Kernel-based fuzzy c-means clustering algorithm based on genetic algorithm

Fuzzy c-means clustering algorithm (FCM) is a method that is frequently used in pattern recognition. It has the advantage of giving good modeling results in many cases, although, it is not capable of specifying the number of clusters by itself. Aimed at the problems existed in the FCM clustering alg...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) Vol. 188; pp. 233 - 238
Main Authors: Ding, Yi, Fu, Xian
Format: Journal Article
Language:English
Published: Elsevier B.V 05.05.2016
Subjects:
Adaptive algorithms
Algorithms
Clustering
Fuzzy
Fuzzy c-means clustering
Fuzzy clustering
Genetic algorithm
Genetic algorithms
Kernel-based fuzzy c-means
Matlab
Optimization
Performance enhancement
Fuzzy clustering
Fuzzy c-means clustering
Kernel-based fuzzy c-means
Genetic algorithm
ISSN:0925-2312, 1872-8286
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fuzzy c-means clustering algorithm (FCM) is a method that is frequently used in pattern recognition. It has the advantage of giving good modeling results in many cases, although, it is not capable of specifying the number of clusters by itself. Aimed at the problems existed in the FCM clustering algorithm, a kernel-based fuzzy c-means (KFCM) is clustering algorithm is proposed to optimize fuzzy c-means clustering, based on the Genetic Algorithm (GA) optimization which is combined of the improved genetic algorithm and the kernel technique (GAKFCM). In this algorithm, the improved adaptive genetic algorithm is used to optimize the initial clustering center firstly, and then the KFCM algorithm is availed to guide the categorization, so as to improve the clustering performance of the FCM algorithm. In the paper, Matlab is used to realize the simulation, and the performance of FCM algorithm, KFCM algorithm and GAKFCM algorithm is testified by test datasets. The results proved that the GAKFCM algorithm proposed overcomes FCM׳s defects efficiently and improves the clustering performance greatly.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2015.01.106