AI listens to toilet sounds to determine whether or not people have diarrhea
- AI technology in smart toilets can help detect diarrhea
- The device decodes the sound of bowel movements to detect diarrhea
- This technology can help in detecting various //inflammatory bowel diseases
“The hope is that this sensor, which is small in footprint and noninvasive in approach, could be deployed to areas where cholera outbreaks are a persistent risk,” says Maia Gatlin, an aerospace engineer at Georgia Tech, in a media release (1✔ ✔Trusted Source
AI listens to toilet sounds to guess whether people have diarrhoea
Go to source).
When someone defecates, urinates, or passes gas, the computer neural network checks for small changes in the sounds. To develop the algorithm, the researchers collected hours of audio and video data from healthy and ill people.
They converted each into a spectrogram, which is essentially a sound image. Diverse experiences result in different characteristics. Urination and defecation, for example, produce a consistent and distinct tone. In comparison, diarrhea is more unpredictable.
The scans were sent into the study’s algorithm, which learned to rank them. The performance of the toilet was tested against data with and without background noises. This ensured that the sensor was learning the correct sound qualities regardless of its surroundings.
Cholera is a Leading Cause of Death all Around the World
The Georgia Tech team intends to collect real-world acoustic data to train their machine-learning model to perform in a range of restroom settings.Identifying potential community disease spread for such an outbreak will inform health experts earlier and optimize resource and help allocation. Monitoring this and other bowel illnesses, however, is a delicate subject for obvious reasons.
Reference:
- AI listens to toilet sounds to guess whether people have diarrhoea - (https://www.newscientist.com/article/2350082-ai-listens-to-toilet-sounds-to-guess-whether-people-have-diarrhoea/)
Source-Medindia