International Conference on Advanced Technologies, Computer Engineering and Science

A Clustering Ranking Based Multiobjective Evolutionary Algorithm

Erdi Dasdemir B. Y. ÖZCAN

Abstract

We propose a new clustering ranking based multiobjective evolutionary algorithm. The algorithm uses decision maker’s preferences to reduce the search space and obtain a final set of preferred Pareto-optimal solutions. A new clustering ranking operator using Hierarchical Clustering on Principle Components (HCPC) and K-means methods is developed. We also develop a new crossover operator. The algorithm is implemented on several problems. The work is still in progress.



Conference
International Conference on Advanced Technologies, Computer Engineering and Science
Keywords
Multiobjective evolutionary algorithms heuristic search clustering ranking crossover

Language
English

Subject
Computer Science

Full Paper (PDF)

411 views
304 downloads