A FUZZY CO-CLUSTERİNG ALGORİTHM FOR BİOMEDİCAL DATA

Abstract

In order to increase the accuracy of clustering biomedical data, fuzzy co-clustering extends co-clustering by applying membership functions to both the objects and the characteristics. In this research, we provide a novel information bottleneck-based fuzzy co-clustering algorithm called ibFCC. The distance between a feature data point and the feature cluster centroid is calculated using the information bottleneck theory by the objective function called the ibFCC. Using five biomedical datasets, numerous experiments were done, and the ibFCC was compared to well-known fuzzy (co-)clustering algorithms as FCM, FCCM, RFCC, and FCCI. According to experimental data, ibFCC could produce high-quality clusters and was more accurate than any of these approaches