Journal of Jilin University(Engineering and Technology Edition) ›› 2019, Vol. 49 ›› Issue (6): 1852-1857.doi: 10.13229/j.cnki.jdxbgxb20180540

Previous Articles     Next Articles

Short⁃term traffic flow prediction based on LSSVMoptimized by immune algorithm

Yuan-li GU1(),Yuan ZHANG1,Xiao-ping RUI2(),Wen-qi LU1,Meng LI1,Shuo WANG1   

  1. 1. Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport,Ministry of Transport,Beijing Jiaotong University,Beijing 100044,China
    2. School of Earth Sciences and Engineering, Hohai University, Nanjing 210098, China
  • Received:2018-05-31 Online:2019-11-01 Published:2019-11-08
  • Contact: Xiao-ping RUI E-mail:ylgu@bjtu.edu.cn;ruixpsz@163.com

Abstract:

In order to intelligently solve the problems existing in urban road networks and improve the accuracy of short-term traffic flow prediction, a short-term traffic prediction model is established by using the least square support vector machine (LSSVM). Specifically, the immune algorithm is adopted to optimize the penalty factor and kernel parameters of the LSSVM, thus obtaining the optimal prediction model. The prediction simulation experiment takes the average speed and occupancy rate of vehicles as the input of the model to predict the traffic flow. The experimental results show that the prediction error of the optimized LSSVM model used in the simulation experiment is reduced, and the output result is closer to the real value.

Key words: engineering of communications and transportation system, traffic flow prediction, immune algorithm, least squares support vector machine, parameter optimization

CLC Number: 

  • U491

Fig.1

Optimization of LSSVM model flow chartby immune algorithm"

Fig.2

Traffic flow prediction based on cross validation optimization of LSSVM parameters"

Fig.3

Traffic flow forecasting based on Bayesianoptimization of LSSVM parameters"

Fig.4

Optimization of LSSVM parameters based on immune algorithm for traffic flow prediction"

Table 1

Comparison of prediction error results"

