Optimized Machine Learning Model for Alzheimer’s Disease Classification

This paper presents an optimized machine learning model for Alzheimer’s disease classification, leveraging nature-inspired algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), and Hunger Search Method (HSM). These algorithms are utilized to reduce data dimensionality while preserving crucial features, ensuring the integrity of the dataset. We then investigate the efficacy of neural network models, including Deep Neural Networks (DNN) and stacked ensemble models, in classifying Alzheimer’s disease. Our experimental results demonstrate that this approach significantly enhances classification accuracy compared to conventional methods, offering a promising direction for improved diagnostic tools in Alzheimer’s research. Around 97% classification accuracy is obtained using stacked model with optimized features extracted using HSM.