High-dimensional clustering using frequency sensitive competitive learning

In this paper a clustering algorithm for sparsely sampled high-dimensional feature spaces is proposed. The algorithm performs clustering by employing a distance measure that compensates for diierently sized clusters. A sequential version of the algorithm is constructed in the form of a frequency sensitive Competitive Learning scheme. Experiments are conducted on an artiicial gaussian data set and on wavelet-based texture feature sets, where classiication performance is used as a clustering signiicance measure. It is shown that the proposed technique improves classiication performance dramatically for high dimensional problems.