<![CDATA[Measles is a contagious disease that is often experienced, especially by children, so it requires early detection to prevent serious complications. This study aims to apply a Convolutional Neural Network (CNN)-based Machine Learning approach to detect measles quickly and accurately. The data used consists of 1,041 skin images (measles and non-measles) obtained from the research dataset. The data is processed through the stages of pre-processing, data augmentation, dataset division (training, validation, testing), model training using the ResNet34 architecture, and performance evaluation with a confusion matrix. The results show that the developed measles detection system has an accuracy of 95%, Precision of 90%, Recall of 100%, and F1-Score of 94.7%. The feasibility test shows that the system is very feasible with a feasibility level of 100% and a user satisfaction level of 100% based on the PSSUQ questionnaire. This study proves that the CNN algorithm with the ResNet34 architecture implemented on the website is able to provide accurate, fast, and effective detection in supporting the early detection of measles.]]>
Copyrights © 2026
