A COMPREHENSIVE COMPARISON OF DIFFERENT CLUSTERING METHODS FOR RELIABILITY ANALYSIS OF MICROARRAY DATA

Abstract

In this study, we considered some competitive learning methods which include hard competitive learning (HCL) and soft competitive learning (SCL) with/ without fixed network dimensionality for reliability analysis in microarrays. In order to have a more extensive view, and keeping in mind that competitive learning methods aim at error minimization or entropy maximization (different kinds of function optimization), we decided to investigate the abilities of mixture decomposition schemes, too. Therefore, we assert that this study covers the algorithms based on function optimization, with particular insistence on different competitive learning methods.  The destination is finding the most powerful method according to a pre-specified criterion determined with numerical methods and matrix similarity measures. Furthermore, we should provide an indication showing the intrinsic ability of the dataset to form clusters before we apply a clustering algorithm. So, we proposed Hopkins statistic as a method for finding the intrinsic ability of a data to be clustered. The results show the remarkable ability of Rayleigh mixture model in comparison with other methods in reliability analysis task.