Traffic flow forecasting of Intersection based on a novel Associative Memory System

摘要：

A novel high-order Associative Memory System was firstly proposed based on Newtons Forward Interpolation(NFI-AMS), which is capable of implementing error-free approximations to multi-variable polynomial functions of arbitrary order. The advantages that NFI-AMS offers over conventional CMAC-type neural network are:high-precision of learning, much smaller memory requirement without the data-collision problem and also much less computational effort for training and faster convergence rates than that attainable with multi-layer BP neural networks. Secondly, The on-line traffic flow intelligent rolling predictive method was designed based on NFI-AMS, and the simulation results show that this method is effective.

关键词： Associative Memory System Newtons Forward Interpolation Traffic flow prediction

作者: Chao Xie Luyuan Liu

作者单位: Department of Automation, Tianjin University, Tianjin, China Department of Automation, Tianjin University of Technology and Education, Tianjin, China

会议类型: 国际会议

会议名称: 2006 International Symposium on Distributed Computing and Applications to Business,Engineering and Science(2006年国际电子、工程及科学领域的分布式计算应用学术研讨会)

会议地点: 杭州

会议语种:英文

页码: 1360-1363

在线出版日期: 2006-10-12（万方平台首次上网日期，不代表论文的发表时间）