.152 172 09
ABC-FCM	0.408 400 850	0.919 409 954	3 044.087 693	13.124 493 50
SG-FCM	0.413 689 585	0.895 056 244	3 075.347 074	13.13401237

聚类算法	轮廓系数	Davies-Bouldin指数	Calinski-Harabasz指数	目标函数
FCM	0.374 180 211	0.941 851 020	2 954.486 441	13.152 365 85
KMeans++-FCM	0.376 032 070	1.042 522 776	2 214.476 676	17.014 337 58
PSO-FCM^［32］	0.411321468	0.910256384	3060.856471	13.134 278 60
DE-FCM	0.374 475 615	0.938 586 652	2 957.567 658	13.152 172 09
AC-FCM	0.374 475 615	0.938 586 652	2 957.567 658	13.152 172 09
ABC-FCM	0.408 400 850	0.919 409 954	3 044.087 693	13.124 493 50
SG-FCM	0.413 689 585	0.895 056 244	3 075.347 074	13.13401237

类别颜色	状态信息	图中标注的聚类中心	样本数	样本比例/%	聚类中心坐标
橙色	严重拥堵（5）	Status 5	605	30.01	（37.375 83， 448.692 11， 31.443 06）
紫色	中度拥堵（4）	Status 4	561	27.83	（56.719 58， 527.789 45， 25.505 64）
绿色	轻度拥堵（3）	Status 3	435	21.58	（60.642 46， 283.190 45， 23.226 44）
蓝色	稳定流动（2）	Status 2	253	12.55	（78.685 77， 286.191 50， 13.941 19）
红色	自由流畅（1）	Status 1	162	8.04	（83.211 55， 206.096 52， 9.553 94）

类别颜色	状态信息	图中标注的聚类中心	样本数	样本比例/%	聚类中心坐标
橙色	严重拥堵（5）	Status 5	605	30.01	（37.375 83， 448.692 11， 31.443 06）
紫色	中度拥堵（4）	Status 4	561	27.83	（56.719 58， 527.789 45， 25.505 64）
绿色	轻度拥堵（3）	Status 3	435	21.58	（60.642 46， 283.190 45， 23.226 44）
蓝色	稳定流动（2）	Status 2	253	12.55	（78.685 77， 286.191 50， 13.941 19）
红色	自由流畅（1）	Status 1	162	8.04	（83.211 55， 206.096 52， 9.553 94）

时间	速度/（km·h^-1）	流量/（veh·5 min^-1）	占有率/%	状态值	SI值
2023-12-08T00：00	78.85	232	12.99	2	1.90
2023-12-08T03：05	82.97	169	7.77	1	1.19
2023-12-08T06：25	83.75	291	10.74	2	1.84
2023-12-08T08：35	39.28	549	34.89	5	5.39
2023-12-08T12：35	52.48	459	28.99	4	4.82
2023-12-08T17：40	55.51	439	22.47	4	4.22
2023-12-08T23：15	72.72	335	17.99	2	2.64

Real-time prediction of traffic status based on clustering multivariate time series model

基于聚类多变量时间序列模型的交通状态实时预测

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 37

Related Articles 15

Recommended Articles

Metrics

预测步长	FSNet^［34］		LightTS^［35］		Informer^［25］		StemGNN^［36］		SCINet^［37］		MTS-EnhanceNet
预测步长	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE
6	0.826 8	0.752 8	0.3955	0.4482	0.496 9	0.479 9	0.432 1	0.451 8	0.487 9	0.510 6	0.305 3	0.382 6
12	1.111 2	0.909 7	0.3840	0.4428	0.439 9	0.446 9	0.446 6	0.454 9	0.545 5	0.536 5	0.270 2	0.388 9

数据类型	时间	速度/（km·h^-1）	流量/（veh·5 min^-1）	占有率/%	SI值
回溯窗口（window=288）	2023-12-05T14：55	51.42	565	30.53	4.69
	2023-12-05T15：00	61.13	368	24.13	3.84
	2023-12-05T15：05	55.86	479	31.00	3.96
	
