Fuzzy Neural Network Model Applied in the Traffic Flow Prediction
The paper proposes a fuzzy neural network model(FNNM) strategy for predicting the traffic flow of real time traffic control systems. The proposed model is composed of two modular. One is a fuzzy network (FN), which is used for fuzzy clustering. Each cluster represents one kind of specific traffic pattern. The other is a neural network (NN), which is one-layer network and is used for partitioning the relationship of input and output vector. And the FN module supervises the learning of the NN. That is, the features of the traffic samples are employed to guide the training of the NN. Moreover, an on-line iterative predictive algorithm is presented in this paper to predict the traffic flow according to the sampled data of the upstream cross roads. Finally, the real sampled traffic flow data is employed to validate the proposed method. Results show that the proposed traffic flow prediction strategy based on fuzzy neural network model is feasible and effective.
Fuzzy neural network model Traffic flow Prediction
Gang Tong Chunling Fan Fengying Cui Xiangzhong Meng
College of Automation & Electronic Engineering,Qingdao University of Science & Technology, Qingdao 266042
国际会议
2006 IEEE International Conference on Information Acquisition
山东威海
英文
1229-1233
2006-08-20（万方平台首次上网日期，不代表论文的发表时间）