An aggregated clustering approach using multi-ant colonies algorithms

This paper presents a multi-ant colonies approach for clustering data that consists of some parallel and independent ant colonies and a queen ant agent. Each ant colony process takes different types of ants moving speed and different versions of the probability conversion function to generate various clustering results with an ant-based clustering algorithm. These results are sent to the queen ant agent and combined by a hypergraph model to calculate a new similarity matrix. The new similarity matrix is returned back to each ant colony process to re-cluster the data using the new information. Experimental evaluation shows that the average performance of the aggregated multi-ant colonies algorithms outperforms that of the single ant-based clustering algorithm and the popular K-means algorithm. The result also shows that the lowest outliers strategy for selecting the current data set has the best performance quality. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.