GPU accelerated genetic clustering

  • Authors:
  • Pavel Krömer;Jan Platoš;Václav Snášel

  • Affiliations:
  • Department of Computer Science, VŠB-Technical University of Ostrava, Ostrava-Poruba, Czech Republic, IT4Innovations, Ostrava-Poruba, Czech Republic;Department of Computer Science, VŠB-Technical University of Ostrava, Ostrava-Poruba, Czech Republic, IT4Innovations, Ostrava-Poruba, Czech Republic;Department of Computer Science, VŠB-Technical University of Ostrava, Ostrava-Poruba, Czech Republic, IT4Innovations, Ostrava-Poruba, Czech Republic

  • Venue:
  • SEAL'12 Proceedings of the 9th international conference on Simulated Evolution and Learning
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Genetic and evolutionary algorithms have been used to find clusters in data with success. Unfortunately, evolutionary clustering suffers from the high computational costs when it comes to fitness function evaluation. The GPU computing is a recent programming and development paradigm introducing high performance parallel computing to general audience. This study presents a design, implementation, and evaluation of a genetic algorithm for density based clustering for the nVidia CUDA platform.