Comparative Performance Analysis of Machine Learning Classifier for COVID-19 Detection using Chest X-Ray Images

Machine learning is a data analysis method that has been used to solve several problems. Image classification is one of them. During this pandemic caused by the spread of Covid-19, the number of people infected was relatively high. The COVID-19 pandemic has had a severe impact on people’s lives. One of the critical steps for overcoming this pandemic lies in the ability of medical personnel to identify patients who are infected with Covid-19 at an early age. Detecting Covid-19 from patient radiographs may be one of the quickest ways to identify Covid-19 patients. Many researchers have applied machine learning to predict Covid-19. The data are based on chest X-ray images of the patient. In this study, K–Nearest Neighbor (K-NN), Support Vector Machine (SVM), and Convolutional neural network (CNN) methods were used to find the best analytical performance in predicting COVID-19 based on chest X-ray images of the patients. The research results from the three methods used, the performance of the CNN method is the best compared to the other two methods, namely SVM and KNN.