Genetic Algorithm Based Deep Learning System for Alzheimer’s Disease Classification

Gowsikraja Palanisamy

Genetic Algorithm Based Deep Learning System for Alzheimer’s Disease Classification

Author(s)	Mr. Gowsikraja Palanisamy
Country	India
Abstract	Alzheimer’s Disease is a problem with the brain that gets worse as time goes on. It affects how people remember things think and understand things. It is really important to know what stage Alzheimer’s Disease is, at so that doctors can give the kind of care and treatment. This project uses computers to look at pictures of the brain from MRI machines to put people into four groups: people who do not have dementia, people who have mild dementia, people who have mild dementia and people who have moderate dementia. The system uses ResNet18, ResNet50 and Vision Transformer models. It also uses a Genetic Algorithm. This algorithm helps to optimize some things like the learning rate the batch size, the weight decay and the model selection, for the ResNet18, ResNet50 and Vision Transformer models. The system really relies on these models, including ResNet18, ResNet50 and Vision Transformer models to get the results. The MRI images are changed to make the model work better with pictures. We tried a lot of things. Found that using ResNet based architectures works the best. We trained these architectures times. The system we made got it 97.78 percent of the time and had a weighted F1-score of 0.9777, which is really good. This is especially true for people, with dementia. It is still hard to tell when someone has Very Mild Dementia. The study is really about Alzheimer’s disease classification. It shows that using learning and optimization techniques together makes Alzheimer’s disease classification more accurate and reliable. This is news for people who are trying to detect Alzheimer’s disease. The people who did the study think that they can make it even better, by using biomarkers to help find the disease early on. Alzheimer’s disease classification is what they are trying to improve.
Keywords	Alzheimer’s disease, MRI, deep learning, ResNet, Vision Transformer, Genetic Algorithm, hyperparameter optimization, dementia classification, medical image analysis.
Field	Medical / Pharmacy
Published In	Volume 17, Issue 2, April-June 2026
Published On	2026-05-20

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 17 Isu 2 Cover Page Vol 17 Isu 1 Cover Page Vol 16 Isu 4

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Genetic Algorithm Based Deep Learning System for Alzheimer’s Disease Classification

Share this