| 基于混沌神经网络的交通流预测算法 |
| |
| 引用本文： | 胡家兴,陈燕,张立东.基于混沌神经网络的交通流预测算法[J].济南大学学报(自然科学版),2012,26(2):152-155. |
| |
| 作者姓名： | 胡家兴 陈燕 张立东 |
| |
| 作者单位： | 1. 大连海事大学交通运输管理学院,辽宁大连,116026
2. 山东大学控制科学与工程学院,山东济南250061;山东省计算中心,山东济南250014 |
| |
| 基金项目： | 国家自然科学基金﹙70940008﹚；山东省自然科学基金﹙Y2008G34﹚ |
| |
| 摘 要： | 为提高 RBF 神经网络的交通流预测精度，提出基于混沌-RBF（Chaos-RBF，C-RBF）神经网络的交通流预测算法，该算法首先计算混沌相空间的嵌入维数和嵌入延迟，构造得到的相空间向量作为 RBF 神经网络的输入，其相空间次邻向量作为期望输出值，滚动训练得到神经网络的权值，然后以实际交通流作为输入，经由网络计算得到预测值。仿真结果表明该算法相比于 RBF 神经网络，预测精度提高 96%，证明了该算法的有效性。
|
| 关 键 词： | RBF 神经网络 智能交通 交通流预测 混沌理论 |
Traffic Flow Prediction Algorithm Study via Chaos RBF Network |
| |
| HU Jia-xing
,
CHEN Yan
,
ZHANG Li-dong.Traffic Flow Prediction Algorithm Study via Chaos RBF Network[J].Journal of Jinan University(Science & Technology),2012,26(2):152-155. |
| |
| Authors: | HU Jia-xing CHEN Yan ZHANG Li-dong |
| |
| Institution: | 2,3(1.Transportation Management School,Dalian Maritime University,Dalian 116026,China;2.Control Science and Engineering Institute, Shandong University,Jinan 250061,China;3.Shandong Computer Science Center,Jinan 250014,China) |
| |
| Abstract: | To improve the precision of traffic flow forecasting,we studied a kind of new chaos RBF neural network(C-RBF) algorithm.It first calculates embedding dimensions and embedding delay of chaos phase space,takes the phase space vector as the input of RBF neural network and the vector value next to input as the output expectation value,finally trains the network and gets the weights.In practice,the collected traffic flow could be input into the net,and after phase space reconstruction and network forecasting,the prediction and error value are got.The simulation results show that our algorithm is much more precise than common RBF network,and the prediction accuracy is improved by 96%. |
| |
| Keywords: | RBF neural network ITS traffic flow prediction chaos theory |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
