基于GA-WNN的高速公路事件检测  

WNN Highway Traffic Incident Detection Based on Genetic Algorithm Optimization

作　　者：谢聪[1] 余立建[1] 

机构地区：[1]西南交通大学交通信息工程及控制实验室,四川成都611756

出　　处：《交通科技与经济》2015年第6期76-79,共4页Technology & Economy in Areas of Communications

摘　　要：由于高速公路事件的发生地点和时刻具有不确定性特点,传统的检测算法难以达到要求。采用小波神经网络(WNN)构建事件检测模型,运用改进的遗传算法优化WNN的初始权值和小波因子,结合真实的交通事件数据库(I-880)进行仿真。用评价指标对仿真结果进行评价,结果表明这种方法具有一定的优越性。Time and location of highway traffic incident has the characteristics of uncertainty.The traditional detection algorithm can not to meet the requirements.This paper constructs incident detection model with wavelet neural network（WNN）,and use the improved Genetic Algorithm to optimize initial weights of WNN and wavelet factor,and simulate it combined with the real incident data set（I-880）.Finally,the simulation results were evaluated with the common evaluation index.The results show that this model has certain advantages.

关 键 词：小波神经网络 交通事件检测 遗传算法优化 I-880数据集 

分 类 号：U491[交通运输工程—交通运输规划与管理]