Inatorial forecasting method considering macro and micro characteristics of chaotic traffic flow

doi:10.1088/1674-1056/acd3df

Abstract Traffic flow prediction is an effective strategy to assess traffic conditions and alleviate traffic congestion. Influenced by external non-stationary factors and road network structure, traffic flow sequences have macro spatiotemporal characteristics and micro chaotic characteristics. The key to improving the model prediction accuracy is to fully extract the macro and micro characteristics of traffic flow time sequences. However, traditional prediction model by only considers time features of traffic data, ignoring spatial characteristics and nonlinear characteristics of the data itself, resulting in poor model prediction performance. In view of this, this research proposes an intelligent combination prediction model taking into account the macro and micro features of chaotic traffic data. Firstly, to address the problem of time-consuming and inefficient multivariate phase space reconstruction by iterating nodes one by one, an improved multivariate phase space reconstruction method is proposed by filtering global representative nodes to effectively realize the high-dimensional mapping of chaotic traffic flow. Secondly, to address the problem that the traditional combinatorial model is difficult to adequately learn the macro and micro characteristics of chaotic traffic data, a combination of convolutional neural network (CNN) and convolutional long short-term memory (ConvLSTM) is utilized for capturing nonlinear features of traffic flow more comprehensively. Finally, to overcome the challenge that the combined model performance degrades due to subjective empirical determined network parameters, an improved lightweight particle swarm is proposed for improving prediction accuracy by optimizing model hyperparameters. In this paper, two highway datasets collected by the Caltrans Performance Measurement System (PeMS) are taken as the research objects, and the experimental results from multiple perspectives show that the comprehensive performance of the method proposed in this research is superior to those of the prevalent methods.

Keywords: traffic flow prediction phase space reconstruction particle swarm optimization algorithm deep learning models

Received: 11 January 2023
Revised: 15 April 2023
Accepted manuscript online: 10 May 2023

PACS:	05.60.-k	(Transport processes)
	05.45.-a	(Nonlinear dynamics and chaos)
	07.05.Mh	(Neural networks, fuzzy logic, artificial intelligence)

Fund: Project supported by the National Natural Science Foundation of China (Grant No. 62063014) and the Natural Science Foundation of Gansu Province, China (Grant No. 22JR5RA365).

Corresponding Authors: Yue Hou
E-mail: houyue@mail.lzjtu.cn

Cite this article:

Yue Hou(侯越), Di Zhang(张迪), Da Li(李达), and Ping Yang(杨萍) Inatorial forecasting method considering macro and micro characteristics of chaotic traffic flow 2023 Chin. Phys. B 32 100508

