Klasifikasi Pneumonia Chest X-Ray Dengan Arsitektur Inceptionresnet-V2

Abstract

In the last century, the use utilization of machine learning, especially the Convolution Neural Network (CNN)has helped the world of health (medicine). Through action research on image datasets, CNN was successful and able to show classification or grouping based on the same characteristics and properties on unlabeled images with higher accuracy and faster than other machine learning methods. This study aims to optimize two CNN architectures (Inception Res Net-V2, and Mobile Net-V2) to classify Covid-19 disease, by training 4000 Chest x-ray image datasets. The accuracy test results from InceptionResNet- V2 yield 98%, and MobileNet-V2 yield 93%. with the precision of each class of the CNN Inception Rest Net-V2 architecture is Covid (99%), Lung Opacity (97%), Normal (99%), Viral_Pneumonia (99%).