Weighted Least Square - Support Vector Machine

Abstract

In binary classification problems, two classes of data seem to be different from each other. It is expected to be more complicated due to the clusters in each class also tend to be different. Traditional algorithms as Support Vector Machine (SVM), Twin Support Vector Machine (TSVM), or Least Square Twin Support Vector Machine (LSTSVM) cannot sufficiently exploit structural information with cluster granularity of the data, cause limitation in the ability to detect data trends. Structural Twin Support Vector Machine (S-TSVM) sufficiently exploits structural information with cluster granularity for learning a represented hyperplane. Therefore, the ability to describe the data of S-TSVM is better than that of TSVM and LSTSVM. However, for the datasets where each class consists of clusters of different trends, the S-TSVM’s ability to describe data seems restricted. Besides, the training time of S-TSVM has not been improved compared to TSVM. This paper proposes a new Weighted Least Square - Support Vector Machine (called WLS-SVM) for binary classification problems with a clusters-vs-class strategy. Experimental results show that WLS-SVM could describe the tendency of the distribution of cluster information. Furthermore, the WLS-SVM training time is faster than that of S-TSVM and TSVM, and the WLS-SVM accuracy is better than LSTSVM and TSVM in most cases.