A novel information-theoretic clustering algorithm for robust, unsupervised classification

Turgay Temel*, Nizamettin Aydin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

A new information-theoretic, unsupervised, subtractive clustering algorithm is proposed. The algorithm eliminates threshold constraint to detect possible cluster members. Cluster centers are formed with minimum entropy. Instead of using a fixed-threshold, a decision region is formed with the use of maximum mutual information. Cluster members are chosen with a relative-cost assigned in partitions of data set. The algorithm yields more reliably distributed cluster numbers in statistical sense, hence reducing further computation for validation, which is justified for a set of synthetic data.

Original languageEnglish
Title of host publication2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007 - Sharjah, United Arab Emirates
Duration: 12 Feb 200715 Feb 2007

Publication series

Name2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007, Proceedings

Conference

Conference2007 9th International Symposium on Signal Processing and its Applications, ISSPA 2007
Country/TerritoryUnited Arab Emirates
CitySharjah
Period12/02/0715/02/07

Fingerprint

Dive into the research topics of 'A novel information-theoretic clustering algorithm for robust, unsupervised classification'. Together they form a unique fingerprint.

Cite this