[1]戴群,陈松灿.打折最小平方RBF网络及其时间序列预测研究[J].东南大学学报(自然科学版),2004,34(6):862-864.[doi:10.3969/j.issn.1001-0505.2004.06.032]
 Dai Qun,Chen Songcan.Discounted least square RBF neural networks with applications in time series prediction[J].Journal of Southeast University (Natural Science Edition),2004,34(6):862-864.[doi:10.3969/j.issn.1001-0505.2004.06.032]
点击复制

打折最小平方RBF网络及其时间序列预测研究()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
34
期数:
2004年第6期
页码:
862-864
栏目:
自动化
出版日期:
2004-11-20

文章信息/Info

Title:
Discounted least square RBF neural networks with applications in time series prediction
作者:
戴群 陈松灿
南京航空航天大学计算机科学与工程系, 南京 210016
Author(s):
Dai Qun Chen Songcan
Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
关键词:
打折最小平方 径向基函数 时间序列预测
Keywords:
discounted least squares radial basis function time series prediction
分类号:
TP183
DOI:
10.3969/j.issn.1001-0505.2004.06.032
摘要:
借用打折最小平方(DLS)原理构建了基于误差平方准则的DLS-RBF网络的学习算法.打折最小平方原理考虑了时间序列本身的结构性变化,较好地刻画了预测点与其他时刻数据的相关性,而这些恰恰是现有的径向基函数神经网络(RBF)在预测过程中所忽视的.实验表明DLS-RBF网络在非平稳方差时间序列和某城市自来水实际的月用水量预测中的效果明显,并优于RBF网络,但在混沌时间序列预测的实验中,因其自身的混沌特性,预测效果并不十分明显.
Abstract:
The discounted least squares(DLS)principle is borrowed to construct the learning algorithm of DLS-RBF based upon squared error criterion. The principle of DLS formulates inherent structural changes and time correlation in time series itself precisely, while in the learning and predicting process of current radial basis function(RBF)network this correlation is neglected. Experiments show that DLS-RBF has better performance than RBF in non-stationary covariance time series and daily-life-water consumption prediction. But in the experiments of chaotic time series forecasting, the predictive effects are not prominent due to its chaotic characteristics.

参考文献/References:

[1] Refenes Apostolos-Paul,Bentz Yves,Bunn Derek W.Financial time series modelling with discounted least squares backpropagation [J]. Neurocomputing,1997,14(2):123-138.
[2] 王旭东,邵惠鹤.RBF神经网络理论及其在控制中的应用 [J].信息与控制,1997,26(4):272-284.
  Wang Xudong,Shao Huihe.RBF neural network theory with applications in cybernetics [J]. Information and Cybernetics, 1997,26(4):272-284.(in Chinese)
[3] 李冬梅,王正欧.基于RBF神经网络的混沌时间序列预测 [J].模式识别与人工智能,2001,14(2):231-234.
  Li Dongmei,Wang Zhengou.Chaotic time series prediction based on RBF neural network [J].Pattern Recognition and Artificial Intelligence,2001,14(2):231-234.(in Chinese)
[4] Neural Computing Research Group.Netlab [EB/OL].http://www.ncrg.aston.ac.uk.2003-01-15/2003-02-08.
[5] Chen C L Philip,Wan John Z.A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction [J]. IEEE Transaction on Systems,Man and Cybernetics-part B:Cybernetics, 1999,29(1):62-72.
[6] 周俊武,孙传尧.径向基函数(RBF)网络的研究及实现 [J].矿冶,2001,10(4):71-75.
  Zhou Junwu,Sun Chuanyao.RBF network research and realization [J]. Mining, 2001, 10(4):71-75.(in Chinese)

相似文献/References:

[1]薛晓岑,向文国,吕剑虹.基于差分进化与RBF神经网络的热工过程辨识[J].东南大学学报(自然科学版),2014,44(4):769.[doi:10.3969/j.issn.1001-0505.2014.04.016]
 Xue Xiaocen,Xiang Wenguo,Lü Jianhong.Thermal process identification based on differential evolution and RBF neural network[J].Journal of Southeast University (Natural Science Edition),2014,44(6):769.[doi:10.3969/j.issn.1001-0505.2014.04.016]

备注/Memo

备注/Memo:
基金项目: 江苏省自然科学基金资助项目(BK2002092)、教育部留学回国人员基金资助项目.
作者简介: 戴群(1974—), 女, 博士生; 陈松灿(联系人), 男, 博士,教授, 博士生导师, s.chen@nuaa.edu.cn.
更新日期/Last Update: 2004-11-20