Abstract
Based on the motivation by computational challenges in microarray data analysis, we propose a fuzzy hyper-cluster analysis as a new framework for pattern classification using such type of data. This approach uses hyperplanes to represent the cluster centers in the fuzzy c-means algorithm. We present in this position paper the formulation of a hyperplane-based fuzzy objective function and suggest possible solutions. Fuzzy hyper-clustering approach appears to have potential as a novel alternative to analyze microarray gene expression data. Furthermore, the proposed hyper-clustering algorithm is not only confined to microarray data analysis but can be used as a general approach for classifying closely related features.