Diagnosis of Alzheimer's disease via Intuitionistic fuzzy least squares twin SVM

M. A. Ganaie, Anuradha Kumari, Anouck Girard, Josephine Kasa-Vubu, M. Tanveer

Abstract: Highlights•To handle the CIL issue, training data are assigned weights based on imbalance ratio.•The regularization term improves the generalization performance of proposed models.•The proposed models solve system of linear equations. Hence, it is very efficient.•The weights reduce the impact of noise/outliers in classifying imbalanced data.•The results on biomedical and UCI data show the superiority of proposed models.