Monitoring of Eating Behavior Using Sensor-Based Methods

The essential physiological functions of the human body, including respiration, circulation, physical exertion, and protein synthesis, rely on energy from dietary constituents. Understanding eating behavior is crucial for overall health, as deviations in energy intake can lead to malnutrition-induced weight loss or obesity-related weight gain. Traditionally, dietary intake assessment has relied on self-reporting methods, such as dietary records, 24-hour recalls, and food frequency questionnaires. While these methods help understand relationships between eating behavior and dietary intake, they lack the granularity needed to explore detailed food consumption processes. Therefore, there is a need for innovative solutions that enable objective, precise, and automated monitoring of eating behavior, especially in free-living conditions.This dissertation investigates the application of wearable sensor systems for the automatic monitoring of eating behavior with minimal effort from subjects. First, a systematic review was conducted to identify available technology-driven methods for monitoring eating behavior. Then, a novel, contactless method for detecting and measuring eating behaviors such as chews and bites from eating videos was developed. Then an algorithm was devised to evaluate and compare different sensor modalities for identifying eating behavior, specifically focusing on chewing and chewing strength measurement. Four sensor modalities--Ear Canal Pressure Sensor, Piezoresistive Bend Sensor, Piezoelectric Strain Sensor, and EMG Sensor--were assessed. Results indicated comparable efficacy across all four systems in identifying chewing and chewing strength.Next, a novel Ear Canal Pressure Sensor system was explored for monitoring eating behavior, particularly chewing, in free-living environments. The findings demonstrated accurate detection and estimation of chewing in both controlled and free-living settings. Finally, a machine learning model to estimate energy intake (EI) from food intake using sensor-captured eating behavior features was developed and evaluated in free-living settings. The results highlight the efficacy of the sensor-based EI model and the potential for improved accuracy by leveraging image assistance and automatic food item detection.In conclusion, this research advances eating behavior monitoring using wearable sensor technologies. The findings hold promise for personalized nutrition interventions and mark a significant step forward in the objective assessment of eating habits.