论文部分内容阅读
为了提高交通流诱导系统的性能,研究了一种基于自适应延时神经网络算法的短时交通流量预测模型,该算法与传统的神经网络方法相比在神经网络的结构和神经网络的训练方法两个方面进行了改进,更适用于预测具有不确定性、非线性、动态性等特征的短时交通流,同时用Matlab7.0编写程序对算法进行了仿真实现,根据仿真结果的分析验证了算法时实性和精确性.
In order to improve the performance of traffic flow guidance system, a short-term traffic flow forecasting model based on adaptive time-delay neural network algorithm is studied. Compared with the traditional neural network method, the proposed algorithm can be used in neural network structure and neural network training method Which is more suitable for forecasting short-time traffic flow with the characteristics of uncertainty, nonlinearity and dynamics. At the same time, Matlab7.0 program is used to simulate the algorithm. Based on the simulation results, it is verified that Algorithm realism and accuracy.