Accession number:20084911757030
Title:Choquet integral regression model based on L-measure and
γ-support
Authors:Liu, Hsiang-Chuan (1); Tu, Yu-Chieh (2); Lin, Wen-Chih (3);
Chen, Chin-Chun (2)
Author affiliation:(1) Department of Bioinformatics, Asia University, Taiwan; (2) Graduate Institute of Educational Measurement and Statistics, Taichung University, Taiwan; (3) Department of Computer Science and Information Engineering, Asia University, Taiwan; (4) General Education, Min-Hwei College of Health Care Management, Taiwan
Corresponding author:Liu, H.-C.
Source title:Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR
Abbreviated source title:Proc. Int. Conf. Wavelet Analysis and Pattern Recognition, ICWAPR
Volume:2
Monograph title:Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR
Issue date:2008
Publication year:2008 Pages:777-782
Article number:4635882 Language:English
ISBN-13:9781424422395
Document type:Conference article (CA)
Conference name:2008 International Conference on Wavelet Analysis and Pattern Recognition, ICWAPR
Conference date:August 30, 2008 - August 31, 2008 Conference location:Hong Kong, China
Conference code:74125
Publisher:Inst. of Elec. and Elec. Eng. Computer Society, 445 Hoes Lane - P.O.Box 1331, Piscataway, NJ 08855-1331, United States Abstract:When the multicollinearity within independent variables occurs in the multiple regression models, its performance will always be poor. Replacing the above models with the ridge
regression model is the traditional improved method. In our previous work, we found that, the Choquet integral regression model with R- measure based on the new support, γ-support, proposed by us has the best performance than before. In this study, for finding the further improved model, we replaced R-measure with our new fuzzy measure, L-measure in Choquet integral regression model with the new support, γ-support. For comparing the Choquet integral regression model with P-measure, λ-measure, R- measure and L-measure based on two different fuzzy supports, V- support and γ-support, respectively, the traditional multiple regression model and the ridge regression model, a real data
experiment by using a 5-fold cross-validation mean square error (MSE) is conducted. Experimental result shows that the Choquet integral regression model with L-measure based on γ- support has the best performance. ©2008 IEEE.
Number of references:12
Main heading:Regression analysis
Controlled terms:Feature extraction - Integral equations - Mean square error - Pattern recognition - Wavelet analysis - Wavelet transforms
Uncontrolled terms:Choquet integrals - Cross validations - Fuzzy measure - Fuzzy measures - Fuzzy support - Improved methods - Improved models - Independent variables - L-measure - Mean
squares - Multicollinearity - Multiple regression models - R-measure - Real datums - Regression models - Ridge regressions
Classification code:922.2 Mathematical Statistics - 921.3
Mathematical Transformations - 921.2 Calculus - 921 Mathematics - 751.1 Acoustic Waves - 741.1 Light/Optics - 731.1 Control Systems - 723.5 Computer Applications - 723.2 Data Processing and Image Processing - 716 Telecommunication; Radar, Radio and Television - 703.2.1 Electric Filter Analysis
DOI:10.1109/ICWAPR.2008.4635882 Database:Compendex
Compilation and indexing terms, Copyright 2009 Elsevier Inc.
