IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2005-11-19 15:40
Application of minimum description length to Least Squares Support Vector Machines for modeling chaotic dynamical systems
Tsutomu Maeda, Masaharu Adachi (Tokyo Denki Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In this study, we attempt to prune the support vectors of Least Squares Support Vector Machines for function estimation by using a model selection algorithm based on Minimum Description Length principle.
However, it is difficult to improve the accuracy of the obtained model by pruning support vectors of LSSVM using the model selection algorithm.
As preliminary stage for the attempt, we apply the model selection algorithm to pruning support vectors of Support Vector Regression.
As examples of the modeling, we evaluate the proposing method in prediction of two chaotic dynamical systems.
As the result, we show that the number of support vectors is reduced by the algorithm.
Moreover, the accuracy of the obtained model improves in prediction accuracy for unknown data.
Keyword (in Japanese) (See Japanese page) 
(in English) Least Squares Support Vector Machines / Support Vector Regression / Minimum Description Length Principle / Pruning / / / /  
Reference Info. IEICE Tech. Rep., vol. 105, no. 417, NLP2005-83, pp. 71-76, Nov. 2005.
Paper # NLP2005-83 
Date of Issue 2005-11-12 (NLP) 
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380
Download PDF

Conference Information
Committee NLP  
Conference Date 2005-11-18 - 2005-11-19 
Place (in Japanese) (See Japanese page) 
Place (in English) Kyushu Institute of Technology 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Special session and general. Subject of special session is ``Randomness and prediction---from fundamentals to applications''. 
Paper Information
Registration To NLP 
Conference Code 2005-11-NLP 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Application of minimum description length to Least Squares Support Vector Machines for modeling chaotic dynamical systems 
Sub Title (in English)  
Keyword(1) Least Squares Support Vector Machines  
Keyword(2) Support Vector Regression  
Keyword(3) Minimum Description Length Principle  
Keyword(4) Pruning  
1st Author's Name Tsutomu Maeda  
1st Author's Affiliation Tokyo Denki University (Tokyo Denki Univ.)
2nd Author's Name Masaharu Adachi  
2nd Author's Affiliation Tokyo Denki University (Tokyo Denki Univ.)
3rd Author's Name  
3rd Author's Affiliation ()
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Date Time 2005-11-19 15:40:00 
Presentation Time 25 
Registration for NLP 
Paper # IEICE-NLP2005-83 
Volume (vol) IEICE-105 
Number (no) no.417 
Page pp.71-76 
#Pages IEICE-6 
Date of Issue IEICE-NLP-2005-11-12 

[Return to Top Page]

[Return to IEICE Web Page]

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan