International Journal of Electrical and Computer Engineering (IJECE) Vol. 14, No. 3, June 2024, pp. 2602~2615 ISSN: 2088-8708, DOI: 10.11591/ijece.v14i3.pp2602-2615  2602 Journal homepage: http://ijece.iaescore.com Analyzing electroencephalograph signals for early Alzheimer’s disease detection: deep learning vs. traditional machine learning approaches Sachin M. Elgandelwar 1 , Vinayak Bairagi 1 , Shridevi S. Vasekar 2 , Aziz Nanthaamornphong 3 , Priyanka Tupe-Waghmare 4 1 Department of Electronics and Telecommunication Engineering, AISSMS Institute of Information Technology, Pune, India 2 Department of Electronics and Telecommunication Engineering, Pune Institute of Computer Technology, Pune, India 3 College of Computing, Prince of Songkla University, Phuket Campus, Phuket, Thailand 4 Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, India Article Info ABSTRACT Article history: Received Oct 15, 2023 Revised Jan 24, 2024 Accepted Jan 25, 2024 Alzheimer’s disease (AD) stands as a progressive neurodegenerative disorder with a significant global public health impact. It is imperative to establish early and accurate diagnoses of AD to facilitate effective interventions and treatments. Recent years have witnessed the emergence of machine learning (ML) and deep learning (DL) techniques, displaying promise in various medical domains, including AD diagnosis. This study undertakes a comprehensive contrast between conventional machine learning methods and advanced deep learning strategies for early AD diagnosis. Conventional ML algorithms like support vector machines, decision trees, and K nearest neighbor have been extensively employed for AD diagnosis through relevant feature extraction from heterogeneous data sources. Conversely, deep learning techniques such as multilayer perceptron (MLP) and convolutional neural networks (CNNs) have demonstrated exceptional aptitude in autonomously uncovering intricate patterns and representations from unprocessed data like EEG data. The findings reveal that while traditional ML methods may perform adequately with limited data, deep learning techniques excel when ample data is available, showcasing their potential for early and precise AD diagnosis. In conclusion, this research paper contributes to the ongoing discourse surrounding the choice of appropriate methodologies for early Alzheimer’s disease diagnosis. Keywords: Alzheimer’s disease Deep learning Dementia Electroencephalograph signal Machine learning Neurodegenerative This is an open access article under the CC BY-SA license. Corresponding Author: Aziz Nanthaamornphong College of Computing, Prince of Songkla University, Phuket Campus Phuket 83120, Thailand Email: aziz.n@phuket.psu.ac.th 1. INTRODUCTION In the field of medical diagnostics, there has been a significant focus on the early and accurate detection of Alzheimer disease (AD) through extensive research and innovation. This pursuit has given rise to two closely related and prominent areas of study: deep learning (DL) and machine learning (ML). These approaches offer unique methodologies for analyzing intricate patterns within complex datasets and have shown great potential in facilitating the early diagnosis of AD [1], [2]. Machine learning, which falls under the umbrella of artificial intelligence, encompasses a variety of algorithms that enable computers to learn from data without explicit programming. This technique has been effectively utilized to uncover complex