摘要
传统的BP神经网络在预测短时交通流问题上存在很多不足。针对这些不足,提出将小波分析与BP神经网络结合,组成小波神经网络来预测短时交通流的方法。以自贡市某十字路口数据来实测交通流量,Matlab2010b仿真结果表明,小波神经网络在交通流预测精度和收敛速度上都有很大提高。
The application of BP neural network in prediction accuracy and convergence rate of short-term traffic flow is not very satisfactory, then join the wavelet transform theory in traditional BP based on neural network, and applied to the short-term traffic flow prediction, according to the time-frequency characteristics of wavelet transform, wavelet neural network is proposed, and according to a crossroads in Zigong city actual traffic flow data, the simulation results of Matlab2010b show , the wavelet neural network has greatly improved the prediction accuracy in short-time traffic flow, and reflect the superiority of the better.
出处
《软件导刊》
2016年第1期37-39,共3页
Software Guide
基金
四川省智慧旅游基地项目(ZHZ14-04)
