Soft Attribute Selection for Hierarchical Clustering in High Dimensions

In this paper we perform an hierarchical clustering in high – dimensional spaces, without first applying any space reduction. Instead, in each step of the algorithm we perform a soft feature selection, witch does not have to be shared among all input elements. The main goal is to correctly identify the patterns that underly in the data. The proposed algorithm is applied, with promising results, in a well known and widely studied set of medical data.