A Monte Carlo simulation study on Choquet integral with respect to different fuzzy measures

Author

Yao, Hsu-chan ; Liu, Hsiang-chuan ; Jheng, Yu-Du ; Chang, Chun-jey

Author_Institution

Grad. Inst. of Educ. Meas. & Stat., Taichung Univ., Taichung, Taiwan

Volume

5

fYear

2010

fDate

11-14 July 2010

Firstpage

2366

Lastpage

2371

Abstract

In this paper, a hybrid method based on Monte Carlo simulation study method and 5-fold cross-validation MSE method is used, a simulation experiment is conducted for comparing the performances of a multiple linear regression model, a ridge regression model, and the Choquet integral regression model with respect to three well known fuzzy measures, P-measure, λ-measure and L-measure, respectively. The result shows that the Choquet integral regression model with respect to L-measure outperforms other forecasting models.

Keywords

Monte Carlo methods; fuzzy set theory; mean square error methods; λ-measure; 5-fold cross-validation MSE method; Choquet integral regression model; L-measure; Monte Carlo simulation study method; P-measure; fuzzy measures; multiple linear regression model; ridge regression model; Correlation; Data models; Linear regression; Machine learning; Mathematical model; Monte Carlo methods; Predictive models; Choquet integral; Fuzzy measure; L-measure; Simulation;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics (ICMLC), 2010 International Conference on

Conference_Location

Qingdao

Print_ISBN

978-1-4244-6526-2

Type

conf

DOI

10.1109/ICMLC.2010.5580667

Filename

5580667