• Sameeha.G
• Dr.M.S.Anbarasi

The necessity for a COVID-19 diagnosis is critical. The presence of COVID-19 in patients' computed tomography (CT) and chest X-ray scans has been identified through a number of investigations. Although these efforts produced efficient methods of classification, the design of a transportable and economically viable COVID-19 diagnosis system has not yet been addressed. Modern COVID-19 diagnosis systems have high memory requirements, requiring hundreds of megabytes or more, making them unsuitable for embedded systems. The goal of the current study is to create an analogous system with low memory requirements. We propose a diagnosis system employing machine learning algorithms in this research. To forecast a patient's CT and chest X-ray image, we use the Inception and VGG prediction algorithms. Local features are extracted using an algorithm prior to Keras and Tensorflow. Transfer learning algorithms extract global features from chest X-rays/CT scans. A flask app was created to upload chest X-rays or CT scans to check for Covid infection, using Random Forest Algorithm and CNN algorithm. Modules such as Covid Prevention and FAQs have been added to make the application user-friendly.

COVID-19, Computed Tomography (CT), Chest X-ray, flask app , Random Forest , CNN

"Covid-19 and Lung Cancer Prediction using Hybrid Deep Learning Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.d395-d402, May-2023, Available :http://www.jetir.org/papers/JETIR2305355.pdf

"Covid-19 and Lung Cancer Prediction using Hybrid Deep Learning Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppd395-d402, May-2023, Available at : http://www.jetir.org/papers/JETIR2305355.pdf