Published: April 8, 2020 5:43:11 noon
Researchers from the University of Cambridge have designed a new mobile application that will be used to collect data to develop machine learning algorithms, which will be able to detect if the person has COVID-19 or not based on their voice, their breath and cough.
How does someone’s voice help detect COVID-19?
A press release issued by the European Research Council (ERC) states that because COVID-19 is a respiratory condition, sounds made by people, including those made during breathing and coughing will be very specific. Application users must conduct a survey, which will collect basic demographic information and their medical history and take their recorded voice, along with their breathing and cough samples. The purpose of this study is to collect data from healthy and unhealthy people.
After the researchers have gathered a large database of that information, they will release it to other researchers and they hope that the dataset will help explain the development of the disease and the relationship between respiratory complications arising from COVID-19 and medical history. This application will also ask if the person tested positive for COVID-19.
Other AI-based efforts to overcome COVID-19
Artificial Intelligence (AI) is when machines are trained to do human tasks. Machine learning, on the other hand, is a subset of AI and involves training machines to look for patterns in data sets, something that humans will need more time to identify. However, to do this, machines need to provide a large amount of data that they can comb to find any patterns in it, which is the reason why researchers from Cambridge aim to collect sound data sets large enough for the machine. to do it.
Several other AI-based approaches to deal with current pandemic including COVID-19 Open Research Dataset (CORD-19), which is a free resource of research that is being carried out on COVID-19. There is also an open-access neural network, COVID-Net, which aims to help researchers around the world develop AI tools that can test people for COVID-19. COVID-Net is being trained by researchers to identify the signs coronavirus in chest X-ray using around 6,000 images taken from more than 2,800 patients with various lung conditions, including COVID-19, bacterial infections and non-COVID-related viral infections.
Even so, most of these AI tools are in the process and their efficacy in detecting diseases remains to be seen.
This is fast Coronavirus Guide from Express Explained to keep you updated: What can cause COVID-19 patients to recur after recovery? | Locking COVID-19 clears the air, but this might not be good news. This is why | Can alternative treatments work against coronavirus? | A five minute test for COVID-19 has been prepared, India might get it too | How India built defenses when locked | Why is it that only a small proportion of those who suffer from coronaviruses suffer from acute | How do health workers protect themselves from infection? | What is needed to arrange an isolation room?
? Indian Express is now in Telegram. Click here to join our channel (@indianexpress) and stay updated with the latest headlines