A comprehensive analysis of twin support vector machines in remote sensing image classification

Recently, a supervised classifier called twin support vector machines (twin-SVM) has been introduced, and it has been compared to classical support vector machines (SVM) on UCI dataset in terms of classification performance. As a result of the studies, it has been stated that twin support vector machines provide higher classification performance compared to SVM. The main advantage of using twin-SVM is its lower computational complexity than classical SVM. In the context of this work, twin-SVM will be firstly applied to remote sensing image classification, and its performance will be analyzed in detail in comparison to SVM. The performance of the method will be evaluated with some criteria such as the sensitivity analysis of model selection, effects of number of training samples to the classification performance, analysis of nonlinear twin-SVM methods with different type of kernels and effects of feature selection to the performance. All the analysis will be conducted with some benchmark dataset frequently used in the remote sensing literature.