Researchers Create AI-Powered Device That Detects Cough
Researchers Create AI-Powered Device That Detects Cough, The ‘FluSense’ platform processes a low-cost microphone array and thermal imaging data with a Raspberry Pi and neural computing engine.
A team of American researchers has invented a portable monitoring device powered by machine learning called “FluSense” which can detect cough and crowd size in real time, analyze data to directly monitor flu-like illnesses and flu trends and predicting the next pandemic in manufacturing. The creators of FluSense from the University of Massachusetts at Amherst said that the new state-of-the-art computing platform, designed for use in hospitals, healthcare waiting rooms and large public spaces, could expand the arsenal of health surveillance tools used to predict seasonal flu and other viral airways. epidemics, such as the COVID-19 pandemic or SARS.
“This can allow us to predict flu trends in a much more accurate way,” said study co-author Tauhidur Rahman, assistant professor of computer and information science.
Such models can save lives by directly informing the public health response to an influenza epidemic.
These data sources can help determine the timing of flu shots, potential travel restrictions, allocation of medical supplies and more.
The “FluSense” platform processes a network of low-cost microphones and thermal imaging data with a Raspberry Pi and a neural calculation engine.
It does not store any personally identifiable information, such as voice data or distinctive images.
In Rahman’s mosaic laboratory, the researchers first developed a model of laboratory cough.
They then trained the deep neural network classifier to draw bounding boxes on thermal images of people and then count them.
“Our main goal was to build predictive models at the population level, not at the individual level,” said Rahman.
From December 2018 to July 2019, the FluSense platform collected and analyzed more than 350,000 thermal images and 21 million non-voice audio samples in public waiting areas.
The researchers found that FluSense was able to accurately predict daily illness rates at the university clinic.
According to the study, “early information on symptoms captured by FluSense could provide valuable additional and complementary information to current influenza forecasting efforts.”
The study’s lead author, Forsad Al Hossain, said that FluSense is an example of the power of combining artificial intelligence with advanced computing.
“We are trying to evolve machine learning systems,” says Al Hossain, showing the compact components inside the FluSense device. “All the processing takes place here. These systems are getting cheaper and more powerful.”
Researchers Create AI-Powered Device That Detects Cough, and the next step is to test “FluSense” in other public spaces and geographic locations.
“We have the initial validation that coughing does have a correlation with flu-related illness. Now we want to validate it beyond this specific hospital setting and show that we can generalize across locations,” said l epidemiologist Andrew Lover.