fbpx

Using Buzz to reduce snoring

The winners are in for Neosensory’s second developer contest. Our judges were thrilled with the dozens of inventive entries that leveraged Buzz to create devices ranging from infrared sensors to echolocation devices. In this ongoing series, we’ll be showcasing these submissions. To see all winners, click here.

What’s worse than nightmares, in that it disrupts the sleep of both you and your partner? Snoring. Twenty five percent of adults suffer from it on a regular basis. Almost half of all adults snore occasionally.

Bryan and Brayden Staley set out to find a solution to this noisy problem. Together, the father-son duo developed a smart device using Neosensory Buzz.

The snoring corrector

The idea is straightforward: automatically interrupt the snorer’s sleep until the snoring stops.

To achieve this, a Raspberry Pi device collects audio and classifies it — specifically looking for snoring. A pre-trained sound interference model, YAMNet, helps detect these audio events.

Buzz, our haptic-feedback wristband with four vibrating motors, is worn by the snorer. Once the base detects snoring over a certain threshold, it sends the information to Buzz, which vibrates in a predetermined pattern in response. The louder the sound, the more intense the vibrations. Once the snoring falls below the threshold, the vibrations stop.

Neosensory Buzz has four motors the Staleys programmed to work as a smart-snoring device.

Naturally, the Staleys had to test out their device on an actual snorer. The first night, the two recoded audio without wearing Buzz. The two recorded 59 instances of snoring. The second night, they recorded audio while the sleeper was wearing Buzz. This resulted in 26 instances of snoring. That’s a 56% reduction.

With these promising first results in mind, the duo wants to continue refining their smart device and create personalized solutions. The next step is to get the classification work directly onto Buzz processing chip so no extra devices are required beyond the wristband. To read about the details of the schematics and code, click here.

Have an idea for your own project? Apply to Neosensory’s third developer contest here.