As many people worldwide are choosing smart devices to keep a check on their health, a team of researchers have developed a smart neckband that allows wearers to monitor their dietary intake.
Managing conditions like diabetes and obesity, or when maximising fitness can benefit from monitoring food and fluid intake automatically. However, distinguishing eating and drinking from similar movements like speaking and walking is necessary for wearable technologies, the researchers pointed out in the study published in the journal PNAS Nexus.
To deal with this issue, Chi Hwan Lee and the team proposed a machine-learning-enabled neckband that can differentiate body movements, speech, and fluid and food intake.
The neckband comes with a sensor module which includes a surface electromyography sensor, a three-axis accelerometer, and a microphone. These sensors work together to capture muscle activation patterns in the thyrohyoid muscle of the neck, along with body movements and acoustic signals, the study mentioned.
In a study that involved six volunteers, the machine-learning algorithm was able to accurately identify movements related to eating or drinking with an accuracy rate of about 96 per cent for individual activities and 89 per cent for concurrent activities.
The authors suggested that the neckband could be used as part of a closed-loop system in combination with a continuous glucose metre and an insulin pump to calculate insulin dosages for diabetic patients by identifying meal timings. It could also be used to help athletes and other individuals interested in improving their overall health and wellness.
The neckband is constructed of a flexible, twistable, breathable mesh-structured textile that contains 47 active and passive components and can operate on battery power for more than 18 hours between charges, the researchers mentioned.