TY - JOUR AU - imad, Muhammad AU - Khan, Naveed AU - Ullah, Farhat AU - Abul Hassan, Muhammad AU - Hussain, Adnan AU - Faiza , PY - 2020/10/06 Y2 - 2024/03/28 TI - COVID-19 Classification based on Chest X-Ray Images Using Machine Learning Techniques JF - Journal of Computer Science and Technology Studies JA - JCSTS VL - 2 IS - 2 SE - Research Article DO - UR - https://al-kindipublisher.com/index.php/jcsts/article/view/531 SP - 01-11 AB - <p>The coronavirus (COVID-19) pandemic rapidly spread from the infected person who has a severe health problem around the world. World Health Organization (WHO) has identified the coronavirus as a global pandemic issue. The infected person has a severe respiratory issue that needs to be treated in an intensive health care unit. The detection of COVID-19 using machine learning techniques will help in healthcare system about fast recovery of patients worldwide. One of the crucial steps is to detect these pandemic diseases by predicting whether COVID19 infects the human body or not. The investigation is carried out by analyzing Chest X-ray images to diagnose the patients. In this study, we have presented a method to efficiently classify the&nbsp;&nbsp; COVID-19 infected patients and normally based on chest X-ray radiography using Machine Learning techniques. The proposed system involves pre-processing, feature extraction, and classification. The image is pre-processed to improve the contrast enhancement. The Histogram of Oriented Gradients (HOG) is used to extract the discriminant features. Finally, In the classification step, five different Machine Learning algorithms, such as Support Vector Machine (SVM), K-Nearest Neighbors, Random Forest, Naïve Bayes algorithm, and Decision Tree) are used to efficiently classify between COVID-19 and normal chest X-ray images. The different metric measures like accuracy, precision, recall, specificity and F1are used to analyze the results. The result evaluation shows that SVM provides the highest accuracy of 96% among the other four classifiers (K-Nearest Neighbors and Random Forest achieved 92% accuracy, 90% accuracy of Naïve Bayes algorithm and 82% accuracy of Decision Tree).</p> ER -