Fusion: Practice and Applications FPA 2692-4048 2770-0070 10.54216/FPA https://www.americaspg.com/journals/show/2765 2018 2018 Research Scholar, Department of Computer Science and Engineering, Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu, India R. R. Professor, Department of Computer Science and Engineering, Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu, India N. Mohanasundaram Professor, Department of Computer Science and Engineering, Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu, India; Professor, Department of Computer Science and Engineering, Faculty 0f Engineering, Karpagam Academy of Higher Education, Coimbatore, Tamil Nadu, India R. Santhosh Pneumonia is a medical condition affecting 100 million people globally, and rates are predicted to reach epidemic levels within the next several decades. As a result of the air sacs in both or even one lung becoming inflamed, the patient may experience fever, chills, and trouble breathing. Coughs with pus may also occur. Various organisms can cause pneumonia, including bacteria, viruses, and fungi. Early detection of pneumonia can allow the severity of the purulent material to be reduced. The ability of computer-aided detection techniques to reliably diagnose pneumonia has made them popular among scientists. We used a pre-trained Inception V3Net, Squeeze Excitation-based deep Convolutional Neural Network (SE-CNN) that was trained on the Kermany dataset and the RSNA Pneumonia Detection Challenge dataset in this study. In early-stage detection, the suggested technique beat previous state-of-the-art networks, achieving 91% precision in severity rating. Furthermore, our network's accuracy, recall, f1-score, as well as quadratic weighted kappa were reported to be 91.56%, 91%, and 90%, respectively. In terms of processing time and space, our suggested framework is simple, precise, and effective. 2024 2024 133 151 10.54216/FPA.160110 https://www.americaspg.com/articleinfo/3/show/2765