摘要
提出了一种差分进化算法优化T-S模糊神经网络预测交通流量的算法方法。该算法利用差分进化来弥补T-S模糊神经网络连接权值和阈值选择上的随机性缺陷,从而能发挥T-S模糊神经网络泛化的映射能力,而且能使T-S模糊神经网络具有较快的收敛性以及较强的学习能力。将该算法应用到实测交通流进行算法的有效性验证,并与传统的T-S模糊神经网络进行比较,仿真结果表明,该算法具有更好的非线性拟合能力和更高的预测准确性,在交通流量预测领域具备可行性和有效性。
A prediction algorithm for traffic flow of T-S fuzzy neural network optimized differential evolution （DETSFNN） is proposed. In the algorithm, DE is used to compensate therandom defects for the thresholds and weights of T-S fuzzy neural net- work, thus it can perform mapping ability of T-S fuzzy neural network for generalization and also can make T-S fuzzy neural net- work have faster convergence and greater learning ability, The efficiency of the proposed prediction method is tested by the simu- lation of real traffic flow. The simulation results show that the proposed method has better nonlinear fitting ability and higher forecasting accuracy compared with the traditional T-S fuzzy neural network, and prove it is feasible and effective in the practical prediction of traffic flow.
出处
《计算机工程与设计》
CSCD
北大核心
2013年第9期3284-3287,共4页
Computer Engineering and Design
基金
甘肃省自然科学基金项目(1112RJZA051)
关键词
差分进化
T-S模型
模糊神经网络
交通流量
预测
differential evolution （DE）~ T-S model~ fuzzy neural network~ traffic flow~ prediction
