An assessment of support vector machine kernel parameters using remotely sensed satellite data

Abstract

This paper reviews the comparative performance of Support Vector Machine (SVM) using four different kernels, i.e., Linear, Polynomial, Radial Basis Function (RBF) and Sigmoid. Overall accuracy (OA), Kappa Index Analysis (KIA), Receiver Operating Characteristic (ROC) and Precision (P) have been considered as evaluation parameters in order to assess the predictive accuracy of SVM. Both high resolution QuickBird sensor data and moderate resolution Landsat Enhanced Thematic Mapper Plus (ETM+) remotely sensed satellite data have been used in the investigation. It was observed that SVM with polynomial kernel (SVMP) achieves highest classification accuracy followed by SVM with linear kernel (SVML), SVM with RBF kernel (SVMRBF) and SVM with sigmoid kernel (SVML) while classifying QuickBird data. On the other hand, SVMS achieves highest accuracy followed by SVML, SVMP and SVMRBF in case of Landsat ETM+ data. However, faces SVMS lots of computational expenses in classifying both QuickBird and Landsat ETM+ data as compared to the SVMs with other three kernels. SVMp was found computationally more efficient with satisfactory predicting ability over all the kernels investigated here. Performance of SVM tit was found very sensitive with the training data set and produced inconsistent results when there is a limited number of training data set. However, performance of SVMP kernel was found consistent and not affected by the size of the training data set.