The Diagnosis of Alzheimer's Disease using EEG Signals

Abstract

Alzheimer is a common and significant neurological disorder worldwide, typically associated with age-related dementia. Alzheimer's patients exhibit slower brain activities compared to healthy individuals, and the most prominent symptom of the disease is the impairment of cognitive functions. Early diagnosis of Alzheimer's is crucial to prevent the rapid progression of the disease. In this study, the feasibility of using electroencephalography (EEG) signals, a non-invasive, cost-effective, and objective method, to facilitate the diagnosis of Alzheimer's Disease (AD) was investigated. The study utilized EEG signals from both Alzheimer's patients and healthy individuals, which were made publicly available by Florida State University. Preprocessing was applied to the EEG signals to eliminate existing noise. Subsequently, a total of 34 various features in the time and frequency domains, such as entropy, Hjorth parameters, etc., were extracted from the EEG signals for the purpose of Alzheimer's diagnosis. Machine learning techniques, including decision trees (DT), support vector machines (SVM), and artificial neural networks (ANN), were applied to classify the data, and success rates for Alzheimer's detection were achieved.