摘要
提出了一种基于遗传算法优化的RBF神经网络交通流预测新方法,该方法把遗传算法应用于RBF神经网络的参数确定中,实现了RBF神经网络隐层高斯函数的中心矢量和基宽向量以及隐层与输出层之间的权值的优化,提高了RBF神经网络的泛化能力。仿真结果表明:改进的RBF网络用于交通流预测中具有可靠的精度和较好的收敛速度,具有广阔的应用推广前景。
A new method of traffic flow forecasting based on optimized RBF neural networks using genetic algorithm was improved. Genetic algorithm was applied to optimize position of data centers, widths and weights of RBF neural network in this method. Consequently, RBF neural networks designed with this method could generalize well. The simulation results show that the improved RBF neural networks applied in traffic flow forecasting with reliable accuracy and good convergence rate. The method possesses high value being generalized.
出处
《计算机与数字工程》
2010年第9期127-129,139,共4页
Computer & Digital Engineering
关键词
遗传算法
RBF神经网络
参数优化
交通流量预测
genetic algorithm, RBF neural networks, parameter optimization, traffic flow forecasting
