Today, Dartmouth graduate student Shengjie Bi presented an Auracle paper, Toward a Wearable Sensor for Eating Detection, at the ACM Workshop on Wearable Systems and Applications (WearSys) in Niagara Falls, NY.
Abstract: Researchers strive to understand eating behavior as a means to develop diets and interventions that can help people achieve and maintain a healthy weight, recover from eating disorders, or manage their diet and nutrition for personal wellness. A major challenge for eating-behavior research is to understand when, where, what, and how people eat. In this paper, we evaluate sensors and algorithms designed to detect eating activities, more specifically, when people eat. We compare two popular methods for eating recognition (based on acoustic and electromyography (EMG) sensors) individually and combined. We built a data-acquisition system using two off-the-shelf sensors and conducted a study with 20 participants. Our preliminary results show that the system we implemented can detect eating with an accuracy exceeding 90.9% while the crunchiness level of food varies. We are developing a wearable system that can capture, process, and classify sensor data to detect eating in real-time.
Auracle Ph.D. student Shengjie Bi presented an overview of the Auracle project at a poster session during the First Annual UMass Center for mHealth and Social Media Conference, hosted at UMass Medical School. Click on the poster for more detail!
Obesity is one of the most pressing health challenges faced by our country, and has been the target of much attention in the academic and commercial mobile health (mHealth) community. Despite the community’s significant effort in developing technology to measure physical activity (in an effort to estimate caloric output), little progress has been made in measuring eating and drinking behavior (caloric intake) – and yet the science of obesity indicates that diet is a major factor in behavioral change to encourage weight loss and healthy weight management.
In the Auracle project we plan to develop a digital earpiece – small and comfortable enough to wear in or behind the ear – that can sense and detect actions such as eating, drinking, smoking, and speaking, and measure physiological stress. The project’s long-term vision is that computational jewelry like this earpiece will enable behavioral-health researchers to better understand health-related behaviors and, subsequently, to support the validation and deployment of effective behavioral-health interventions that promote healthy diet and behavior.
The project’s approach is to build a prototype wireless earpiece, small enough to wear behind the ear, with low-power (microwatt-scale) electronics and software sufficient to allow for the battery to last a full waking day; to develop efficient algorithms for detecting and distinguishing health-related behaviors (eating, drinking, smoking, speaking, and stress); and to develop effective means for the wearer to interact with the earpiece and its applications.