Assisting Food Journaling with Automatic Eating Detection
Xu Ye, Guanling Chen, Yang Gao, Honghao Wang, Yu Cao · 2016
In this work we study the feasibility and usability of an assistive food journaling system that sends users just-in-time reminders when unique hand gestures during food consumption are detected using a smartwatch. Our study shows that participants were able to sustain food logging throughout a 2-week period with the help of our eating detection system, as the number of reminders correlate well with the number of food logs. Despite the fact that participants were required to wear the watch on their dominant hand, it was still quite usable and did not interfere with their normal activities. Participant feedback provided additional insights to inform future work to increase detection accuracy, reduce detection delay, and allow for more dietary logging features in the app.