Two popular Universities are working hard to help the detection of coronavirus through mobile applications. this application takes into consideration the breathing and coughing recording of users and based on Artificial Intelligence and Machine Learning determines whether a person is infected or not.
Cambridge Universities seek to archive this task through anonymous volunteers giving out their data to help strengthen their AI whilst the team at Carnegie Mellon University requires users to register before taking part. Currently, Mellon University has temporarily gone offline.
How the system works
- The general public are entreated to visit the COVID 19 sounds project website by University of Cambridge
- Cough into your microphone, as well as providing details about your age, gender, location, whether tested positive or not in recent days.
- They then ask you to read “I Hope my data can help to manage the coronavirus pandemic” and breathe for three consecutive times.
As Prof Cecilia Mascolo explained, “the aim is to collect enough data to check from these sounds we’re able to diagnose people who have COVID-19 and perhaps even the stage of the disease”.
Currently, both projects are limited to collecting samples via the website rather than a smartphone app because Apple and Google are restricting publishing of corona-virus related apps from their store
According to Chris Mitchell, chief executive of Audio analytics who has concerns stated “With the Midlands and London suffering the worst COVID-19 outbreaks in the UK, the regional variations in the way people sound means some areas could have undue influence on the AI model unless carefully controlled in the data” he continued by saying “Picking up detailed respiratory sounds for expert analysis is made harder without using specialist microphones, and both trials require patients to record themselves using a smartphone [or PC]”. triggering some equipment limitations but yet still both projects are optimistic about their results.
