文档介绍：ARTICLE IN PRESS
puting 69 (2006) 449–465
ate/
Time-series prediction using a local linear wavelet
work
Yuehui Chena,Ã, Bo Yanga,b, Jiwen Donga,b
aSchool of Information Science and Engineering, Jinan University, 250022 Jinan, PR China
bState Key Laboratory of Advanced Technology for Materials Synthesis and Processing,
Wuhan University of Science and Technology, Wuhan, PR China
Received 11 July 2004; received in revised form 25 January 2005; accepted 7 February 2005
Available online 19 April 2005
Communicated by T. Heskes
Abstract
A local linear wavelet work (LLWNN) is presented in this paper. The difference
of work with conventional wavelet work (WNN) is that the connection
weights between the hidden layer and output layer of conventional WNN are replaced by a
local linear model. A hybrid training algorithm of particle swarm optimization (PSO) with
diversity learning and gradient descent method is introduced for training the LLWNN.
Simulation results for the prediction of time-series show the feasibility and effectiveness of the
proposed method.
r 2005 Elsevier . All rights reserved.
Keywords: Local linear wavelet work; Particle swarm optimization algorithm; Gradient descent
algorithm; Time-series prediction
1. Introduction
Recently, in stead of mon sigmoid activation functions, the wavelet
work (WNN) employing nonlinear wavelet basis functions (named
ÃCorresponding author.
E-mail addresses: ******@ujn. (Y. Chen), ******@ujn. (B. Yang), ******@ujn.
(J. Dong).
0925-2312/$ - see front matter r 2005 Elsevier . All rights reserved.
doi:..
ARTICLE IN PRESS
450 Y. Chen et al. / puting 69 (2006) 449–465
wavelets), which are localized in both the time space and frequency space,
has been developed as an alternative approach to nonlinear fitting problem
[31,36]. Two key problems in designing of WNN are how to determine WNN
architecture and what learning algorithm can be effectively used for training