TY - JOUR AU - Singh, Kuldeep AU - Kaur, Jaspreet PY - 2022/05/27 Y2 - 2024/03/29 TI - A CNN Approach to Identify COVID-19 Patients among Patients with Pneumonia JF - International Journal of Intelligent Systems and Applications in Engineering JA - Int J Intell Syst Appl Eng VL - 10 IS - 2 SE - Research Article DO - UR - https://ijisae.org/index.php/IJISAE/article/view/1683 SP - 166-169 AB - <p><em>Due to COVID-19 pandemic, the healthcare system has been collapsed worldwide. Keeping in view of the shortage of healthcare services during these times, the automated identification of COVID patients among other non-COVID patients suffering from pneumonia is an essential task. It will help the medical professionals for speedy diagnosis of the patients with appropriate treatments. Therefore, the present work presents an automated approach for detection of COVID patients using convolutional neural network model. This approach takes into account chest X-ray images of COVID positive patients as well as non-COVID pneumonia patients for the training of the proposed CNN model. The simulation results show that the proposed CNN model performs binary classification of COVID and non-COVID pneumonia classes with an average accuracy of 97.92%, sensitivity of 99.69% and specificity of 98.48%. Thus, the proposed CNN model is an effective technique for the accurate identification of COVID patients among other patients suffering from bacterial or viral pneumonia using X-ray images. </em></p> ER -