Hybrid Machine Learning Model Using Particle Swarm Optimization for Effectual Diagnosis of Alzheimer's Disease from Handwriting
R. Subha, B R Nayana, M Selvadass
Abstract
Alzheimer's disease (AD) is a condition that weakens nerves, impairs cognitive and memory functions, and eventually results in amnesia. An improved approach for early diagnosis of AD is crucial to identify and control the decline as they advance. Machine Learning (ML) approaches have proved successful in intelligently identifying patterns in the data to categorize it into different classes. Hybrid ML models with Swarm Intelligence (SI) based feature selection will result in robust and efficient model for diagnosis and prediction. In this work, Particle Swarm Optimization has been used for feature selection to identify the best performing feature dimension resulting in a hybrid ML model with good performance. Six classifier models have been explored in the hybrid ML.