Open AccessParticle swarm optimization for linear support vector machines based classifier selection
Author(s) -
Gintautas Garšva,
Paulius Danėnas
Publication year - 2014
Publication title -
nonlinear analysis
Language(s) - English
Resource type - Journals
eISSN - 2335-8963
pISSN - 1392-5113
DOI - 10.15388/na.2014.1.2
Subject(s) - metaheuristic , particle swarm optimization , classifier (uml) , computer science , support vector machine , multi swarm optimization , solver , selection (genetic algorithm) , mathematical optimization , artificial intelligence , linear classifier , heuristics , optimization problem , parallel metaheuristic , machine learning , algorithm , mathematics
Particle swarm optimization is a metaheuristic technique widely applied to solve various optimization problems as well as parameter selection problems for various classification techniques. This paper presents an approach for linear support vector machines classifier optimization combining its selection from a family of similar classifiers with parameter optimization. Experimental results indicate that proposed heuristics can help obtain competitive or even better results compared to similar techniques and approaches and can be used as a solver for various classification tasks.