This Smart Toilet Will Know You by the Shape of Your Asshole​

Your butthole is like a snowflake: No two are exactly alike.

At least, that's the crux of a new scientific paper outlining the mechanisms for a smart toilet that identifies poopers based on video clips of their unique anuses.

Stanford researchers have created the panopticon of looking up your own ass, with a "smart toilet" that monitors your health by analyzing your stool, urine, and the timing of both, using four cameras and an array of sensors and identification systems. The paper, "A mountable toilet system for personalized health monitoring via the analysis of excreta," was published Monday in the journal Nature.

"Each user of the toilet is identified through their fingerprint and the distinctive features of their anoderm," the researchers write, "and the data are securely stored and analysed in an encrypted cloud server." The anoderm is the scientific word for your asshole-skin, entomologically a combination of "anus," and "derm," or skin.

"Schematic of analprint analysis for biometric identification," via Stanford University

Rather than sending people to a clinic or labs for expensive and time-consuming blood tests, these researchers posit that the most valuable health data is in our shit, spit and piss. They write that "the ideal sources of diagnostic information for continuous health monitoring are the potentially information-rich molecular contents of breath, sweat, saliva, urine and stool."

Their prototype mounts to an existing toilet, and uses flush-lever fingerprinting, "analprint recognition" (an incredible phrase, thank you science), and analyzes urine and stool, as well as the speed and timing of your business—all done using two-factor authorization and automatically sent to the cloud.

By now, I'm sure you're begging to know how it works. Well, these scientists have thought of everything.

For pee analysis, there are two high-speed cameras watching the flow rate, and a stack of urinalysis strips are loaded into the back of the seat. A passive infrared motion sensor detects when you start peeing, and slides out a strip. This system was tested on one male and one female participant, the paper notes, but is designed for men to be able to stand and aim directly for the strip. (The researchers note that urinalysis and uroflowmetry modules were tested for only standing participants because of the differences, but future studies will include more data on sitting-urination.) When the strip is soaked, it's sucked back into the seat and a camera analyses the results. Wow!

For poop analysis, a pressure sensor activates a video camera that captures images of the toilet bowl, from clean, to shat, to covered in toilet paper. These images are fed to a convolutional neural network (an AI algorithm), which determines the time from when the first kid is dropped off at the pool to the last, "which is significantly correlated with overall bowel function," they write. Each frame of the bowl is time-stamped for accuracy. "Here we assumed that the use of toilet paper or standing up indicates the user’s intention to terminate the defecation event."

"As a user sits on the toilet for a defecation event, the pressure sensor below the toilet seat initiates the defecation monitoring camera. The camera records the toilet bowl until the end of the defecation event. The collected images are then fed into deep CNN layers for stool classification." Image via Stanford University

This camera can also observe "the dynamic changes of stool—that is, stool morphology and liquidity changes over time in the toilet bowl—which have not been investigated in the field," they write.

Distinguishing whose poo is whose within a household is obviously important for this system to work, and this research team went above and beyond to make sure every person is absolutely the owner of their own particular dump. Hence, the analprint.

Now, presumably they could have stopped at installing a fingerprint scanner on the flusher, but no—they added a scanner inside the toilet, to record a short video clip of the user’s butthole. The anus is identified using an image recognition algorithm. A video clip of the asshole is divided into frames, and the algorithm compares it with a dataset of reference images of the user’s "analprint." God, I just really love the word analprint!

Motherboard reached out to the team to clarify how the stool images will be analyzed, and will update when we hear back.

With everyone right now so obsessed with toilet paper—where they'll get their next batch of toilet paper, and bidet-usage as an alternative to toilet paper—it's good to see scientists working hard to put all that valuable backend data to good use.

from VICE https://ift.tt/2xaqWI0
via cheap web hosting