ABSTRACT

Obesity is one of the most pressing health challenges faced by our country, and has been the target of much attention in the mobile health (mHealth) community. While the science of obesity indicates that diet is a major factor in behavioral change to encourage healthy weight management, we are still not able to effectively, quickly and easily measure eating and drinking behavior. This project's goal is to develop a digital earpiece ­­ small and comfortable enough to wear behind the ear ­­ that can sense and detect actions such as eating and drinking. The project's long­term vision is to enable behavioral­health researchers to better understand health­related behaviors and, subsequently, to support the development of effective behavioral­health interventions that promote healthy diet and behavior.
Ultimately, a better understanding of eating­related behaviors, and better design of effective interventions regarding eating behavior, will have profound impact on personal and public health as well as the national economy. The project's hardware and software prototypes will be shared widely in the research community to enable experimentation around the sensing and interaction opportunities possible in an earpiece device. Furthermore, the project directly involves undergraduate and graduate students in interdisciplinary research, and outreach to middle­school students, expanding the supply of scientists educated in this important emerging topic.

The goal of the proposed work is to develop a digital earpiece ­­ small and comfortable enough to wear behind the ear ­­ that can sense and detect actions such as eating, drinking, smoking, and speaking, and measure physiological stress. The project's long­term vision is that computational jewelry like this earpiece will enable behavioral­health researchers to better understand health­related behaviors and, subsequently, to support the validation and deployment of effective behavioral­health 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 low­power (microwatt­scale) electronics and software sufficient to allow for the battery to last a full waking day; to develop efficient algorithms for detecting and distinguishing health­related behaviors (eating, drinking, smoking, speaking, and stress); and to develop easy and effective means for the wearer to interact with the earpiece and its applications.
Contributions: The team expects to answer scientific questions important to achieving the above goals. Specifically, they seek to advance scientific knowledge through the design and development of a wireless earpiece capable of sensing behavior and interacting with its wearer; develop novel low­power analog electronics and distributed software algorithms for inferring relevant behaviors from sensor data; develop novel interaction modalities involving bone­conduction audio between the earpiece and its wearer, complemented by tactile interfaces on the earpiece, on the skin, or on auxiliary devices like a wristband or smartphone; and validate these approaches through user studies and experiments inside and outside the lab.

Please report errors in award information by writing to: awardsearch@nsf.gov.