The field of Artificial Intelligence is constantly evolving with new applications being developed for machine learning and data analysis. Researchers at the Sardar Vallabhbhai National Institute of Technology in Surat have developed an innovative use for AI by analyzing voice patterns to detect individuals with a cold.
As reported by The Economist, the researchers analyzed the voice patterns of 630 people, out of which 111 were found to be suffering from a cold. The aim was to detect individuals with a cold in real-time by analyzing their speech patterns.
Innovative AI Application
The Sardar Vallabhbhai National Institute of Technology in Surat has successfully used artificial intelligence (AI) to identify individuals suffering from a cold by analyzing their voice patterns. The researchers analyzed the voice patterns of 630 people, including 111 who had a cold, by using the concept of harmonics, which are the vocal rhythms in human speech that decrease in amplitude as their frequency increases.
People suffering from a cold tend to display an irregular pattern of harmonics, and the researchers used machine-learning algorithms to analyze these differences in amplification and accurately identify those who had a cold. Test subjects were asked to perform various vocal tasks such as counting and reciting a fable, and the researchers reported an accuracy rate of 70% in detecting colds using this method.
Although the main objective of the study was to diagnose colds without requiring medical consultation, the research could also have a potential application in identifying employees who may be feigning illness to take time off work. Employers could use this technology to accurately determine whether an employee is genuinely sick, which could result in a reduction in the number of fake sick days taken by employees.