交叉验证LSSVM 贝叶斯验证LSSVM 免疫算法优化LSSVM
MSE 11.400 1 9.411 4 3.454 6
MAE 3.745 6 2.757 4 1.556 4
MAXRE 0.323 5 0.263 4 0.265 6
1 郭海锋, 方良君, 俞立 . 基于模糊卡尔曼滤波的短时交通流量预测方法[J]. 浙江工业大学学报, 2013, 41(2): 218-221.
1 Guo Hai-feng , Fang Liang-jun , Yu Li . A short-term traffic flow prediction model based on fuzzy Kalman filtering[J]. Journal of Zhejiang University of Technology, 2013, 41(2): 218-221.
2 钱伟, 杨慧慧, 孙玉娟 . 相空间重构的卡尔曼滤波交通流预测研究[J]. 计算机工程与应用, 2016, 52(14): 37-41.
2 Qian Wei , Yang Hui-hui , Sun Yu-juan . Kalman filtering traffic flow prediction research based on phase space reconstruction[J]. Computer Engineering and Application, 2016, 52(14): 37-41.
3 Guo J H , Huang W , Williams B M . Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification[J]. Transportation Research Part C, 2014, 43(1): 50-64.
4 林鑫, 王晓晔, 王卓, 等 . 基于蚁群聚类算法的RBF神经网络交通流预测[J]. 河北工业大学学报, 2010, 39(3): 42-45.
4 Lin Xin , Wang Xiao-ye , Wang Zhuo , et al . Traffic flow forecasting based on ant colony clustering algorithm and RBF neural network[J]. Journal of Hebei University of Technology, 2010, 39(3): 42-45.
5 李松, 刘力军, 翟曼 . 改进粒子群算法优化BP神经网络的短时交通流预测[J]. 系统工程理论与实践, 2012, 32(9): 2045-2049.
5 Li Song , Liu Li-jun , Zhai Man . Prediction for short-term traffic flow based on modified PSO optimized BP neural network[J]. Systems Engineering-Theory & Practice, 2012, 32(9): 2045-2049.
6 Wu Y K , Tan H C , Qin L Q , et al . Hybrid deep learning based on traffic flow prediction method and its understanding[J]. Transportation Research Part C: Emerging Technologies, 2018, 90: 166-180.
7 Polson N G , Sokolov V . Deep learning for short-term traffic flow prediction[J]. Transportation Research Part C: Emerging Technologies, 2017, 79: 1-17.
8 成云, 成效刚, 谈苗苗, 等 . 基于ARIMA和小波神经网络组合模型的交通流预测[J]. 计算机技术与发展, 2017, 27(1): 169-172.
8 Cheng Yun , Cheng Xiao-gang , Tan Miao-miao , et al . Traffic low prediction based on hybrid model of ARIMA and WNN[J]. Computer Technology and Development, 2017, 27(1): 169-172.
9 商强,杨兆升,张伟,等 . 基于奇异谱分析和CKF-LSSVM的短时交通流量预测[J]. 吉林大学学报:工学版, 2016, 46(6): 1792-1798.
9 Shang Qiang , Yang Zhao-sheng , Zhang Wei , et al . Short-term traffic flow prediction based on singular spectrum analysis and CKF-LSSVM[J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(6): 1792-1798.
10 徐鹏, 姜凤茹 . 基于蚁群优化支持向量机的短时交通流预测[J]. 计算机应用与软件, 2013, 30(3): 250-254.
10 Xu Peng , Jiang Feng-ru . Short-term traffic flow prediction based on SVM optimized by ACO[J]. Computer Application and Software, 2013, 30(3): 250-254.
11 张婉琳 . 遗传算法优化支持向量机的交通流量预测[J].激光杂志, 2014, 35(12): 116-119.
11 Zhang Wan-lin . Traffic flow prediction based on support vector machine optimized by genetic algorithm[J]. Laser Journal, 2014, 35(12): 116-119.
12 刘钊, 杜威, 闫冬梅, 等 . 基于K邻近算法和支持向量机回归组合的短时交通利用预测[J]. 公路交通科技,2017, 34(5): 122-128,158.
12 Liu Zhao , Du Wei , Yan Dong-mei , et al . Short-term traffic flow forecast based on combination of K nearest neighbor algorithm and support vector regression[J]. Journal of Highway and Transportation Research and Development, 2017, 34(5):122-128,158.
13 张建, 李艳军, 曹愈远, 等 . 免疫支持向量机用于航空发动机磨损故障诊断[J]. 北京航空航天大学学报, 2017, 43(7): 1419-1425.
13 Zhang Jian , Li Yan-jun , Cao Yu-yuan , et al . Immune SVM used in wear fault diagnosis of aircraft engine[J]. Journal of Beijing University of Aeronautics and Astronautics, 2017, 43(7): 1419-1425.
14 刘大有, 谷方明, 王生生 . 基于人工免疫核聚类的支持向量的数据描述方法[J]. 吉林大学学报:工学版, 2011, 41(5): 1369-1373.
14 Liu Da-you , Gu Fang-ming , Wang Sheng-sheng . Support vector data description based on artificial immune kernel clustering[J]. Journal of Jilin University(Engineering and Technology Edition), 2011, 41(5): 1369-1373.
15 胡风新, 郭红瑾, 孙运芳 . 免疫算法理论及应用研究[J]. 计算机与数字工程, 2009, 37(7): 46-49.
15 Hu Feng-xin , Guo Hong-jin , Sun Yun-fang . Research on immune algorithm theory and its application[J]. Computer & Digital Engineering, 2009, 37(7): 46-49.
16 赵亚萍, 张和生, 周卓楠, 等 . 基于最小二乘支持向量机的交通流量预测模型[J]. 北京交通大学学报, 2011, 35(2): 114-117, 136.
16 Zhao Ya-ping , Zhang He-sheng , Zhou Zhuo-nan , et al . Model of traffic volume forecasting based on least squares support vector machine[J]. Journal of Beijing Jiaotong University, 2011, 35(2): 114-117, 136.
17 张静, 刘向东 . 混沌粒子群算法优化最小二乘支持向量机的混凝土强度预测[J]. 吉林大学学报:工学版, 2016, 46(4): 1097-1102.
17 Zhang jing , Liu Xiang-dong . Prediction of concrete strength based on least square support vector machine optimized by chaotic particle swarm optimization[J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(4): 1097-1102.
18 郭新辰 . 最小二乘支持向量机算法及应用[D]. 长春:吉林大学计算机科学与技术学院, 2008.
18 Guo Xin-chen . Study on least square support vector machine algorithms and theirs application[D]. Changchun: College of Computer Science and Technology, Jilin University, 2008.
