A Dynamic Traffic Forecast Using Hybrid Wavelet Network with an Adaptive Genetic Local Search

Author

Cao, Kai ; Zhao, Mo

Author_Institution

Shandong Univ. of Technol., Zhangdian

fYear

2007

fDate

Sept. 30 2007-Oct. 3 2007

Firstpage

7

Lastpage

11

Abstract

The paper proposes a dynamic predictor using hybrid wavelet neural network, which use multiple types of mother wavelet in the network according to the feature of pattern change of predicted information instead of a single type. The predictor has function of parallel prediction. In addition, an adaptive genetic local search algorithm is employed to train effectively the network. A case study of traffic information forecasting using proposed wavelet neural network is demonstrated.

Keywords

neural nets; search problems; traffic engineering computing; wavelet transforms; adaptive genetic local search; dynamic predictor; dynamic traffic forecast; hybrid wavelet neural network; parallel prediction; traffic information forecasting; Adaptive systems; Artificial neural networks; Feedforward neural networks; Function approximation; Genetics; Intelligent transportation systems; Neural networks; Signal processing algorithms; Space technology; Telecommunication traffic;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation Systems Conference, 2007. ITSC 2007. IEEE

Conference_Location

Seattle, WA

Print_ISBN

978-1-4244-1396-6

Electronic_ISBN

978-1-4244-1396-6

Type

conf

DOI

10.1109/ITSC.2007.4357671

Filename

4357671