[1] Zhang J P, Wang F Y, Wang K F, Lin W H, Xu X and Chen C 2011 IEEE Trans. Intell. Transp. Syst. 12 1624
[2] Hamilton A, Waterson B, Cherrett T, Robinson A and Snell I 2013 Transp. Plann. Technol. 36 24
[3] Poole A and Kotsialos A 2016 Appl. Soft Comput. 38 134
[4] Deng S J, Jia S Y and Chen J. 2019 Appl. Soft Comput. 78 712
[5] Grassberger P and Procaccia I 1983 Physica D 9 189
[6] Fraser A M and Swinney H L 1986 Phys. Rev. A 33 1134
[7] Kennel M B, Brown R and Abarbanel H D I 1992 Phys. Rev. A 45 3403
[8] Kim H S, Eykholt R and Salas J D 1999 Physica D 127 48
[9] Peng Y N and Xiang W L 2020 Physica A 549 123913
[10] Zhang L Y, Wang G L, Tan G R and Wu Y 2022 Acta Phys. Sin. 71 080502 (in Chinese)
[11] Zhang C T, Ma Q L, Peng H and Jiang Y Y 2011 Acta Phys. Sin. 60 020508 (in Chinese)
[12] Ma Q L, Huang G H and Ullah S 2020 IEEE Access 8 222774
[13] Williams B M and Hoel L A 2003 J. Transp. Eng. 129 664
[14] Hamed M M, Al-Masaeid H R and Bani Said Z M 1995 J. Transp. Eng. 121 249
[15] Castro-Neto M, Jeong Y S, Jeong M K and Han L D 2009 Expert Syst. Appl. 36 6164
[16] Jeong Y S, Byon Y J, Castro-Neto M M and Easa S M 2013 IEEE Trans. Intell. Transp. Syst. 14 1700
[17] Sun S L, Zhang C S and Yu G Q 2006 IEEE Trans. Intell. Transp. Syst. 7 124
[18] Li C J, Xu Y, Yu X H, Ryan C and Huang T W 2017 IEEE Trans. Ind. Inform. 13 2620
[19] Smith B L and Demetsky M J 1997 J. Transp. Eng. 123 261
[20] Hochreiter S and Schmidhuber J 1997 Neural Comput. 9 1735
[21] Zhang D and Kabuka M R 2018 IET Intell. Transp. Syst. 12 578
[22] Dai G W, Ma C X and Xu X C 2019 IEEE Access 7 143025
[23] Yang D, Li S J, Peng Z, Wang P, Wang J H and Yang H M 2019 IEICE Trans. Inf. Syst. E102.D 1526
[24] Zhuang W Q and Cao Y B 2022 Appl. Sci. 12 8714
[25] Zhang W B, Yu Y H, Qi Y, Shu F and Wang Y H 2019 Transportmetrica A: Transp. Sci. 15 1688
[26] Zheng H F, Lin F, Feng X X and Chen Y J 2020 IEEE Trans. Intell. Transp. Syst. 22 6910
[27] Li Y F, Jiang X, Zhu H, He X Z, Peeta S, Zheng T X and Li Y G 2016 Nonlinear Dyn. 85 179
[28] Huang W J, Li Y T and Huang Y 2020 IEEE Access 8 159552
[29] Marini F and Walczak B 2015 Chemometr. Intell. Lab. Syst. 149 153
[30] Sheikhan M and Mohammadi N 2013 Neural Comput. Appl. 23 1185
[31] Mohamad E T, Armaghani D J, Momeni E, Yazdavar A H and Ebrahimi M 2018 Neural Comput. Appl. 30 1635
[32] Hu W B, Yan L P, Liu K Z and Wang H 2016 Neural Process. Lett. 43 155
[33] Yan H, Qi Y, Ye Q L and Yu D J 2022 IEEE Trans. Intell. Transp. Syst. 23 14542
[34] Cai W H, Yang J J, Yu Y D, Song Y Y, Zhou T and Qin J 2020 IEEE Access 8 6505
[35] Wolf A, Swift J B, Swinney H L and Vastano J A 1985 Physica D 16 285
[36] Zhou Y, Wang N and Xiang W 2016 IEEE Access 5 2241

[1]	Angular insensitive nonreciprocal ultrawide band absorption in plasma-embedded photonic crystals designed with improved particle swarm optimization algorithm Yi-Han Wang(王奕涵) and Hai-Feng Zhang(章海锋). Chin. Phys. B, 2023, 32(4): 044207.
[2]	Traffic flow prediction based on BILSTM model and data denoising scheme Zhong-Yu Li(李中昱), Hong-Xia Ge(葛红霞), and Rong-Jun Cheng(程荣军). Chin. Phys. B, 2022, 31(4): 040502.
[3]	Ground-state structure determination and mechanical properties of palladium seminitride Zhang Gang-Tai (张刚台), Bai Ting-Ting (白婷婷), Zhao Ya-Ru (赵亚儒), Lu Cheng (卢成). Chin. Phys. B, 2013, 22(11): 116104.
[4]	Phase space reconstruction of chaotic dynamical system based on wavelet decomposition You Rong-Yi(游荣义)and Huang Xiao-Jing(黄晓菁). Chin. Phys. B, 2011, 20(2): 020505.
[5]	Low dimensional chaos in the AT and GC skew profiles of DNA sequences Zhou Qian(周茜) and Chen Zeng-Qiang(陈增强). Chin. Phys. B, 2010, 19(9): 090508.
[6]	An efficient method of distinguishing chaos from noise Wei Heng-Dong(魏恒东), Li Li-Ping(李立萍), and Guo Jian-Xiu(郭建秀). Chin. Phys. B, 2010, 19(5): 050505.
[7]	Determining the input dimension of a neural network for nonlinear time series prediction Zhang Sheng (张胜), Liu Hong-Xing (刘红星), Gao Dun-Tang (高敦堂), Du Si-Dan (都思丹). Chin. Phys. B, 2003, 12(6): 594-598.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Metrics
Related Articles

Inatorial forecasting method considering macro and micro characteristics of chaotic traffic flow

Cite this article:

Online attention