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

Abstract

Neurodegenerative disorders like Alzheimer's disease (AD) are irreversible and show atrophies in the area of the cerebral cortex of brain. AD leads to loss of memory and other cognitive impairments. The AD subjects are evaluated based on magnetic resonance imaging scans. The data may have the problem of class imbalance, noise and outliers which is a great challenge for classification. Support vector machines and twin support vector machine-based classifiers may not effectively deal with these problems as both these models assume that all the samples are equally important for the separating hyperplane. To overcome these issues, we propose intuitionistic fuzzy least square twin support vector machine for class imbalance problems (IFLSTSVM) and class specific-IFLSTSVM (CS-IFLSTSVM). To minimize the effects of class imbalance, the samples are appropriately weighted to minimize their effect on the optimal hyperplane. Moreover, we use intuitionistic fuzzy scores to overcome the issues of noise and outliers. Intuitionistic fuzzy score values generate appropriate weights by considering both the distance of the samples from the class centroid as well as the heterogeneity of the samples. The proposed models IFLSTSVM and CS-IFLSTSVM are efficient as they need to solve a system of linear equations. In Alzheimer's disease diagnosis, the proposed IFLSTSVM and CS-IFLSTSVM models showed better performance in MCI_vs_AD and CN_vs_MCI cases, respectively. Moreover, the proposed models showed better performance in the diagnosis of breast cancer classification. The statistical analysis carried out over KEEL and UCI data leads to the superiority of the proposed models. The source code of the proposed model is available at https://github.com/mtanveer1/Diagnosis-of-Alzheimer-s-disease-via-Intuitionistic-fuzzy-least-squares-twin-SVM. © 2023 Elsevier B.V.