Information Theoretic Hierarchical Clustering

Entropy

Mehdi Aghagolzadeh¹  Hamid Soltanian-Zadeh¹ 

[1] Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, University of Tehran, PO Box 1439957131, Tehran 14395-515, Iran

关键词: information theory;    Rényi’s entropy;    quadratic mutual information;    hierarchical clustering;    proximity measure;   

DOI  :  10.3390/e13020450

来源: mdpi

【 摘 要 】

Hierarchical clustering has been extensively used in practice, where clusters can be assigned and analyzed simultaneously, especially when estimating the number of clusters is challenging. However, due to the conventional proximity measures recruited in these algorithms, they are only capable of detecting mass-shape clusters and encounter problems in identifying complex data structures. Here, we introduce two bottom-up hierarchical approaches that exploit an information theoretic proximity measure to explore the nonlinear boundaries between clusters and extract data structures further than the second order statistics. Experimental results on both artificial and real datasets demonstrate the superiority of the proposed algorithm compared to conventional and information theoretic clustering algorithms reported in the literature, especially in detecting the true number of clusters.

【 授权许可】

CC BY   
© 2011 by the authors; licensee MDPI, Basel, Switzerland.