Comparative Analysis of Support Vector Machine: Employing Various Optimization Algorithms

被引：0

作者：

Khalid, M. A. R. ^{[1
]}

Alwaqdani, Majid ^{[2
]}

Farquad, M. A. H. ^{[2
]}

机构：

[1] Jawaharlal Nehru Tech Univ, Coll Engn, Comp Sci & Informat Engn, Hyderabad, Andhra Pradesh, India

[2] Islamic Univ Madinah, Fac Comp & Informat Syst, Madinah Al Munawwara, Saudi Arabia

来源：

2015 14TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY (ICIT 2015) | 2015年

关键词：

Support Vector Machine; EvoSVM; PSOSVM; Breast Cancer; Bankruptcy Prediction; CLASSIFICATION;

D O I：

10.1109/ICIT.2015.52

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Support Vector Machines (SVMs) have proved to be good alternative compared to other machine learning techniques specifically for classification problems. The use of optimization methodologies plays a central role in finding solutions of SVMs. In this paper, we present a comparative analysis of study of standard SVM implementing Quadratic Programming (QP) in comparison with SVM employing Evolutionary Algorithm (EvoSVM) and Particle Swam Optimization (PSOSVM) to solve the quadratic optimization problem of SVM. Two class classification problems pertaining to Wisconson Breast Cancer and Bankruptcy prediction using Spanish Banks, Turkish Banks and US Banks data have been analyzed in this study. Based on the datasets used in this study and the results yielded, it is observed that standard SVM outperform other variants of SVM.

引用

页码：171 / 174

页数：4