A Study of Temporal Action Sequencing During Consumption of a Meal

Advances in body sensing and mobile health technology have created new opportunities for empowering people to take a more active role in managing their health. Measurements of dietary intake are commonly used for the study and treatment of obesity. However, the most widely used tools rely upon self-report and require considerable manual effort, leading to underreporting of consumption, non-compliance, and discontinued use over the long term. We are investigating the use of wrist-worn accelerometers and gyroscopes to automatically recognize eating gestures. In order to improve recognition accuracy, we studied the sequential dependency of actions during eating. Using a set of four actions (rest, utensiling, bite, drink), we developed a hidden Markov model (HMM) and compared its recognition performance against a non-sequential classifier (KNN). Tested on a dataset of 20 meals, the KNN achieved 71.7% accuracy while the HMM achieved 84.3% accuracy, showing that knowledge of the sequential nature of activities during eating improves recognition accuracy.