A novel weighted SVM based on theory of belief functions
Weibing Liu, Deqiang Han, Yi Yang · 2017
Support vector machine (SVM) is a popular machine learning method and has been widely applied in many real-world applications. Since SVM is sensitive to noises, fuzzy SVM (FSVM) has been proposed to relieve the over-fitting problem caused by noises through assigning a fuzzy membership to each sample. Then, different samples make different contributions to the learning of classification hyperplane. However, standard fuzzy SVM only concerns on the information within the classes. It can't make full use of the prior information of the samples. Therefore, we propose a new method called weighted SVM based on the theory of belief functions (BFW-SVM). The main idea is to associate the samples with corresponding weights before training according to the theory of belief functions, which can describe the information more detailed. Experiments on benchmark datasets show that our proposed BFW-SVM can handle the classification problems with noises and outliers more effectively.