计算机科学与探索 ›› 2014, Vol. 8 ›› Issue (1): 121-126.DOI: 10.3778/j.issn.1673-9418.1309008

• 人工智能与模式识别 • 上一篇    

基于改进T-S模糊神经网络的交通流量预测

侯  越+   

  1. 兰州交通大学 电子与信息工程学院,兰州 730070
  • 出版日期:2014-01-01 发布日期:2014-01-03

Traffic Flow Prediction Based on Improved T-S Fuzzy Neural Network

HOU Yue+   

  1. School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
  • Online:2014-01-01 Published:2014-01-03

摘要: 在萤火虫优化算法和T-S模糊神经网络的基础上,提出了一种采用萤火虫算法优化的T-S模糊神经网络预测交通流量的算法。该算法利用萤火虫算法得到T-S模糊神经网络的最优参数配置,从而能发挥T-S模糊神经网络泛化的映射能力。将该算法应用到实测交通流中进行算法的有效性验证,并与传统的T-S模糊神经网络和遗传算法优化的T-S模糊神经网络进行比较,仿真结果表明该算法具有更高的预测准确性,从而证明了该算法在交通流量预测领域的可行性和有效性。

关键词: 智能交通系统(ITS), 萤火虫优化算法(GSO), T-S模型, 模糊神经网络, 交通流量, 预测

Abstract: Based on the glowworm swarm optimization (GSO) and T-S fuzzy neural network (TSFNN), this paper proposes a prediction algorithm for traffic flow of T-S fuzzy neural network optimized glowworm swarm optimization (GSOTSFNN). The proposed algorithm uses GSO to get the optimal parameter configuration, thus can perform mapping ability of T-S fuzzy neural network for generalization. The efficiency of the proposed prediction algorithm is tested by the simulation of real traffic flow. The simulation results show that the proposed algorithm has higher forecasting accuracy compared with the traditional T-S fuzzy neural network and T-S fuzzy neural network optimized genetic algorithm, so it is feasible and effective in the practical prediction of traffic flow.

Key words: intelligent transportation system (ITS), glowworm swarm optimization (GSO), T-S model, fuzzy neural network, traffic flow, prediction