Traffic Accident Forecast Model Based on SVR Optimized by Improved PSO

doi:10.3969/j.issn.1006-2475.2014.05.007

Abstract

Abstract: In order to predict traffic accidents effectively, this article introduced a traffic accident forecast model based on SVR optimized by improved PSO. The improved particle swarm algorithm searches the neighborhoods of the global optimal particle by grid search which combines the faster convergence speed of the particle swarm algorithm with the stronger local search ability of the grid search. The improved particle swarm algorithm improves the optimization precision of SVR parameters and improves the performance of the traffic accident prediction model. The simulation results show that the traffic accident forecast model based on SVR optimized by improved PSO gets faster learning speed and higher prediction precision, it is of good engineering applicability.


Key words: particle swarm optimization, grid search, support vector regression, parameter optimization, traffic accident forecast

CLC Number:

TP301.6

LI Tong, MAO Li, WU Bin. Traffic Accident Forecast Model Based on SVR Optimized by Improved PSO[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2014.05.007.

References ［15］

［1］	孔令铮. 交通事故致因中的人为因素分析［J］. 中国安全科学学报, 2013,23(1):28-34.
［2］	Smruti Rekha Das, Kaberi Das, Debahuti Mishra, et al. An empirical comparison study on kernel based support vector machine for classification of gene expression data set［J］. Procedia Engineering, 2012,38:1340-1345.
［3］	Bai Liming, Lin Hui, Sun Hua, et al. Remotely sensed percent tree cover mapping using support vector machine combined with autonomous endmember extraction［J］. Physics Procedia, 2012,33:1702-1709.
［4］	顾亚祥,丁世飞. 支持向量机研究进展［J］. 计算机科学, 2011,38(2):14-17.
［5］	刘道文,忽海娜. 基于网格搜索支持向量机的网络流量预测［J］. 计算机应用与软件, 2012,29(11):185-186,247.
［6］	Shrime A E, Yousefi M. Recognition of the communication signals using particle swarm optimization and support vector machine based on the multi-resolution wavelet analysis［J］. Wireless Personal Communications, 2012,63(4):847-860.
［7］	Li D S, He Q. A version of cooperative multi-swarm PSO using electoral mechanism to solve hybrid flow shop scheduling problem［J］. Przegland Elektrotechniczny, 2012,88(5b):22-26.
［8］	〖JP2〗Wang Jianlin, Feng Xuying, Yu Tao. A geometric approach to support vector regression and its application to fermentation process fast modeling［J］. Chinese Journal of Chemical Engineering, 2012,20(4):715-722.
［9］	司利云,林辉. 支持向量回归机模型结构及性能的研究［J］. 计算机工程与应用, 2008,44(32):53-55.
［10］	罗瑜,李涛,王丹琛,等. 支持向量机中核函数的性能评价策略［J］. 计算机工程, 2007,33(19):186-187,198.
［11］	Xu Z Q, Li P W, Wang Y X. Text classifier based on an improved SVM decision tree［J］. Physics Procedia, 2012,33:1986-1991.
［12］	Qi Z Q, Tian Y J, Shi Y. Structural twin support vector machine for classification［J］. Knowledge-Based Systems, 2013,43:74-81.
［13］	Chu W, Gao X G, Soroosh S. Handling boundary constraints for particle swarm optimization in high-dimensional search space［J］. Information Sciences, 2011,181(20):4569-4581.
［14］	Liang J J, Qin A K, Suganthan P N, et al. Comprehensive learning particle swarm optimizer for global optimization of multimodal functions［J］. IEEE Transactions on Evolutionary Computation, 2006,10(3):281-295.
［15］	陆春霞,马少辉. 基于网格搜索的船体不规则分段动态堆放方法［J］. 计算机应用, 2013,33(2):333-337.

[1]	ZHANG Xiao-dong, WANG Xu-ying, QIN Zi-xuan. Pump Detection Period Predicting of Pump Well Based on Feature Fusion [J]. Computer and Modernization, 2022, 0(12): 60-66.
[2]	ZHOU Chang-ye, LI Cheng. Prediction of Railway Freight Volume Based on GS-LSTM Model [J]. Computer and Modernization, 2022, 0(10): 24-28.
[3]	WANG Lei, SONG Bo. Risk Prediction Model of Heart Failure Unplanned Readmission Based on ADE-Stacking [J]. Computer and Modernization, 2022, 0(01): 23-27.
[4]	XI Xing-xing, LIU Yu-hong, ZHANG Rong-fen. SVR Blood Pressure Prediction Method Based on Grid Search and Cross Validation [J]. Computer and Modernization, 2020, 0(03): 44-.
[5]	LIU Hong-mei1, XU Ying-lan1, ZHANG Bo2， LI Rong1. Prediction of Water Quality Based on Least Square Support Vector Regression [J]. Computer and Modernization, 2019, 0(09): 31-.
[6]	ZHOU Di1,2. An Optimization Method of SVM Parameters Based on Improved QPSO Algorithm [J]. Computer and Modernization, 2018, 0(09): 27-.
[7]	SHI Qiangqiang1， ZHAO Yingding2,3， YANG Hongyun2,3. Emotion Analysis of Hotel Customers Reviews Based on SVM [J]. Computer and Modernization, 2017, 0(3): 117-.
[8]	LU Jian1, ZHANG Ke2. PID Controller of Permanent Magnet Synchronous Motor Based #br# on Improved Particle Swarm Optimization Algorithm [J]. Computer and Modernization, 2015, 0(7): 123-.
[9]	WU Xin-sheng. PID Neural Network Optimizing Control Based on Particle Swarm Optimization in Paper Process [J]. Computer and Modernization, 2015, 0(3): 71-74,79.
[10]	DU Ying, LIU Yi-an. An Improved Particle Swarm Optimization Algorithm Based on Dimension #br# Sine Changing Inertia Weight and t Mutation [J]. Computer and Modernization, 2014, 0(6): 84-87,93.
[11]	YE Ning;YING Ren-dong;ZHU Xin-zhong;LI Chao;LIU Pei-lin . Parameter Optimization of High-reliable Bus in System-on-Chip [J]. Computer and Modernization, 2013, 1(9): 190-194,.
[12]	LI Xuesi;BI Yangang;YANG Hongqiao;WU Fei. An Automatic Model Selection Method for Support Vector Regression [J]. Computer and Modernization, 2011, 194(10): 19-23.
[13]	GUAN Yan;YU Zhong-dang. Study of Image Magnification Method Based on LS-SVR Filter [J]. Computer and Modernization, 2010, 1(5): 50-52.
[14]	LIU Jiao. Application of Improved Particle Swarm Optimization Algorithm in PID Controller Parameters Optimization for Main Steam Temperature System [J]. Computer and Modernization, 2009, 1(12): 29-32.