An Improvement Text Clustering Algorithm Based on Ant Colony

Ant colony clustering was first proposed by Deneubourg in 1990, it is a bionic clustering method and has been widely used in cluster analysis. In this paper, an ant colony clustering algorithm based on appropriate retention of the elites is presented. Based on the general ant colony clustering algorithm, the mechanism to retain the elites is introduced, in each of the iterative algorithm always retain a certain number excellent solution into the next cycle, with a view to improving the performance of algorithm. In order to verify the effectiveness of the algorithm, a text data set judged by two external evaluation indicators is selected, the experimental results show that the new algorithm can effectively improve the performance.