A Survey on Various Approaches for Support Vector Machine Based Engineering Applications

Abstract

Support vector machines describe a system that uses a feature space with a hypothesis space of linear functions that is trained using various learning algorithms from optimization theory. This paper presents a brief introduction to SVM, and a survey with different methods applied for obtaining results using classifiers. The aim is to classify and obtain results for different classes of points with different SVM classifiers and to justify the results using various methods like Gaussian Kernel, Custom Kernel, Cross Validate functioning of SVM classifiers through Posterior Probability Regions for SVM classification models with various types of data.