| Abstrakt: |
At the present time, COVID-19 considers the pandemic that has most dangerous, representing a great threat to both, Communities and individuals especially scientist and researchers. Determine the infection in the early time is the only way to avoid getting worst especially for those who have respiratory diseases. The researchers working daily without stopping to get the possible solutions to rescue patients or who have the Symptoms of the disease. CT-Scans and X-rays for the lungs consider one of the most popular methods used by the researchers, where analyzing this image to detect the infection by this pandemic. However, it demands long time to examine each test, beside a large number of radiology specialists will be required. Oxygen data may be an interesting signal data samples that can be used to detect the COVID-19 via number of oxygen blood tests, in this research, detection of COVID-19 through some tests of oxygen signals is an essential goal. Tests like oxygen saturation (spO2), Pulse Oximetry (plusOX), Arterial blood gas (ABG) and Carboxyhaemoglobin (COHb) are the most common and important test for this purpose. In this research, a method based on deep neural network as well as machine learning methods using (stochastic gradient decision, decision tree, random forest, linear regression and k-nearest neighbour) was proposed for detecting COVID-19 through analysing the X-rays of patients which will look for visual indicators found in the chest radiography imaging of COVID-19 patients. Also proposed architecture can be applied to the oxygen data when it will be available (lack of well-structured data). [ABSTRACT FROM AUTHOR] |
