Battery-free smart glasses monitor your health using blink energy

Your eyes blink roughly 14 to 20 times a minute, and every one of those movements is wasted energy. Engineers at Northwestern University have found a way to put that motion energy to work, powering a pair of battery-free health-sensing glasses.Almost half of us on this planet wear glasses. So harnessing a technology that more than 4 billion people already use to collect health data would be a neat way to kill two birds with one stone. Add in the fact that there's no battery to charge or replace once it wears out, and you're looking at nearly the perfect wearable."The human face is a goldmine for health data, making everyday glasses the perfect wearable," said Northwestern's Nivedita Arora, who led the work. "Generally, wearables track health data, like heart rate, through the wrist. But people have to remember to wear those trackers and take them off to recharge. Our idea is based on the fact that half the population already wears glasses. We can turn those glasses into wearables without asking people to change their habits and behaviors." Northwestern researcher Nivedita Arora led the work on GlassTENGNorthwestern University The prototype is called GlassTENG, and it harnesses not only a blink's motion energy but also the energy from smiles, jaw clenches, and eyebrow raises. Its sensors read those movements, along with your pulse, to track conditions including bruxism (teeth grinding), fatigue, and cardiovascular health.To do that, the researchers used sensors called triboelectric nanogenerators, or TENGs, which are thin devices that harvest static electricity, the same energy that makes a balloon stick to your hair. When two different materials – in this case the sensors and the wearers face – touch and then separate, they can swap electrons and produce a brief electrical charge. GlassTENG's flexible sensors contain layers that press together and pull apart as the face moves. Arora explained that this very motion supplies the mechanical energy needed to power its sensing.The team mounted three sensors on the frame. One sits on the nose bridge, next to the angular artery, and picks up pulse, blinking, and eyebrow movement. A second rests on the temple above the superficial temporal artery, tracking pulse and jaw activity. The third sits nearer the ear and detects chewing and teeth clenching.Each action leaves a distinct electrical fingerprint. Pulse, the faintest signal tested, produced 50 to 100 millivolts. Blinks and eyebrow raises produced 200 to 500 millivolts, and strong jaw movements reached up to 1.5 volts. Each blink and jaw clench leaves its own electrical fingerprintNorthwestern University To test the results, a machine-learning algorithm trained to learn to recognize patterns from examples analyzed signals from 20 volunteers. The researchers report an overall accuracy of 93.8% in identifying what each person was doing. Teeth clacking was recognized 99% of the time and jaw clenching 96% of the time. Pulse was checked separately with 10 participants who were seated and at rest. Compared with a reference chest strap, the glasses were off by an average of 1.82 beats per minute.The system is not perfect yet. Chat over dinner, and the glasses may assume your mouth is busy with the main course. Talking was correctly identified only 55% of the time and was mistaken for eating in 37% of cases. The authors attribute this to both activities moving the jaw and engaging the temporalis muscle (a muscle at the side of the head) in similar ways.For now, GlassTENG sends its data over Bluetooth to a smartphone or tablet, but the team wants to cut that tether. "In the long-term, we want to do on-device computation," Arora said. "If it detected a physiological event, it could have on-device intelligence in a battery-free way that could give immediate feedback. For example, if it detected jaw clenching, it could immediately alert the user to relax their jaw. I think it's only a matter of time until the glasses we wear everyday can monitor our health."The work is being presented this week at the UbiComp/ISWC 2026 symposium in Shanghai.Source: Northwestern University