This paper is published in Volume-5, Issue-2, 2019
Area
Data Mining
Author
A. V. S. N. Kaushik, D. Harsha vardhan, Dr. M. Rama Krishna Murthy, B. Sai Chaitanya, G. Nikhil Das
Org/Univ
Anil Neerukonda Institute of Technology and Sciences, Visakhapatnam, Andhra Pradesh, India
Pub. Date
16 March, 2019
Paper ID
V5I2-1303
Publisher
Keywords
Cluster ensemble, Weighted co-association matrix, Latent variable model, Cluster validity index, Margin expectation, Minimum spanning tree

Citationsacebook

IEEE
A. V. S. N. Kaushik, D. Harsha vardhan, Dr. M. Rama Krishna Murthy, B. Sai Chaitanya, G. Nikhil Das. Bunch ensemble with averaged co-association matrix maximizing the expected margin, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
A. V. S. N. Kaushik, D. Harsha vardhan, Dr. M. Rama Krishna Murthy, B. Sai Chaitanya, G. Nikhil Das (2019). Bunch ensemble with averaged co-association matrix maximizing the expected margin. International Journal of Advance Research, Ideas and Innovations in Technology, 5(2) www.IJARIIT.com.

MLA
A. V. S. N. Kaushik, D. Harsha vardhan, Dr. M. Rama Krishna Murthy, B. Sai Chaitanya, G. Nikhil Das. "Bunch ensemble with averaged co-association matrix maximizing the expected margin." International Journal of Advance Research, Ideas and Innovations in Technology 5.2 (2019). www.IJARIIT.com.

Abstract

The problem considered is cluster analysis with the usage of the ensemble approach. The paper proposes a method for finding optimal weights for the averaged co-association matrix applied to the construction of the ensemble partition. The main idea is to find such weights for which the expectation of ensemble margin takes its maximum value. A latent variable pairwise classification model is used for determining margin characteristics dependent on cluster validity indices. To construct the ensemble partition, we apply a minimum spanning tree found on the averaged co-association matrix as an adjacency matrix. The efficiency of the method is confirmed by Monte-Carlo simulations with artificial data sets.