Sensor Technology to Measure and Intervene on Eating Behavior
Dr. Edward Sazonov is a Professor in the Department of Electrical and Computer Engineering at the University of Alabama.
Abstract: The emergence of wearable sensor technology paves the way for objective, sensor-driven assessment of health-related behaviors, which in modern society act as the major determining factors of life expectancy and quality of life. The modern sensor technology carries the promise to objectively measure and quantify complex human behaviors such as physical activity, food intake patterns, addictions, sleeping patterns, and social interactions. Furthermore, real-time recognition of the behavior enables novel approaches for just-in-time behavior modification. The recognition, characterization and interpretation of behaviors form sensor data presents a challenging problem due to complexity and variability of real-life behaviors as well as the indirect manner in which events of interest are inferred from behavioral and physiological manifestations registered by the sensors.
The talk will provide an overview of our work on wearable sensors for monitoring of food intake in adults and infants, which are of particular interest for understanding and treatment of related medical conditions, such as obesity and eating disorders. Traditionally, ingestive behavior in humans has been assessed through self-monitoring. However, this approach is time-consuming and suffers from the observation and misreporting effects. Wearable sensors present a compelling alternative that may potentially provide more objective measurements of food intake by monitoring behavioral and physiological phenomena related to one or more stages of the food consumption process: hand-to-mouth gestures, bites, chewing or swallowing. Signal processing and pattern recognition methodologies applied to the sensor signals can be used to automatically detect and characterize each ingestion episode. Timing, duration of the meals, the mass and volume, caloric and nutritional content of ingested food, and the rate of ingestion could potentially be estimated from sensor data. Furthermore, the sensor-derived measurements of ingestive behavior may inform tailored, real-time interventions aimed at modification of eating behaviors.
*If you are interested in attending this Seminar, please email Staff Support, Amber Tweebeeke, to receive the Zoom link and password.