Said the toilet to the engineer: Do you hear what I hear?
A mythical hero’s journey took Dorothy along the yellow brick road to find the Wizard of Oz. Huckleberry Finn used a raft to float down the Mississippi River. Luke Skywalker did most of his traveling between planets. For the rest of us, the journey may be just a bit shorter.
Maia Gatlin
Also a bit less heroic. Unless, of course, you’re prepping for a colonoscopy. Yup, we’re headed to the toilet, but not just any toilet. This toilet was the subject of a presentation at the annual meeting of the Acoustical Society of America, titled “The feces thesis: Using machine learning to detect diarrhea,” and that presentation was the hero’s journey of Maia Gatlin, PhD, a research engineer at the Georgia Institute of Technology.
She and her team attached a noninvasive microphone sensor to a toilet, and now they can identify bowel diseases without collecting any identifiable information.
The audio sample of an excretion event is “transformed into a spectrogram, which essentially captures the sound in an image. Different events produce different features in the audio and the spectrogram. For example, urination creates a consistent tone, while defecation may have a singular tone. In contrast, diarrhea is more random,” they explained in the written statement.
They used a machine learning algorithm to classify each spectrogram based on its features. “The algorithm’s performance was tested against data with and without background noises to make sure it was learning the right sound features, regardless of the sensor’s environment,” Dr. Gatlin and associates wrote.
Their goal is to use the toilet sensor in areas where cholera is common to prevent the spread of disease. After that, who knows? “Perhaps someday, our algorithm can be used with existing in-home smart devices to monitor one’s own bowel movements and health!” she suggested.
That would be a heroic toilet indeed.