[1] Yi-ming BIE,Kai JIANG,Ru-ru TANG,Lin-hong WANG,Xin-yu XIONG. Time of interval partition for traffic control at isolated intersection considering impacts of plan transition [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 1844-1851.
[2] Guo-zhu CHENG, Si-he FENG, Tian-jun FENG. Setting condition of on⁃street parking space occupied vehicle lane [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 1858-1864.
[3] Quan LIANG,Jian-cheng WENG,Wei ZHOU,Jian RONG. Stability identification of public transport commute passengers based on association rules [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(5): 1484-1491.
[4] Hai-bo LONG,Jia-qi YANG,Xue-yu ZHAO. Optimizing vehicles allocation of multimodal coordinated freight transport based on transshipment delay risks [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(5): 1492-1499.
[5] Zhao⁃wei QU,Zhao⁃tian PAN,Yong⁃heng CHEN,Peng⁃fei TAO,Di SUN. Car⁃following model with improving safety distance based on optimal velocity model [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1092-1099.
[6] Wen⁃jing WU,Run⁃chao CHEN,Hong⁃fei JIA,Qing⁃yu LUO,Di SUN. Collaborative control method of vehicles in U⁃turn zone under environment of cooperative vehicle infrastructure system [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1100-1106.
[7] Qiao⁃wen BAI,Zhao⁃wei QU,Yong⁃heng CHEN,Shuai XIONG,Chu⁃qing TAO. Modeling on trajectories of through vehicles with an unprotected left⁃turn phase under non⁃strict priority [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 673-679.
[8] Ning⁃bo CAO,Li⁃ying ZHAO,Zhao⁃wei QU,Yong⁃heng CHEN,Qiao⁃wen BAI,Xiao⁃lei DENG. Social force model considering bi⁃direction pedestrian slipstreaming behavior [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 688-694.
[9] Lei CHEN,Jiang⁃feng WANG,Yuan⁃li GU,Xue⁃dong YAN. Multi⁃source traffic data fusion algorithm based onmind evolutionary algorithm optimization [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 705-713.
[10] Qiang TU,Lin CHENG,Fen LIN,Chao SUN. Finding shortest path considering traveler′s risk attitude [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 720-726.
[11] Chao⁃ying YIN,Chun⁃fu SHAO,Xiao⁃quan WANG. Influence of urban built environment on car commuting considering parking availability [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 714-719.
[12] CHEN Yong-heng,LIU Fang-hong,CAO Ning-bo. Analysis of conflict factors between pedestrians and channelized right turn vehicles at signalized intersections [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1669-1676.
[13] LIU Zhao-hui, WANG Chao, LYU Wen-hong, GUAN Xin. Identification of data characteristics of vehicle running status parameters by nonlinear dynamic analysis [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1405-1410.
[14] LIU Xiang-yu, YANG Qing-fang, KUI Hai-lin. Traffic guidance cell division based on random walk algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1380-1386.
[15] KUI Hai-lin, BAO Cui-zhu, LI Hong-xue, LI Ming-da. Idling time prediction method based on least square support vector machine [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(5): 1360-1365.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] Wang Tian-ling, Li Jun, Wu Jun-hua, Wang Zhan-feng. Synergic effects of EGR and VNT on exhaust emissions from turbocharged diesel engine[J]. 吉林大学学报(工学版), 2006, 36(04): 493 -496 .
[2] Gao Yin-han, Xie Jun, Liang Jie, Li Qiang . Auditory filter bank model based on wavelet transform[J]. 吉林大学学报(工学版), 2008, 38(增刊): 177 -0181 .
[3] XU Zhixing , CONG Wenlong , TANG Kehong. Computeraided Selective Assembly Method[J]. 吉林大学学报(工学版), 2005, 35(06): 613 -0616 .
[4] Hu Xing-jun;Zhang Ying-chao;Li Sheng;Lin You-zhi;Wang Jia-xue;Yang Yong-bai . Numerical simulation of vehicle aerodynamic characteristics based on DRSM[J]. 吉林大学学报(工学版), 2008, 38(03): 504 -0507 .
[5] SUN Bao-feng1,TIAN Xiao-chuan1,XIAO Wei2,MA Li-li1 . Simulation modeling with Drum-Buffer-Rope for remanufacturing system [J]. 吉林大学学报(工学版), 2008, 38(04): 852 -857 .
[6] . [J]. 吉林大学学报(工学版), 2005, 35(02): 214 -0218 .
[7] Fu Han-guang. Structure and performance of high boron cast steel liner[J]. 吉林大学学报(工学版), 2006, 36(04): 467 -471 .
[8] Cheng Jingyuan,Song Kezhu,Yang Junfeng. inglecable checking system for timelapse marine seismic data acquisition and recording system[J]. 吉林大学学报(工学版), 2006, 36(02): 237 -0241 .
[9] Li Peng,Cui Hu-tao,Cui Ping-yuan . UPF based autonomous navigation scheme for probe encountering small celestial body[J]. 吉林大学学报(工学版), 2007, 37(03): 691 -0695 .
[10] Wang Yun-chao,Gao Xiu-hua,Yang Xu,Chen De-xin . Effect of hydropneumatic suspension parameters on steering
characteristics of multiaxlesteering vehicle
[J]. 吉林大学学报(工学版), 2007, 37(02): 269 -0274 .