Fuzzy <i>c</i>-Means Clustering Using Kernel Functions in Support Vector Machines

Abstract

We studied clustering algorithms of fuzzy c-means using a kernel to represent an inner product for mapping into high-dimensional space. Such kernels have been studied in support vector machines used by many researchers in pattern classification. Algorithms of fuzzy c -means are transformed into kernel-based methods by changing objective functions, whereby new iterative minimization algorithms are derived. Numerical examples show that clusters that cannot be obtained without a kernel are generated.