Title :
Nonlinear fuzzy multiregressions based on fuzzy Choquet integrals
Author :
Ji, Ai-bing ; Qiu, Hong-Jie ; Ha, Ming-Hu
Author_Institution :
Coll. of Med., Hebei Univ., Baoding
Abstract :
In this paper, two kinds of fuzzy Choquet integral are first defined: one is the fuzzy Choquet integral of fuzzy-valued functions with respect to fuzzy measure, the another is the fuzzy Choquet integral of real-valued functions with respect to fuzzy-valued fuzzy measure. Using a nonadditive crisp/fuzzy set function to describe the interaction among attributes, two kinds of new nonlinear fuzzy multiregression are established based on fuzzy Choquet integrals. Such models are generalizations of the traditional fuzzy linear multiregression.
Keywords :
fuzzy set theory; integral equations; regression analysis; fuzzy Choquet integrals; fuzzy-valued functions; nonlinear fuzzy multiregressions; real-valued functions; Cybernetics; Data mining; Educational institutions; Fuzzy sets; Linear programming; Linear regression; Machine learning; Parameter estimation; Regression analysis; Uncertainty; Fuzzy Choquet integral; Fuzzy-valued fuzzy measure; Non-additive measures; Nonlinear fuzzy multiregression;
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
DOI :
10.1109/ICMLC.2008.4620465