A jackknife entropy-based clustering algorithm for probability density functions

Abstract

This paper proposes a new unsupervised learning algorithm called jackknife entropy-based clustering algorithm for grouping families of probability density functions (pdfs). The fitness function is used to choose the best threshold values of similarity in the proposed algorithm. We demonstrate the correctness and robustness of the proposed algorithm on a synthetic data set. Finally, we apply the algorithm to texture clustering.

Keywords:

• Cluster analysis
• entropy
• jackknife
• probability density function
• variance ratio criterion

Disclosure statement

No potential conflict of interest was reported by the authors.