	2023-12-06T14：50	67.69	315	23.07	3.29
预测窗口（H=12）	2023-12-06T14：55	61.35	352	22.50	3.82
	2023-12-06T15：00	55.62	388	19.82	3.10
	
	2023-12-06T15：50：00	31.83	481	38.04	5.61

时间	数据类型	速度/（km·h^-1）	流量/（veh·5 min^-1）	占有率/%	SI值
2023-12-06T15：00：00	真实数据	48.41	338	25.28	3.82
	在线学习前	55.62	388	19.82	3.10
	在线学习后	54.48	331	21.26	3.31
2023-12-06T15：05：00	真实数据	53.43	462	24.46	4.89
	在线学习前	43.46	587	29.05	5.51
	在线学习后	49.39	501	26.40	5.18
2023-12-06T15：10：00	真实数据	57.64	479	29.01	4.63
	在线学习前	65.75	465	30.53	4.45
	在线学习后	62.07	467	30.03	4.52

2023-12-06T15：50：00	真实数据	35.17	477	32.22	5.49
	在线学习前	31.83	481	38.04	5.61
	在线学习后	41.07	471	33.62	5.19

[1]	Zhangjie XU, Yanping CHEN, Ying HU, Ruizhang HUANG, Yongbin QIN. Nested named entity recognition combined with boundary generation by multi-objective learning [J]. Journal of Computer Applications, 2025, 45(7): 2229-2236.
[2]	Danyang CHEN, Changlun ZHANG. Multi-scale decorrelation graph convolutional network model [J]. Journal of Computer Applications, 2025, 45(7): 2180-2187.
[3]	Yuelan ZHANG, Jing SU, Hangyu ZHAO, Baili YANG. Multi-view knowledge-aware and interactive distillation recommendation algorithm [J]. Journal of Computer Applications, 2025, 45(7): 2211-2220.
[4]	Yingjun ZHANG, Weiwei YAN, Binhong XIE, Rui ZHANG, Wangdong LU. Gradient-discriminative and feature norm-driven open-world object detection [J]. Journal of Computer Applications, 2025, 45(7): 2203-2210.
[5]	Qiaoling QI, Xiaoxiao WANG, Qianqian ZHANG, Peng WANG, Yongfeng DONG. Label noise adaptive learning algorithm based on meta-learning [J]. Journal of Computer Applications, 2025, 45(7): 2113-2122.
[6]	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.
[7]	Yongpeng TAO, Shiqi BAI, Zhengwen ZHOU. Neural architecture search for multi-tissue segmentation using convolutional and transformer-based networks in glioma segmentation [J]. Journal of Computer Applications, 2025, 45(7): 2378-2386.
[8]	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.
[9]	Zimo ZHANG, Xuezhuan ZHAO. Multi-scale sparse graph guided vision graph neural networks [J]. Journal of Computer Applications, 2025, 45(7): 2188-2194.
[10]	Erkang XIANG, Rong HUANG, Aihua DONG. Open set recognition method with open generation and feature optimization [J]. Journal of Computer Applications, 2025, 45(7): 2195-2202.
[11]	Zonghang WU, Dong ZHANG, Guanyu LI. Multimodal fusion recommendation algorithm based on joint self-supervised learning [J]. Journal of Computer Applications, 2025, 45(6): 1858-1868.
[12]	Tianchen HUA, Xiaoning MA, Hui ZHI. Portable executable malware static detection model based on shallow artificial neural network [J]. Journal of Computer Applications, 2025, 45(6): 1911-1921.
[13]	Chaoying JIANG, Qian LI, Ning LIU, Lei LIU, Lizhen CUI. Readmission prediction model based on graph contrastive learning [J]. Journal of Computer Applications, 2025, 45(6): 1784-1792.
[14]	Lu CHEN, Huaiyao WANG, Jingyang LIU, Tao YAN, Bin CHEN. Robotic grasp detection with feature fusion of spatial-Fourier domain information under low-light environments [J]. Journal of Computer Applications, 2025, 45(5): 1686-1693.
[15]	Dan WANG, Wenhao ZHANG, Lijuan PENG. Channel estimation of reconfigurable intelligent surface assisted communication system based on deep learning [J]. Journal of Computer Applications, 2025, 45(5): 1613-1618.