Application of RQEA-SVR in traffic flow forecasting

doi:10.3778/j.issn.1002-8331.2010.09.069

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (9): 241-245.DOI: 10.3778/j.issn.1002-8331.2010.09.069

• 工程与应用 • Previous Articles Next Articles

Application of RQEA-SVR in traffic flow forecasting

ZHANG Rui^1，2，ZHANG Tao³，GAO Hui⁴

1.School of Electrical Engineering & Automation，Harbin Institute of Technology，Harbin 150010，China
2.School of Automation，Harbin University of Science and Technology，Harbin 150080，China
3.School of Electrical & Electronic Engineering，Harbin University of Science and Technology，Harbin 150080，China
4.School of Traffic and Transportation，Southwest Jiaotong University，Chengdu 610031，China

Received:2009-04-24 Revised:2009-06-17 Online:2010-03-21 Published:2010-03-21
Contact: ZHANG Rui

RQEA-SVR在交通流预测中的应用

张锐^1，2，张涛³，高辉⁴

1.哈尔滨工业大学电气工程及自动化学院，哈尔滨 150010
2.哈尔滨理工大学自动化学院，哈尔滨 150080
3.哈尔滨理工大学电气与电子工程学院，哈尔滨 150080
4.西南交通大学交通运输学院，成都 610031

通讯作者: 张锐

Abstract

Abstract: Support Vector Regression（SVR） based on statistical learning theory and structural risk minimization principle is a powerful tool for solving small-sample regression problem，and selecting appropriate parameters is very crucial to learn accuracy and generalization performance of SVR.Firstly，the parameters selection of SVR is considered as a combinatorial optimization problem，and the objective function of optimization problem is set.Then，Real-coded Quantum Evolutionary Algorithm（RQEA） is employed to solve this problem furthermore to select appropriate parameters of SVR，which is called RQEA-SVR，and RQEA-SVR is applied to the problem of traffic flow forecasting.The experiment results show that the proposed method is an effective approach for parameters selection of SVR，and the good performance for traffic flow forecasting is obtained.

Key words: Support Vector Regression（SVR）, parameters selection, real-coded quantum evolutionary algorithm, traffic flow forecasting

摘要： 建立在统计学习理论和结构风险最小化准则基础上的支持向量回归（SVR）是处理小样本数据回归问题的有利工具，SVR的参数选取直接影响其学习性能和泛化能力。文中将SVR参数选取看作是参数的组合优化问题，确定组合优化问题的目标函数，采用实数量子进化算法（RQEA）求解组合优化问题进而优选SVR参数，形成RQEA-SVR，并应用RQEA-SVR求解交通流预测问题。仿真试验表明RQEA是优选SVR参数的有效方法，解决交通流预测问题具有优良的性能。

关键词: 支持向量机, 参数优选, 实数量子进化算法, 交通流预测

CLC Number:

TP18

ZHANG Rui^1，2，ZHANG Tao³，GAO Hui⁴. Application of RQEA-SVR in traffic flow forecasting[J]. Computer Engineering and Applications, 2010, 46(9): 241-245.

张锐^1，2，张涛³，高辉⁴. RQEA-SVR在交通流预测中的应用[J]. 计算机工程与应用, 2010, 46(9): 241-245.

[1]	ZHANG Lin, WANG Tinghua, ZHOU Huiying. Research Progress on Parameter Optimization of SVR Based on Swarm Intelligence Algorithm [J]. Computer Engineering and Applications, 2021, 57(16): 50-64.
[2]	DENG Xuankun1，2, WAN Liang1，2, DING Hongwei1，2, XIN Zhuang1，2. Traffic Flow Prediction Based on Deep Neural Networks [J]. Computer Engineering and Applications, 2019, 55(2): 228-235.
[3]	LUO Xianglong1，2, ZHANG Shengrui1, NIU Liyao2. Short-term traffic flow prediction based on detector optimal selection [J]. Computer Engineering and Applications, 2017, 53(8): 199-202.
[4]	DING Hongfei1，2, QIN Zheng1, LIU Bo1, LI Yanhong1. Study on urban expressways’ multi-source traffic data fusion technology based on AF-SVR model [J]. Computer Engineering and Applications, 2017, 53(5): 266-270.
[5]	CHU Pengyu, LIU Lan, YIN Junsong, LU Weike. Short-term traffic flow forecasting by fusing spatial-temporal traffic information [J]. Computer Engineering and Applications, 2016, 52(12): 246-250.
[6]	HUANG Liang, WU Shuai, TAN Guolv, ZHENG Jun. Network intrusion detection based on relevance vector machine optimized by particle swarm algorithm with elite election strategy [J]. Computer Engineering and Applications, 2015, 51(3): 85-88.
[7]	WANG Daxi1, HU Zhiyuan1, QIAN Liujian2. Product sales forecasting based on Chaos Fruit Fly Support Vector Regression [J]. Computer Engineering and Applications, 2015, 51(12): 235-240.
[8]	WANG Xin1, WANG Qian1, ZHAO Zhike2. Improved method for endpoint extension of empirical mode decomposition based on SVR [J]. Computer Engineering and Applications, 2014, 50(9): 204-208.
[9]	LAN Jiao1, QIN Xizhong1, JIA Zhenhong1, CHEN Li2. Busy traffic forecasting based on improved semi supervised SVR algorithm [J]. Computer Engineering and Applications, 2014, 50(20): 211-214.
[10]	HUANG Min1, HU Xuegang2. Internet public opinion chaotic prediction based on Support Vector Regression machine [J]. Computer Engineering and Applications, 2013, 49(24): 130-134.
[11]	CUI Jing1,2, LIU Benyong1,2. Single-frame image superresolution using grouping SVR and KNR [J]. Computer Engineering and Applications, 2012, 48(23): 185-190.
[12]	CHEN Tao，YONG Longquan，DENG Fang’an，YANG Xiao. Parameters selection of support vector machine based on differential evolution [J]. Computer Engineering and Applications, 2011, 47(5): 24-26.
[13]	WU Kang，HAN Bo，LI Ping. Fault detection and isolation for sensors on SUH based on SVR and wavelet transform [J]. Computer Engineering and Applications, 2011, 47(20): 221-224.
[14]	HE Tong-di^1，2，LI Jian-wei¹，HUANG Hong¹. Water quality evaluation based on Support Vector Regression with parameters optimized by particle swarm optimization algorithm [J]. Computer Engineering and Applications, 2010, 46(24): 11-14.
[15]	HE Ming-hui，LI Sheng，LI Ping，NIE Jing-xu. Parameters selection for SVM using simulated annealing combinatorial algorithms [J]. Computer Engineering and Applications, 2010, 46(22): 37-39.

Application of RQEA-SVR in traffic flow forecasting

RQEA-SVR在交通流预测中的应用

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics