Active Surveillance for COVID-19 through artificial intelligence using concept of real-time speech-recognition mobile application to analyse cough sound.

In view of recent coronavirus (SARS-CoV2) outbreak, we propose a novel model of active surveillance for COVID-19 through artificial intelligence. Both past and recent events of viral disease outbreaks have shown us that we do not have effective methods to screen the whole population and efforts are failing to stop the pandemics. Moreover, at this stage, social distancing and home quarantine are only measures to stop the spread of COVID-19 infection. The purpose of our project is to introduce a robust method of using speech-recognition techniques through a mobile application in analysing cough sounds of suspected people, who previously were healthy, suffering from a respiratory ailment and actively monitor the progress of their symptoms in real-time. The mobile application will give feedback to the app users on a routine basis and advise to take medication and necessary precautions to avoid spreading of the infection. The app will also notify the local healthcare facilities about sick users or vice-versa if their symptoms deteriorates. A feedback will be sent to an app-centre notifying the number of both new and old sick users appeared in a particular region. With the data compiled at the app-centre, we will also be able to trace the disease spread patterns, categorise the regions in three levels- mild, moderate and severe based on the number of sick users and deploy the resources accordingly to stop the transmission hence, preventing unnecessary use of both human and medical resources to stop the infection in redundant regions.