Title :
Constrained ant clustering
Author :
Xu, Xiao-Hua ; Pan, Zhou-Jin ; He, Ping ; Chen, Ling
Author_Institution :
Dept. of Comput. Sci. & Eng., Yangzhou Univ., Yangzhou, China
Abstract :
By simulating the clustering behavior of the real-world ant colonies, we propose in this paper a constrained ant clustering algorithm based on random walk to deal with the constrained clustering problems with pairwise must-link and cannot-link constraints. Experimental results show that our approach is more effective on both synthetic datasets and UCI datasets compared with the cop-kmeans algorithm and ant-based clustering algorithm.
Keywords :
data analysis; pattern clustering; UCI datasets; clustering behavior; constrained ant clustering; constrained clustering problems; cop-k means algorithm; data analysis; synthetic datasets; Algorithm design and analysis; Clustering algorithms; Cybernetics; Educational institutions; Machine learning; Machine learning algorithms; Particle swarm optimization; Ant clustering; Constrained clustering; Random walk;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2011 International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-1-4577-0305-8
DOI :
10.1109/ICMLC.2011.6016967
