Publication Details

PSO-based Constrained Imbalanced Data Classification

HLOSTA, M.; STRÍŽ, R.; ZENDULKA, J.; HRUŠKA, T. PSO-based Constrained Imbalanced Data Classification. Proceedings of the Twelth International Conference on Informatics INFORMATICS'2013. Spišská Nová Ves: The University of Technology Košice, 2013. p. 234-239. ISBN: 978-80-8143-127-2.
Czech title
Klasifikace nevyvážených dat s omezením založená na PSO
Type
conference paper
Language
English
Authors
Hlosta Martin, Ing., Ph.D.
Stríž Rostislav, Ing.
Zendulka Jaroslav, doc. Ing., CSc. (UIFS)
Hruška Tomáš, prof. Ing., CSc. (DIFS)
Keywords

Data mining, imbalance classification, constraints, PSO, Genetic Algorithm

Abstract

The paper deals with classification of highly imbalanced data with accuracy constraints for the minority class. We solve this problem by our proposed meta-learning method that uses cost-sensitive logistic regression to generate initial candidate models. These models can be used as an initial solutions for various optimization algorithms. This paper is aimed for using Particle Swarm Optimization (PSO) to handle the constrained imbalanced classification problem. Experiments, comparing with Genetic Algorithm (GA), show that the swarm intelligence approach is suitable for this problem and outperforms GA.

Published
2013
Pages
234–239
Proceedings
Proceedings of the Twelth International Conference on Informatics INFORMATICS'2013
ISBN
978-80-8143-127-2
Publisher
The University of Technology Košice
Place
Spišská Nová Ves
BibTeX 
@inproceedings{BUT103558,
  author="Martin {Hlosta} and Rostislav {Stríž} and Jaroslav {Zendulka} and Tomáš {Hruška}",
  title="PSO-based Constrained Imbalanced Data Classification",
  booktitle="Proceedings of the Twelth International Conference on Informatics INFORMATICS'2013",
  year="2013",
  pages="234--239",
  publisher="The University of Technology Košice",
  address="Spišská Nová Ves",
  isbn="978-80-8143-127-2",
  url="https://www.fit.vut.cz/research/publication/10438/"
}
Back to top