<![CDATA[Alzheimer's Disease (AD), is a neurodegenerative condition that develops slowly and generally occurs in older people. The aim of this research is to optimize Deep Learning models so that they can process complex brain imaging data efficiently. The method used involves the use of a CNN (Convolutional Neural Network) network which is trained with a dataset of brain MRI images that have been processed and divided into subsets for training, validation and testing. The data used was taken from the Kaggle platform and processed using augmentation techniques with `ImageDataGenerator`. The research results show that the implemented model is able to achieve high accuracy in detecting structural and functional changes in the brain related to Alzheimer's. The loss and accuracy curves monitored during the training process show a positive trend, with accuracy reaching over 96% in just seven epochs. The main conclusion of this research is that Deep Learning technology has great potential in early detection of Alzheimer's disease, enabling earlier and more effective interventions to prevent or slow the progression of this disease, as well as improving the quality of life of individuals at risk.]]>
Copyrights © 2024
