Year: 2024
Type: conference-paper
Abstract: Alzheimer’s Disease is an incurable cognitive disease that affects thousands of people globally. While some diagnosis methods exist for Alzheimer’s Disease, many of these methods can’t catch Alzheimer’s in it’s earlier stages. Recently, researchers have considered the use of Electroencephalogram (EEG) technology for the diagnosis of Alzheimer’s. EEG technology is a noninvasive method of recording the brain’s electrical signals, and EEG data has shown differences between patients with and without Alzheimer’s. In the past, Artificial Neural Networks have been used for the prediction of Alzheimer’s from EEG data, but these prediction models can sometimes contain false positive diagnoses. In this study, we aim to compare losses between Artificial Neural Networks and Kolmogorov-Arnold Networks between multiple types of Epochs, Learning Rates, and Nodes. We have found that, throughout these different parameters, ANNs are more accurate in predicting Alzheimer’s Disease from EEG signals.
Authors: Akshay Sunkara, Sriram Sattiraju, Aakarshan Kumar, Zaryab Kanjiani, Himesh Anumala
Institution: University of North Texas
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W4409019890