A research team from the University of Washington has enabled smart speakers to use white noise to soothe infants while they sleep and monitor their movement and breathing. This program, BreathJunior, has the smart speaker play white noise and records how this noise is reflected in a manner that detects the infant’s breathing motions. When tested in five infants, BreathJunior was found to characterize respiratory rates with accuracy on par with standard breathing monitors. These Washington researchers will be presenting their findings at the MobiCom 2019 conference on October 22 in Los Cabos, Mexico.
“One of the biggest challenges new parents face is making sure their babies get enough sleep,” explained study co-author Dr. Jacob Sunshine, an assistant professor of anesthesiology and pain medicine at the University of Washington School of Medicine. “They also want to monitor their children while they’re sleeping. With this in mind, we sought to develop a system that combines soothing white noise with the ability to unobtrusively measure an infant’s motion and breathing.”
Sunshine and colleagues designed BreathJunior so that it could be integrated into existing commercial smart speakers such as the popular Amazon Echo. Shyam Gollakota, co-author and associate professor in the UW’s Paul G. Allen School of Computer Science & Engineering, feels that these speakers’ strong presence and current capabilities make them a convenient tool in monitoring neonatal health.
“Smart speakers are becoming more and more prevalent, and these devices already have the ability to play white noise,” said Gollakota, who is also the director of the UW computing for health group. “If we could use this white noise feature as a contactless way to monitor infants’ hand and leg movements, breathing and crying, then the smart speaker becomes a device that can do it all, which is really exciting.”
How BreathJunior Monitors Infant’s Breathing
White noise offers a soothing sound that can block out other noises, being that the sound is a combination of different frequencies. Using the smart speaker to generate white noise with known qualities, these researchers aimed to analyze how the sound reflects off the baby to measure breathing and sleeping patterns. The biggest challenge with this approach is that the infant’s body and breathing movements are so small that the smart speaker needs to know their precise location to measure their respiratory qualities.
“The breathing signal is so weak that we can’t just look for a change in the overall signal we get back,” explained first author Anran Wang, a doctoral student in the Allen School of Computer Science & Engineering. “We needed a way to scan the room and pinpoint where the baby is to maximize changes in the white noise signal. Our algorithm takes advantage of the fact that smart speakers have an array of microphones that can be used to focus in the direction of the infant’s chest. It starts listening for changes in a bunch of potential directions, and then continues the search toward the direction that gives the clearest signal.”
In addition to subtle chest movements associated with breathing, BreathJunior also picks up on the infant’s movement in the crib and sounds of crying.
Evaluating the White Noise System
An experimental smart speaker was created to test the technology on an infant simulator, allowing the team to set the test BreathJunior’s ability to detect a variety of respiratory rates (from 20 to 60 breaths per minute). This simulator-driven trial also allowed the researchers to test the technology’s ability to identify breathing abnormalities like sleep apnea, a condition common in prematurely born babies.
After having success measuring both respiratory qualities in the simulation, BreathJunior was then put to the test in a neonatal intensive care unit (NICU). Comparing the results from the smart speaker technology to traditional respiratory monitors used in the hospital, BreathJunior was found to accurately identify breathing rates up to 65 breaths per minute.
“Infants in the NICU are more likely to have either quite high or very slow breathing rates, which is why the NICU monitors their breathing so closely,” explained Sunshine. “BreathJunior holds potential for parents who want to use white noise to help their child sleep and who also want a way to monitor their child’s breathing and motion. It also has appeal as a tool for monitoring breathing in the subset of infants in whom home respiratory monitoring is clinically indicated, as well as in hospital environments where doctors want to use unwired respiratory monitoring.”
Sunshine cautions that BreathJunior is not a platform that reduces the risk of infant death. “It is very important to note that the American Academy of Pediatrics recommends not using a monitor that markets itself as reducing the risk of sudden infant death syndrome, and this research and the team makes no such claim,” he explained.
Currently, BreathJunior only uses white noise to monitor the infant during sleep. The Washington researchers are interested in expanding this technology to use different sounds as well, such as lullabies that infants may prefer.
“In just a few years, we have come a long way from monitoring large motions in adults to extracting the tiny motion of a newborn infant’s breathing,” Gollakota said. “This has been possible because of algorithmic innovations as well as advances in smart speaker hardware. Looking ahead, one can envision transforming a smart speaker into a ‘medical tricorder’ that can contactlessly monitor a variety of vital signs beyond just breathing.”
This speaker uses white noise to monitor infant’s movement, breathing: To use white noise… https://t.co/OvsjJTIKKv
— ummid.com (@ummid) October 16, 2019