In this paper, an self-organizing TSK-Type fuzzy neural network is proposed for predicting the short-term traffic flow. The proposed fuzzy neural network is adaptively organized from the collected short-term traffic flow data. The whole process is divided into two stage, i.e., structure identification and parameter learning. In structure identification, the mean shift clustering algorithm performs the whole traffic flow data set in order to generate the initial structure and mean firing strength method is used to prune the redundant fuzzy neurons. After the structure identification is finished, the chaotic parameter PSO is adopted to perform the parameter learning. Then the trained fuzzy neural network is employed the collected shortterm traffic flow test set and the prediction result verifies that the self-organizing TSK-Type fuzzy neural network has higher prediction accuracy than some traditional methods.
Short-term fuzzy traffic flow prediction using self-organizing TSK-type fuzzy neural network
01.12.2007
204839 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Short-Term Traffic Flow Prediction Based on Fuzzy Time Series
SAE Technical Papers | 2002
|Short-term traffic flow prediction based on fuzzy time series
Kraftfahrwesen | 2002
|Chemical Feeding Control Using a Self-Organizing Fuzzy Neural Network
British Library Online Contents | 1998
|