Title :
An improved scheme for the fuzzifier in fuzzy clustering
Author :
Romdhane, L.B. ; Ayeb, B. ; Wang, S.
Author_Institution :
Dept. of Math. & Comput. Sci., Sherbrooke Univ., Que., Canada
Abstract :
Clustering is an important research area and of practical applications in many fields. Fuzzy clustering has shown advantages over crisp and probabilistic clustering especially when there are significant overlaps between clusters. However, all of the fuzzy clustering algorithms are sensitive to an exponent parameter, namely the fuzzifier. To our knowledge, no theoretical foundations are yet available for the optimal choice of this parameter. The current work develops an improved scheme for the fuzzifier by embedding more knowledge about the data set to cluster in its computation
Keywords :
fuzzy set theory; neural nets; pattern recognition; exponent parameter; fuzzy clustering; neural nets; Application software; Clustering algorithms; Computer science; Embedded computing; Fuzzy neural networks; Fuzzy sets; Neural networks; Partitioning algorithms; Pattern recognition; Thumb;
Conference_Titel :
Neural Networks for Signal Processing [1997] VII. Proceedings of the 1997 IEEE Workshop
Conference_Location :
Amelia Island, FL
Print_ISBN :
0-7803-4256-9
DOI :
10.1109/NNSP.1997.622414
