| dc.description.abstract | Alzheimer's disease is a progressive neurodegenerative disorder that affects millions of people worldwide. It is characterized by a significant decline in cognitive function and memory, which has a major impact on the quality of life of sufferers and their families. Early and accurate diagnosis is essential for proper treatment, but the manual diagnosis process requires time and specialized skills. This research aims to develop an automatic classification system for Alzheimer's disease using Magnetic Resonance Imaging (MRI) images by combining Convolutional Neural Network (CNN) and Support Vector Machine (SVM) methods. The methodology used is web-based system development with hybrid architecture, where CNN is implemented for feature extraction from brain MRI images, while SVM is used as a classifier to classify the presence or absence of Alzheimer's disease. The dataset used consists of 118 brain MRI images taken from Santa Elisabeth Hospital Medan. The system development process includes image preprocessing, feature extraction using CNN, classification using SVM, and system performance evaluation. The test results show that the developed system is able to classify Alzheimer's disease with excellent performance, achieving a precision value of 94.3%, recall 96.3%, f1-score 95%, and accuracy 92%. The high value of these metrics indicates that the CNN-SVM combination is effective in detecting Alzheimer's disease characteristics from MRI images. | en_US |
