Home Appliances

AI Can Now Use Radio Waves to Monitor Sleep

07 August 2017

Researchers at MIT and Massachusetts General Hospital have created a new device to monitor sleep stages without having to attach sensors to the body. Typically diagnosing and tracking sleep issues involves attaching electrodes and many other sensors to the patient, further disrupting sleep. The researchers developed a device that uses an advanced artificial intelligence (AI) algorithm to analyze radio signals around the sleeping person and then translate the measurements into sleep stages: light, deep or rapid eye movement (REM).

Some of the machinery that is traditionally used in sleep studies (Source: Chris Higgins/Mental Floss)Some of the machinery that is traditionally used in sleep studies (Source: Chris Higgins/Mental Floss)

Kabati and members of her group at MIT’s Computer Science and Artificial Intelligence Laboratory developed radio-based sensors that allow them to remotely measure vital signs and behaviors that can be signs of poor health. The sensors consist of a wireless device about the size of a laptop that emits low-power radio frequency (RF) signals. Radio waves reflect off of the body, so any slight movement of the body alters the frequency of the reflected waves. Vital signs like pulse and breathing rate can be revealed through analyzing the waves.

"It's a smart Wi-Fi-like box that sits in the home and analyzes these reflections and discovers all of these changes in the body, through a sign that the body leaves on the RF signal," Katabi says.

The team has used this approach to create a sensor called WiGait. WiGait can measure walking speed using wireless signals that could help doctors predict cognitive decline, falls, and other diseases and health problems. After developing the sensors, Katabi thought a similar approach could be useful for monitoring sleep.

"The opportunity is very big because we don't understand sleep well, and a high fraction of the population has sleep problems," says Zhao. "We have this technology that, if we can make it work, can move us from the world where we do sleep studies once every few months in the sleep lab to continuous sleep studies in the home."

In order to achieve that, researchers came up with a way to translate measurements of pulse, breathing rate and movement into sleep stages. Recent AI advances have made it possible to train computer algorithms known as deep neural networks to extract and analyze information from complex datasets like radio signals from the sensor. But these signals contain information irrelevant to sleep that can be confusing for existing algorithms. The MIT researchers came up with a new deep AI algorithm that eliminates irrelevant information.

"The surrounding conditions introduce a lot of unwanted variation in what you measure. The novelty lies in preserving the sleep signal while removing the rest," says Jaakkola. Their algorithm can be used in different locations and with different people, without any calibration.

With 25 healthy volunteers, researchers found their technique was around 80 percent accurate. This is comparable to the accuracy of ratings determined by sleep specialists based on EEG measurements.

"Our device allows you not only to remove all of these sensors that you put on the person and make it a much better experience that can be done at home, it also makes the job of the doctor and the sleep technologist much easier," Katabi says. "They don't have to go through the data and manually label it."

Other researchers have attempted to use radio signals for monitor sleep, but these have only been 65 percent accurate and only determine if a person is awake or asleep, not the stage of sleep they are in. Katabi was able to improve on this by training their algorithm to ignore wireless signals that bounce off of other objects in the room and only include data reflected from the person who is sleeping.

Researchers plan to use this technology to study how Parkinson’s disease affects sleep. The sensor could also be used to learn more about how sleep changes in someone with Alzheimer’s, insomnia and sleep apnea. It could also be helpful for studying difficult to detect epileptic seizures that happen during sleep.

Powered by CR4, the Engineering Community

Discussion – 0 comments

By posting a comment you confirm that you have read and accept our Posting Rules and Terms of Use.
Engineering Newsletter Signup
Get the GlobalSpec
Stay up to date on:
Features the top stories, latest news, charts, insights and more on the end-to-end electronics value chain.
Weekly Newsletter
Get news, research, and analysis
on the Electronics industry in your
inbox every week - for FREE
Sign up for our FREE eNewsletter
Find Free Electronics Datasheets