Abstract
Clustering analysis is an important field in data mining, and also one of the current research hotspots in computer science. This paper focus on some classical data clustering algorithms and swarm intelligence, especially ant colony optimization, trying to combine these two kinds of algorithms and improve the efficiency and accuracy of data clustering. This paper proposes a new ant colony optimization data clustering algorithm, named ant colony clustering algorithm with elitist ant and local search (ACC-EAL). This algorithm adopts a new pheromone incremental calculation method, making the distances among the clusters tend to increase, and the clusters get denser. Meanwhile local search provides the ants more opportunity to find optimal solution and the elite ant strategy makes the ants with optimal solutions contribute more to the pheromone increment.
Highlights
Ant system (AS) algorithm is a kind of heuristic bionic evolutionary system based on swarm intelligence, and is proposed by Italian scholar M.Dorigo first to solve the TSP problem[1,2,3,4]
At present some well-studied ant system includes ant optimization algorithm, the Rankbased Version of Ant System proposed by Bullnhemier[7], the ant nest and ant eggs classification model raised by Deneubourg, and the MAX-MIN Ant System (MMAS) by T.Stützle and H.Hoos[8,9], and the Best-Worst Ant System (BWAS) by O.Cordón[10], etc
The step is local search, after which we re-rank the ants according to their new solution, we use the elitist ants to update the pheromone level, the method is adding up the pheromone increment and the amount of volatile, just like follows
Summary
Ant system (AS) algorithm is a kind of heuristic bionic evolutionary system based on swarm intelligence, and is proposed by Italian scholar M.Dorigo first to solve the TSP problem[1,2,3,4]. All these models and algorithms, have made great progress, is still flawed, for example, some models need to set a lot of parameters Another type of clustering algorithms attempts to combine classical clustering algorithm and ant optimization algorithm, such as combining fuzzy c-means clusters and ACO [11], achieved remarkable results. In this paper we proposed an ant colony optimization (ACO) algorithm for the cluster task of data mining. In this task, the goal is to assign each case to one cluster, based on the similarity of the case with others.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
