When it comes to communicable diseases, it's important to identify the source of an outbreak as soon as possible. In the case of cholera, a new toilet sensor could help, by detecting how many people in a given area are experiencing one of the main symptoms – diarrhea.
The prototype device was developed by a team at the Georgia Institute of Technology, led by research engineer Maia Gatlin.
It incorporates a microphone (but definitely not a camera) and, well … it listens in while people use the toilet. Utilizing a machine-learning-based algorithm running on an integrated microprocessor, it's able to identify the distinct audio signature of the loose, watery bowel movements associated with diarrhea.
Gatlin and her team trained the algorithm using audio samples of "excretion events" – such as urination, normal defecation, and diarrhea – obtained from online sources. Each sample was transformed into a spectrogram, which is essentially a visual representation of the sound.
Because each audio sample was already known to be a recording of a certain type of event, the algorithm was able to learn which distinctive spectrogram features accompanied which sorts of excretions. As a result, when subsequently presented with spectrograms of other audio samples, the algorithm was able to accurately identify the corresponding event types.
Importantly, it could single out the diarrhea spectrograms even when background noises were also recorded.
Plans now call for the algorithm to be refined further, using recordings obtained in real-world settings representing a variety of bathroom environments. Ultimately, networks of the sensors may provide an early warning of cholera outbreaks, particularly if used in regions where the disease is already known to occur with some regularity … although the potential applications don't stop there.
"The sensor could also be used in disaster zones (where water contamination leads to spread of waterborne pathogens), or even in nursing/hospice care facilities to automatically monitor bowel movements of patients," said Gatlin. "Perhaps someday, our algorithm can be used with existing in-home smart devices to monitor one's own bowel movements and health."
She presented her team's research this Monday, at the 183rd Meeting of the Acoustical Society of America.
Source: Acoustical Society of America via Newswise
