COVID-19 Diagnosis in Chest X-rays Using Deep Learning and Majority Voting

The COVID-19 disease has spread all over the world, representing an intriguing challenge for humanity as a whole. efficient diagnosis of humans infected by still remains increasing need worldwide. chest X-ray imagery represents, among others, one attractive means to detect cases efficiently. Many studies have reported efficiency using deep learning classifiers in diagnosing from images. They conducted several comparisons subset identify most accurate. In this paper, we investigate potential combination state-of-the-art achieving highest possible accuracy detection X-ray. For purpose, comprehensive comparison study 16 classifiers. To best our knowledge, is first considering number This paper’s innovation lies methodology that followed develop inference system allows us with high accuracy. consists three steps: (1) comparative between classifiers; (2) different ensemble classification techniques, including hard/soft majority, weighted voting, Support Vector Machine, and Random Forest; (3) finding models techniques lead confidence on classes. We found Majority Voting approach adequate strategy adopt general task may achieve average up 99.314%.