Enhancing SVM with Visualization

Authors: ThanhNghi Do François Poulet

Publish Date: 2004/10/2

Volume: , Issue: , Pages: 183-194

PDF Link

Abstract

Understanding the result produced by a datamining algorithm is as important as the accuracy Unfortunately support vector machine SVM algorithms provide only the support vectors used as “black box” to efficiently classify the data with a good accuracy This paper presents a cooperative approach using SVM algorithms and visualization methods to gain insight into a model construction task with SVM algorithms We show how the user can interactively use cooperative tools to support the construction of SVM models and interpret them A preprocessing step is also used for dealing with large datasets The experimental results on Delve Statlog UCI and biomedical datasets show that our cooperative tool is comparable to the automatic LibSVM algorithm but the user has a better understanding of the obtained model

Keywords: