摘要
采用VISSIM软件模拟交通事件,获得交通流数据,作为检测系统的训练源数据.利用MAT-LAB软件进行仿真.结果表明:相对于其他算法,该网络结构具有检测率高、误报率低、检测时间短的优点,完全适用于交通事件检测系统,同时也存在不足之处,指出了今后进一步研究的方向.
Based on the model of incident in VISSIM software,we simulated an incident that caused by a car suddenly stop on it,and then collect the traffic parameters before and after the incident.After obtaining the original simulated data,we use DB2 wavelet analysis to deal and process the traffic parameters,and then propose the results based on BP neural network.After the simulation of MATLAB language,the results shows that this new method has many advantages and has a such higher detection rate,lower false alarm rate and shorter mean detection time.
出处
《武汉理工大学学报（交通科学与工程版）》
2012年第1期69-73,共5页
Journal of Wuhan University of Technology（Transportation Science & Engineering）
