New information-based clustering method using Renyi's entropy and Fuzzy C-means clustering
Mehdi Aghagolzadeh, Hamid Soltanian‐Zadeh, Babak Nadjar Araabi · IEEE International Conference on Signal and Image Processing · 2005
This paper presents a new clustering method based on Renyi entropy. The proposed method maximizes entropy of clusters using between and within clusters entropies. It is a top-down multi-resolution method and uses the initial clusters found by Fuzzy C-Means. Applications of the proposed algorithm on the synthetic data are compared with those of C-Means and GustafsonKessel algorithms. Results show superiority of the proposed algorithm to these methods.