Alzheimer's Disease Diagnosis Based on Moth Flame Optimization

• Published in: Genetic and Evolutionary Computing Vol. 536; pp. 298 - 305
• Main Authors: Sayed, Gehad Ismail, Hassanien, Aboul Ella, Nassef, Tamer M., Pan, Jeng-Shyang
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2016; Springer International Publishing
• Series: Advances in Intelligent Systems and Computing
• Subjects: Alzheimer’s disease; Artificial intelligence; Features selection; Genetic algorithm (GA); Grey wolf optimizer (GWO); Moth flame optimization (MFO); Swarm optimization algorithms
• ISBN: 3319484893; 9783319484891
• ISSN: 2194-5357; 2194-5365
• DOI: 10.1007/978-3-319-48490-7_35

Alzheimer’s disease (AD) is the most cause of dementia affecting senior’s age staring from 65 and over. The standard criteria for detecting AD is tedious and time consuming. In this paper, an automatic system for AD diagnosis is proposed. A principle of moth-flame optimization is used as features selection algorithm and support vector machine classifier is adopted to distinguish three kinds of classes including Normal, AD and Cognitive Impairment. The main objective of this paper is to aid physicians in detecting AD and to compare two different anatomical views of the brain and identify the best representative one. The performance of this algorithm is evaluated and compared with grey wolf optimizer and genetic algorithm. A benchmark dataset consists of 20 patients for each class is adopted. The experimental results show the efficiency of the proposed system in terms of Recall, Precision, Accuracy and F-Score.