Machine Learning Neckband Tracks Food and Hydration Intake

Chi Hwan Lee and his colleagues developed a smart neckband that tracks eating and drinking habits. This machine-learning-powered device uses sensors to distinguish between these actions and similar movements like talking and walking, offering the potential for managing diabetes and improving overall health. The study was published in the journal PNAS Nexus.

Machine Learning Neckband Tracks Food and Hydration Intake
The sensor module, positioned on the thyrohyoid muscle, features a 45-degree pre-curved design and soft, waterproof encapsulation. Image Credit: Park et al.

Wearers of smart neckbands can monitor how much food they consume. When maximizing fitness or managing illnesses like diabetes and obesity, automatically tracking food and hydration intake might be helpful. However, eating and drinking must be distinguished from related motions like speaking and walking via wearable technology.

Chi Hwan Lee and colleagues propose a neckband with machine learning capabilities that can distinguish between speech, body language, hydration, and food intake. The neckband's sensor module includes a microphone, a three-axis accelerometer, and a surface electromyography sensor.

Combined, these sensors can record auditory data, body motions, and muscular activation patterns in the neck's thyrohyoid muscle. With an accuracy rate of almost 96 % for individual activities and 89 % for concurrent activities, the machine-learning algorithm accurately identified which movements in research involving six participants were related to eating or drinking.

Made of breathable, mesh-structured, flexible, and twistable cloth, the neckband has 47 active and passive components that can operate on battery power for over 18 hours without recharging.

The neckband can help athletes and other people interested in improving their general health and wellness. It can also be used in a closed-loop system with a continuous glucose meter and an insulin pump to help diabetic patients determine when to take their insulin dosages.

Journal Reference:

‌Park, T., et al. (2024) A machine-learning-enabled smart neckband for monitoring dietary intake. PNAS Nexus.


Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.