Locality preserving projection least squares twin support vector machine for pattern classification

During the last few years, multiple surface classification algorithms, such as twin support vector machine (TWSVM), least squares twin support vector machine (LSTSVM) and least squares projection twin support vector machine (LSPTSVM), have attracted much attention. However, these algorithms did not consider the local geometrical structure information of training samples. To alleviate this problem, in this paper, a locality preserving projection least squares twin support vector machine (LPPLSTSVM) is presented by introducing the basic idea of the locality preserving projection into LSPTSVM. This method not only inherits the ability of TWSVM, LSTSVM and LSPTSVM for pattern classification, but also fully considers the local geometrical structure between samples and shows the local underlying discriminatory information. Experimental results conducted on both synthetic and real-world datasets illustrate the effectiveness of the proposed LPPLSTSVM method.