Aarhus University Seal / Aarhus Universitets segl

Solving Large Clustering Problems with Meta-Heuristic Search

Research output: Contribution to conferencePaperResearchpeer-review

  • CORAL - Centre for Operations Research Applications in Logistics
  • Department of Business Studies
In Clustering Problems, groups of similar subjects are to be retrieved from data sets. In this paper, Clustering Problems with the frequently used Minimum Sum-of-Squares Criterion are solved using meta-heuristic search. Tabu search has proved to be a successful methodology for solving optimization problems, but applications to large clustering problems are rare. The simulated annealing heuristic has mainly been applied to relatively small instances. In this paper, we implement tabu search and simulated annealing approaches and compare them to the commonly used k-means approach. We find that the meta-heuristic search methods are able to return solutions of very high quality.
Original languageEnglish
Publication year2009
Publication statusPublished - 2009
EventMIC 2009 - VIII Metaheuristic International Conference - Hamburg, Germany
Duration: 13 Jul 200916 Jul 2009


ConferenceMIC 2009 - VIII Metaheuristic International Conference

See relations at Aarhus University Citationformats

ID: 219487