COVID-19 is often difficult to discover. Many people who catch the virus(病毒) clearly show symptoms of being ill. But many others show no signs at all. These people are asymptomatic(无症状的).
Though asymptomatic people don't feel pain, they can still pass the virus on to others. And sincethey may not even realize they are ill, they're likely to go around and spread the virus further.
Now, scientists at MIT(麻省理工学院) have developed technology which can quickly discover whether a person has COVID-19 or not, just from the way he or she coughs or speaks. The scientists used an AI(人工智能) method known as "Deep Learning".
In deep learning, computer programs are organized deeply through huge amounts of information, allowing them to find patterns that humans are often unable to notice. These patterns get stored in a"model." It can later be used to fit those patterns in new and surprising ways. In this case, the information used to create the AI model was tens of thousands of recorded samples(样本) of people coughing and speaking. In all, the scientists had over 200,000 records ofcoughs.
When the scientists tested their AI model, they found that it was able to discover 98.5% of allthe cases where the people coughing had COVID-19. Even greater was the fact that it discovered 100%of the asymptomatic people.
One of the scientists says, "We think this shows that the way you produce sound will changewhen you have COVID-19, even if you're asymptomatic."
Of course, the model isn't perfect ...
