EEG Based Brain Imaging Analysis for Alzheimer’s Disease Classification Using Machine Learning Techniques

Abstract

Electroencephalography (EEG) is a widely used non-invasive technique for capturing electrical activity in the brain, providing critical insights for diagnosing neurological disorders such as Alzheimer’s disease. However, EEG signals are often affected by ocular artifacts (OAs) caused by eye movements and blinking, which overlap with brain signals, leading to potential misclassification. This study presents an enhanced machine learning-based approach for Alzheimer’s disease classification using EEG-based brain imaging analysis. The proposed methodology follows a two-step process: first, ocular artifacts are detected and removed using a combination of Independent Component Analysis (ICA) and Discrete Wavelet Transform (DWT), optimized with a tailored wavelet function to improve signal clarity. In the second step, a deep learning-based modified Gated Recurrent Unit (GRU) model is employed to classify Alzheimer's disease. Experimental results demonstrate that preprocessing EEG signals significantly enhances classification accuracy, achieving a 99.50% accuracy rate along with improved precision, recall, and F1-score metrics. The proposed GRU model proves highly effective in EEG-based Alzheimer’s disease classification, showcasing its potential for robust medical signal processing and applications in Brain-Computer Interface (BCI) systems.