Alzheimer detection using Group Grey Wolf Optimization based features with convolutional classifier. (July 2019)

• Record Type: Journal Article
• Authors: K, Shankar; S.K., Lakshmanaprabu; Khanna, Ashish; Tanwar, Sudeep; Rodrigues, Joel J.P.C.; Roy, Nihar Ranjan
• Is Part Of: Computers & electrical engineering. Volume 77(2019)
• Page Start: 230
• Page End: 243
• Publication Date: 2019-07
• Subjects: Alzheimer's disease -- Classification -- Feature extraction -- Group Grey Wolf Optimization -- Magnetic resonance imaging -- Optimization; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2019.06.001
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: A novel model for Alzheimer detection based on the brain image analysis. Group Grey Wolf Optimization technique is used to increase the detection performance using Decision Tree, K-Nearest Neighbor, and Convolutional Neural Network classifiers. Achieved 96.23% of accuracy for the accurate detection of Alzheimer disease. Abstract: Alzheimer Detection (AD) is one of the most common memory depletion diseases that occurs at an older age and is also, a widely recognized type of dementia. In this paper, we propose a novel model for AD with Brain Image Analysis (BIA). Initially, the image database is considered for the removal of the unwanted region. Then an intermediate output is sent to extract the considerable features such as, texture, histogram, and scale-invariant transform from the magnetic resonance images of the brain. The Group Grey Wolf Optimization (GGWO) technique is used to increase the detection performance using Decision Tree, K-Nearest Neighbor, and Convolutional Neural Network classifiers. These are used to identify the reduced set of useful features without degrading the performance. The proposed approach achieved 96.23% of accuracy for the detection of Alzheimer disease, in comparison to the other competitive schemes in the existing literature.