Open AccessParameters Optimization and Application of SVM Based on PCA-Particle Swarm Algorithm
Author(s) -
Qingmi Yang
Publication year - 2019
Publication title -
international journal of scientific research in science, engineering and technology
Language(s) - English
Resource type - Journals
eISSN - 2395-1990
pISSN - 2394-4099
DOI - 10.32628/ijsrset196431
Subject(s) - particle swarm optimization , support vector machine , principal component analysis , computer science , pattern recognition (psychology) , multi swarm optimization , kernel (algebra) , algorithm , generalization , redundancy (engineering) , artificial intelligence , mathematical optimization , mathematics , mathematical analysis , combinatorics , operating system
The parameter optimization of Support Vector Machine (SVM) has been a hot research direction. To improve the optimization rate and classification performance of SVM, the Principal Component Analysis (PCA) - Particle Swarm Optimization (PSO) algorithm was used to optimize the penalty parameters and kernel parameters of SVM. PSO which is to find the optimal solution through continuous iteration combined with PCA that eliminates linear redundancy between data, effectively enhance the generalization ability of the model, reduce the optimization time of parameters, and improve the recognition accuracy. The simulation comparison experiments on 6 UCI datasets illustrate that the excellent performance of the PCA-PSO-SVM model. The results show that the proposed algorithm has higher recognition accuracy and better recognition rate than simple PSO algorithm in the parameter optimization of SVM. It is an effective parameter optimization method.