KNN weighted reduced universum twin SVM for class imbalance learning

Highlights：

• To incorporate the local neighbourhood information, K nearest neighbourbased weights are used in the proposed KWRUTSVM-CIL.

• Unlike RUTSVM-CIL, UTSVM, TSVM and FTWSVM models which implement the empirical risk minimization principle, the proposed KWRUTSVM-CIL model implements the structural risk minimization principle.

• Similar to RUTSVM-CIL, the proposed KWRUTSVM-CIL model incorporates prior information about the data (universum data) to handle the class imbalance problem.

• The matrices appearing in the Wolfe dual of the proposed KWRUTSVM-CIL are positive definite, while as the matrices in the Wolfe dual of RUTSVM-CIL, UTSVM, TSVM and FTWSVM are positive semi-definite.

• Experimental results and statistical analysis show the efficacy of the proposed KWRUTSVM-CIL model. As an application, we use the proposed KWRUTSVM-CIL model for the classification of Alzheimer’s disease and breast cancer subjects.

摘要

•To incorporate the local neighbourhood information, K nearest neighbourbased weights are used in the proposed KWRUTSVM-CIL.•Unlike RUTSVM-CIL, UTSVM, TSVM and FTWSVM models which implement the empirical risk minimization principle, the proposed KWRUTSVM-CIL model implements the structural risk minimization principle.•Similar to RUTSVM-CIL, the proposed KWRUTSVM-CIL model incorporates prior information about the data (universum data) to handle the class imbalance problem.•The matrices appearing in the Wolfe dual of the proposed KWRUTSVM-CIL are positive definite, while as the matrices in the Wolfe dual of RUTSVM-CIL, UTSVM, TSVM and FTWSVM are positive semi-definite.•Experimental results and statistical analysis show the efficacy of the proposed KWRUTSVM-CIL model. As an application, we use the proposed KWRUTSVM-CIL model for the classification of Alzheimer’s disease and breast cancer subjects.