DocumentCode :
3287659
Title :
The deformation time series prediction based on wavelet and neural network
Author :
Hong-yan, Wen ; Lin, Jiang ; Bin, Liu ; Lilong, Liu
Author_Institution :
Coll. of Civil Eng., Guilin Univ. of Technol., Guilin, China
fYear :
2011
fDate :
15-17 April 2011
Firstpage :
6242
Lastpage :
6245
Abstract :
In the paper, the research present situation and development in the wavelet neural network model and a novel learning algorithm for wavelet neural network based on extended Kalman filter are discussed. Based on combining the exceptional property of localization of the wavelet transform and characteristics of self-learning of neural networks, the non-line time series model and network architecture model which combines affine transform with revolving transform is discussed .A novel learning algorithm for wavelet neural network based on extended Kalman filter is proposed to predict the deformation of structure. In comparison with the WNN algorithm, the EKF learning algorithm has improved convergence and can provide much more accuracy learning results.
Keywords :
Kalman filters; neural nets; time series; wavelet transforms; affine transform; deformation time series prediction; extended Kalman filter; network architecture model; novel learning algorithm; wavelet neural network model; Artificial neural networks; Deformable models; Equations; Kalman filters; Mathematical model; Predictive models; Wavelet analysis; deformation prediction; extended kalman filter; wavelet analysis; wavelet neural network;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electric Information and Control Engineering (ICEICE), 2011 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-8036-4
Type :
conf
DOI :
10.1109/ICEICE.2011.5777996
Filename :
5777996
Link To Document :
بازگشت