|
Title:
|
SELF-TUNING CLUSTERING USING THE INFORMATION GEOMETRY TECHNIQUE |
|
Author(s):
|
Renata Avros, Zeev Barzily, Zeev Volkovich |
|
ISBN:
|
978-972-8939-93-9 |
|
Editors:
|
António Palma dos Reis and Ajith P. Abraham |
|
Year:
|
2013 |
|
Edition:
|
Single |
|
Keywords:
|
Clustering, Cluster validation, Distance learning. |
|
Type:
|
Full Paper |
|
First Page:
|
13 |
|
Last Page:
|
20 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
In this paper a new adaptive clustering algorithm is presented. This method incorporates metric learning attitude based on the information geometry methodology and uses the pair-wise constraints created at each step in order to refine the clustering solution. Individual distance weight matrices of clusters are calculated at relying on the previously obtained information with reference to the desired partition. The weighed distance matrices obtained as a collateral outcome of the partitioning process are considered as a new cluster quality characteristic. Numerical experiments demonstrate the potential of such an approach in clustering and in predicting the true number of clusters. |
|
|
|
|
|
|
