The first lesson a new parent learns is that the second you think you’ve finally figured out your kid’s patterns — sleeping, eating, pooping, crying endlessly in the middle of the night for no apparent reason, whatever — the kid will change it. It’s the Uncertainty Principle of kids — the mere act of observing the pattern changes it, and you’re back at square one.
As immutable as this rule seems, [Caleb Olson] is convinced he can work around it with this over-engineered sleep pattern tracker. You may recall [Caleb]’s earlier attempts to automate certain aspects of parenthood, like this machine learning system to predict when baby is hungry; and yes, he’s also strangely obsessed with automating his dog’s bathroom habits. All that preliminary work put [Caleb] in a good position to analyze his son’s sleep patterns, which he did with the feed from their baby monitor camera and Google’s MediaPipe library.
This lets him look for how much the baby’s eyes are open, calculate with a wakefulness probability, and record the time he wakes up. This worked great right up until
the wave function collapsed the baby suddenly started sleeping on his side, requiring the addition of a general motion detection function to compensate for the missing eyeball data. Check out the video below for more details, although the less said about the screaming, demon-possessed owl, the better.
The data [Caleb] has collected has helped him and his wife understand the little fellow’s sleep needs and fine-tune his cycles. There’s a web app, of course, and a really nice graphical representation of total time asleep and awake. No word on naps not taken in view of the camera, though — naps in the car are an absolute godsend for many parents. We suppose that could be curated manually, but wouldn’t doubt it if [Caleb] had a plan to cover that too.
Continue reading “Machine Learning Baby Monitor, Part 2: Learning Sleep Patterns” →
Between the 1930s and the 1950s, something sort of strange happened in the United States. The infant mortality rate went into decline, but the number of babies that died within 24 hours of birth didn’t budge at all. It sounds terrible, but back then, many babies who weren’t breathing well or showed other signs of a failure to thrive were usually left to die and recorded as stillborn.
As an obstetrical anesthesiologist, physician, and medical researcher, Virginia Apgar was in a great position to observe fresh newborns and study the care given to them by doctors. She is best known for inventing the Apgar Score, which is is used to quickly rate the viability of newborn babies outside the uterus. Using the Apgar Score, a newborn is evaluated based on heart rate, reflex irritability, muscle tone, respiratory effort, and skin color and given a score between zero and two for each category. Depending on the score, the baby would be rated every five minutes to assess improvement. Virginia’s method is still used today, and has saved many babies from being declared stillborn.
Virginia wanted to be a doctor from a young age, specifically a surgeon. Despite having graduated fourth in her class from Columbia University College of Physicians and Surgeons, Virginia was discouraged from becoming a surgeon by a chairman of surgery and encouraged to go to school a little bit longer and study anesthesiology instead. As unfortunate as that may be, she probably would have never have created the Apgar Score with a surgeon’s schedule. Continue reading “Virginia Apgar May Have Saved Your Life” →
While an engineering mindset is a valuable tool most of the time, there are some situations where it just seems to be a bad fit. Solving problems within the family unit would seem to be one such area, but then again, this self-rocking mechatronic crib seems to be just the cure for sleepytime woes.
From the look of [Peter]’s creation, this has less of a rocking motion and more of a gentle back-and-forth swaying. Its purpose is plainly evident to anyone who has ever had to rock a child to sleep: putting a little gentle motion into the mix can help settle down a restless infant pretty quickly. Keeping the right rhythm can be a problem, though, as can endurance when a particularly truculent toddler is fighting the urge to sleep. [Peter]’s solution is a frame of aluminum extrusion with some nice linear bearings oriented across the short axis of the crib, which sits atop the whole thing.
A recirculating ball lead screw — nothing but the best for [Junior] — and a stepper drive the crib back and forth. [Peter] took care to mechanically isolate the drivetrain from the bed, and with the selection of the drive electronics and power supply, to make sure that noise would be minimal. Although thinking about it, we’ve been lulled to sleep by the whining steppers of our 3D printer more than once. Or perhaps it was the fumes.
Hats off to [Peter] for a setup that’s sure to win back a little of the new parent’s most precious and elusive commodity: sleep.
Preterm infants frequently require ventilator support while they’re in the neonatal ICU, and this is usually done with a CPAP machine. The machine to infant interface is called a nasal cannula, a bit of plastic that connects an infant’s nose to the machine. Because there aren’t that many sizes of nasal cannula available, and preemies come in all sizes, there are inevitable problems. Ill-fitting nasal cannula can reduce the effectiveness of a CPAP, and can even cause significant damage to an infant’s septum.
For his Hackaday Prize entry, [Ben] is tackling this problem head on. He’s working on creating individualized nasal cannula for newborns using 3D modeling and printing, allowing nasal cannula of all shapes and sizes to be created in a matter of hours.
To create these customized cannula, [Ben] is 3D scanning an infant mannequin head to gather enough data to import it into a Processing sketch. A custom cannula is then created and printed with flexible 3D printer filament. In theory, it should work, apart from the considerations involved in building a medical device.
As for why custom plastic tubes matter, [Ben] works at the only NICU in Western Australia. Even though he only sees 8-10 CPAP ‘pressure injuries’ in his unit each year, these kids are extremely fragile and some parents have expressed a desire for something that isn’t as uncomfortable for their newborn than the off-the-shelf solution. Customizing these cannula from a quick 3D scan is a great way to do that, and a perfect example of the Hackaday Prize theme of ‘build something that matters.’
Researchers at the University of Delaware are helping disabled kids by designing robot transportation for them. Exploring one’s environment is an important part of early development. Disabilities that limit mobility can prevent young children from experiencing this. Typically children are not offered a powered wheelchair until they are five or six years old, but adding intelligent technologies, like those found in the UD1, makes this possible at a much younger age. Proximity sensors all around the drive unit of the robot add obstacle avoidance and ensure safety when used around other children. When confronted with an obstacle the UD1 will stop, or navigate around it. The unit is controlled by a joystick in front of the rider but it can also be overridden remotely by a teacher, parent, or caregiver.
[via Robot Gossip]
This surprisingly pleasant looking crib is actually a robot, designed to keep babies quiet and happy all night long. Once inside and locked up, the baby is under the robot’s care. When the robot senses crying, it rocks gently back and forth. This should allow parents the time to catch some sleep. As pointed out in the article, the $5000 price tag is a bit steep. Especially considering the fact that you can get a much less technologically advanced equivalent for relatively cheap. How many of you hackers have babies? What hacks did you do to get your babies to sleep?