AHIMSA: Ad hoc histogram information measure sensing algorithm for feature selection in the context of histogram inspired clustering techniques

This letter outlines an approach to the problem of dimensionality reduction in the context of clustering techniques based on multidimensional histogram analysis. The approach is founded on an evaluation of the hills and valleys in the unidimensional histograms along the different features as the basis for assessing the information contained in the individual feature dimensions from the point of view of clusterability of the data set using these features.