|Table of Contents|

[1] Li Shubin, Kong Xiangke, Li Qingtong, et al. Short-term traffic flow prediction with PSR-XGBoostconsidering chaotic characteristics [J]. Journal of Southeast University (English Edition), 2022, 38 (1): 92-96. [doi:10.3969/j.issn.1003-7985.2022.01.014]
Copy

Short-term traffic flow prediction with PSR-XGBoostconsidering chaotic characteristics()
考虑混沌特性的PSR-XGBoost短期交通流预测
Share:

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
38
Issue:
2022 1
Page:
92-96
Research Field:
Traffic and Transportation Engineering
Publishing date:
2022-03-20

Info

Title:
Short-term traffic flow prediction with PSR-XGBoostconsidering chaotic characteristics
考虑混沌特性的PSR-XGBoost短期交通流预测
Author(s):
Li Shubin1 2 Kong Xiangke1 Li Qingtong1 Lin Zhaofeng1 Zhao Zihao3
1School of Traffic Engineering, Shandong Jianzhu University, Jinan 250101, China
2Department of Traffic Management Engineering, Shandong Police College, Jinan 250014, China
3Beijing Urban Construction Design and De
李树彬1 2 孔祥科1 李青桐1 林兆丰1 赵子豪3
1山东建筑大学交通工程学院, 济南 250101; 2山东警察学院交通管理工程系, 济南 250014; 3北京城建设计发展集团股份有限公司, 北京 100017
Keywords:
traffic prediction phase space reconstruct complex networks model optimization
交通流预测 相空间重构 复杂网络 模型优化
PACS:
U491.1
DOI:
10.3969/j.issn.1003-7985.2022.01.014
Abstract:
To improve the level of active traffic management, a short-term traffic flow prediction model is proposed by combining phase space reconstruction(PSR)and extreme gradient boosting(XGBoost)algorithms. Firstly, the traditional data preprocessing method is improved. The new method uses hierarchical clustering to determine the traffic flow state and fills in missing and abnormal data according to different traffic flow states. Secondly, one-dimensional data are mapped into a multidimensional data matrix through PSR, and the time series complex network is used to verify the data reconstruction effect. Finally, the multidimensional data matrix is inputted into the XGBoost model to predict future traffic flow parameters. The experimental results show that the mean square error, average absolute error, and average absolute percentage error of the prediction results of the PSR-XGBoost model are 5.399%, 1.632%, and 6.278%, respectively, and the required running time is 17.35 s. Compared with mathematical-statistical models and other machine learning models, the PSR-XGBoost model has clear advantages in multiple predictive indicators, proving its feasibility and superiority in short-term traffic flow prediction.
为了提升主动式交通管理的水平, 结合相空间重构和XGBoost算法提出了一种短时交通流预测模型.首先, 改进了传统的数据预处理方法, 通过层次聚类判定交通流状态, 并根据不同的交通流状态对缺失、异常数据进行填充.其次, 利用相空间重构将一维数据映射为多维数据矩阵, 并利用时间序列复杂网络验证数据重构效果.最后, 将多维数据矩阵输入到XGBoost模型以预测未来交通流参数.结果表明, PSR-XGBoost模型预测结果的均方误差、平均绝对误差和平均绝对百分数误差分别为5.399%、1.632%和6.278%, 所需运行时间为17.35 s.相比于数理统计模型和其他机器学习模型, PSR-XGBoost模型在多项预测指标上均有明显提高, 从而验证了其在短时交通流预测方面的可行性和优越性.

References:

[1] Han C, Song S, Wang C H. A real-time short-term traffic flow adaptive forecasting method based on ARIMA model[J]. Journal of System Simulation, 2004, 16(7): 1530-1532, 1535. DOI:10.3969/j.issn.1004-731X.2004.07.042. (in Chinese)
[2] Yang G F, Xu R, Qin M, et al. Short-term traffic volume forecasting based on ARMA and Kalman filter[J]. Journal of Zhengzhou University(Engineering Science), 2017, 38(2): 36-40. DOI:10.13705/j.issn.1671-6833.2017.02.009. (in Chinese)
[3] Tian Z D. Chaotic characteristic analysis of network traffic time series at different time scales[J]. Chaos Solitons & Fractals, 2020, 130: 109412. DOI: 10.1016/j.chaos.2019.109412.
[4] Jia X C, Chen X M, Gong J L, et al. Multi-step short-term traffic flow prediction based on chaotic theory [J]. Journal of Transport Information and Safety, 2013, 31(6): 27-32. DOI:10.3963/j.issn.1674-4861.2013.06.006. (in Chinese)
[5] Wu Q. Research and application of short-term traffic flow forcasting based on support vector machine regression[D]. Xi’an: Chang’an University, 2016.(in Chinese)
[6] Zhang L Z, Alharbe N R, Luo G C, et al. A hybrid forecasting framework based on support vector regression with a modified genetic algorithm and a random forest for traffic flow prediction[J]. Tsinghua Science and Technology, 2018, 23(4): 479-492. DOI: 10.26599/TST.2018.9010045.
[7] Ma X L, Tao Z M, Wang Y H, 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. DOI: 10.1016/j.trc.2015.03.014.
[8] Zhao J D, Gao Y, Yang Z Z, et al. Truck traffic speed prediction under nonrecurrent congestion: Based on optimized deep learning algorithms and GPS data[J]. IEEE Access, 2019, 7: 9116-9127. DOI: 10.1109/ACCESS.2018.2890414.
[9] Li Y Y. Research on the short-term traffic flow forecasting method of based on phase space reconstruction and SVR[D]. Beijing: Beijing Jiaotong University, 2018.(in Chinese)
[10] Matilla García M, Morales I, Rodríguez J M, et al. Selection of embedding dimension and delay time in phase space reconstruction via symbolic dynamics[J]. Entropy, 2021, 23(2): 221-221. DOI: 10.3390/e23020221.
[11] Gao Z K, Jin N D. Complex network from time series based on phase space reconstruction[J]. Chaos, 2009, 19(3): 033137. DOI: 10.1063/1.3227736.
[12] Chen T Q, Guestrin C. XGBoost: A scalable tree boosting system[C]// The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, CA, USA, 2016: 785-794. DOI: 10.1145/2939672.2939785.

Memo

Memo:
Biography: Li Shubin(1977—), male, doctor, professor, li_shu_bin@153.com.
Foundation items: The National Natural Science Foundation of China(No.71771019, 71871130, 71971125); the Science and Technology Special Project of Shandong Provincial Public Security Department(No. 37000000015900920210010001, 37000000015900920210012001).
Citation: Li Shubin, Kong Xiangke, Li Qingtong, et al.Short-term traffic flow prediction with PSR-XGBoost considering chaotic characteristics[J].Journal of Southeast University(English Edition), 2022, 38(1):92-96.DOI:10.3969/j.issn.1003-7985.2022.01.014.
Last Update: 2022-03-20