The extended Kullback-Leibler divergence measure in the unknown probability density function cases and applications. (8th September 2021)

• Record Type: Journal Article
• Authors: Le, Hoa; Truong, Hoang Van; Bao, Pham The
• Is Part Of: International journal of intelligent information and database systems. Volume 14:Number 4(2021)
• Page Start: 403
• Page End: 420
• Publication Date: 2021-09-08
• Subjects: Kullback-Leibler divergence -- relative entropy -- mixture models -- similarity measure -- extended Kullback-Leibler divergence; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

The Kullback-Leibler divergence measure is used to evaluate the similarity between two probability distributions. In theory, the probability density functions are known before applying the formula. However, estimating this information of real data is challenging. For that reason, the Kullback-Leibler divergence needs to be modified for similarity measures in these cases. In this paper, we proposed and evaluated an extended Kullback-Leibler divergence similarity measure by two experiments. The first experiment is based on two datasets that have unknown probability density functions, while the second one is conducted on one dataset with an unknown probability density function and the other with a known probability density function. Besides, the proposed method is applied to the simulated data and the plagiarism detection cases.