Share
NEW DELHI — Drowsy driving is a critical hazard which contributes to road accidents worldwide. However, engineers have now developed earbuds to address the drowsiness while driving.
Engineers at the University of California, Berkeley, have developed prototype earbuds that can detect signs of drowsiness in the brain, aiming to protect drivers and machine operators from the dangers of drowsiness.
The earbuds function like an electroencephalogram (EEG), measuring brain waves through built-in electrodes that contact the ear canal. While the electrical signals detected are smaller than those in traditional EEGs, the new study shows that the Ear EEG platform is sensitive enough to detect alpha waves, a pattern of brain activity that increases when drowsiness sets in.
“I was inspired when I bought my first pair of Apple's AirPods in 2017. I immediately thought what an amazing platform for neural recording. We believe this technology can classify drowsiness, indicating its potential to classify sleep and diagnose sleep disorders,” said study author Rikky Muller, Associate Professor of Electrical Engineering and Computer Science at UC Berkeley
Creating an earbud that fits a variety of ear sizes and shapes posed significant challenges. While other groups used wet electrode gels or custom-moulded earpieces, Muller's team aimed for a dry, user-generic model that anyone could use.
“My goal was to create a device usable every day by those who would benefit from it,” said Ryan Kaveh, the designer.
Kaveh designed the earpiece in three sizes. The design includes multiple electrodes applying gentle pressure to the ear canal, ensuring a comfortable fit, with signals read through a low-power, wireless interface.
In a paper, the researchers demonstrated the earpieces could detect physiological signals, including eye blinks and alpha brain waves. The study incorporated machine learning to validate the earpieces' real-world application. Nine volunteers wore the earpieces while performing tasks in a darkened room, periodically rating their drowsiness and response times.
“We found that even with seemingly lower signal quality, we could classify drowsiness onset as accurately as with more complex systems,” Kaveh said. The earpieces' accuracy in new users suggests they could work 'out of the box'.
Exploring other applications, including recording heartbeats, eye movements and jaw clenches are in the works.