Predication of Sunspot Number Based on Parallel Process Neural Networks-Reference-Cited by-同舟云学术

Predication of Sunspot Number Based on Parallel Process Neural Networks

Published:2013-09 Issue: Volume:411-414 Page:2098-2101
ISSN:1662-7482
Container-title:Applied Mechanics and Materials
language:
Short-container-title:AMM

Author:

Gao Yan¹,Yu Tie Cheng¹,Li Zhi¹,Li Yun Jiang¹,Li Xin²

Affiliation:

1. Daqing Oilfield Co.,LTD

2. Daqing Hongweijiye Automation Technology Co., Ltd

Abstract

To solve prediction of sunspot number, a parallel process neural networks model is proposed in this paper, Firstly, by dividing the whole time-varying process into several small time intervals, the process neural networks are constructed in these small time intervals, which may disperse the load of networks. Then, employing the orthogonal basis expansion in functional space, the learning algorithm of the above-mentioned model is designed. The experimental results of time series predication of sunspots show that the proposed method has great potential for complicated nonlinear time series prediction.

Publisher

Trans Tech Publications, Ltd.

Link

https://www.scientific.net/AMM.411-414.2098.pdf

Reference7 articles.

1. X.G. He, J.Z. Liang: Some Theoretical Issues on Procedure Neural Networks. Engineering Science. Vol. 2( 2000), pp.40-44.

2. X.G. He, J.Z. Liang, S.H. Xu: Learning for process neural networks and its applications. Engineering Science. Vol. 3 (2001), pp.31-35.

3. K.H. Xu, P.F. Cheng, H.J. Wen: Singular spectrum analysis and wavelet analysis on time series of sunspot. Science of Surveying and Mapping. Vol. 32 (2007), pp.35-38.

4. H.J. Zhao, J.L. Wang, W.G. Zong: Prediction of the smoothed monthly mean sunspot numbers by means of radial basis function neural networks. Chinese Journal of Geophysics. Vol. 51 (2008), pp.31-35.

5. G. Ding, S.S. Zhong: Sunspot number prediction based on process neural network with time-varying threshold functions. Acta Physica Sinica. Vol. 56 (2007), pp.1224-1230.