Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.11861/7565
Title: Classification of heterogeneous fuzzy data by choquet integral with fuzzy-valued integrand
Authors: Yang, Rong 
Wang, Zhenyuan 
Heng, Pheng-Ann 
Prof. LEUNG Kwong Sak 
Issue Date: 2007
Source: IEEE Transactions on Fuzzy Systems, 2007, Vol. 15 ( 5), pp. 931 - 942
Journal: IEEE Transactions on Fuzzy Systems 
Abstract: As a fuzzification of the Choquet integral, the defuzzified choquet integral with fuzzy-valued integrand (DCIFI) takes a fuzzy-valued integrand and gives a crisp-valued integration result. In this paper, the DCIFI acts as a projection to project high-dimensional heterogeneous fuzzy data to one-dimensional crisp data to handle the classification problems involving different data forms, such as crisp data, interval values, fuzzy numbers, and linguistic variables, simultaneously. The nonadditivity of the signed fuzzy measure applied in the DCIFI can represent the interaction among the measurements of features towards the discrimination of classes. Values of the signed fuzzy measure in the DCIFI are considered to be unknown parameters which should be learned before the classifier is used to classify new data. We have implemented a genetic algorithm (GA)-based adaptive classifier-learning algorithm to optimally learn the signed fuzzy measure values and the classified boundaries simultaneously. The performance of our algorithm has been tested both on synthetic and real data. The experimental results are satisfactory and outperform those of existing methods, such as the fuzzy decision trees and the fuzzy-neuro networks. © 2007 IEEE.
Type: Peer Reviewed Journal Article
URI: http://hdl.handle.net/20.500.11861/7565
ISSN: 10636706
DOI: 10.1109/TFUZZ.2006.890658
Appears in Collections:Applied Data Science - Publication

Show full item record

SCOPUSTM   
Citations

41
checked on Nov 3, 2024

Page view(s)

26
Last Week
0
Last month
checked on Nov 13, 2024

Google ScholarTM

Impact Indices

Altmetric

PlumX

Metrics


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.