Title :
Performance of kernel-based fuzzy clustering
Author :
Graves, D. ; Pedrycz, W.
Author_Institution :
Univ. of Alberta, Edmonton
Abstract :
An evaluation and comparative study of kernel-based fuzzy clustering algorithms is presented. The main objective is to evaluate the performance gains provided by kernelised FCM (fuzzy C-means). It is shown that kernelised FCM provides marginal improvements in the classification rate for several popular Machine Learning data sets. It is observed that the performance of kernelised FCM depends greatly on the selection of the kernel parameters.
Keywords :
fuzzy set theory; learning (artificial intelligence); pattern clustering; fuzzy C-means; kernel-based fuzzy clustering; kernelised FCM; machine learning;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20073093
