Authors:
H. Panahi
and
R. Tavakkoli-Moghaddam
Affiliation:
Faculty of Engineering, University of Tehran, Iran, Islamic Republic of
Keyword(s):
Clustering problems, Ant colony optimization, Genetic algorithms, Paired comparison test.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Enterprise Information Systems
;
Evolutionary Programming
;
Industrial Applications of Artificial Intelligence
;
Intelligent Agents
;
Internet Technology
;
Web Information Systems and Technologies
Abstract:
This paper presents a hybrid efficient method based on ant colony optimization (ACO) and genetic algorithms (GA) for clustering problems. This proposed method assumes that agents of ACO has life cycle which is variable and changes by a special function. We also apply three local searches on the basis of heuristic rules for the given clustering problem. This proposed method is implemented and tested on two real datasets. Further, its performance is compared with other well-known meta-heuristics, such as ACO, GA, simulated annealing (SA), and tabu search (TS). At last, paired comparison t-test is also applied to proof the efficiency of our proposed method. The associated output gives very encouraging results; however, the proposed method needs longer time to proceed.