Non-Invasive Evaluation of Diet: Devices and Algorithms

In 2008, medical costs associated with obesity were estimated to be over $147 billion, and over one-third of adults in the United States are considered obese. The average BMI (body mass index) has consistently increased over the last two decades, which has been shown to be a contributor to risk of stroke, diabetes, certain cancers, heart disease, and other conditions. Though many activity-monitoring systems have been proposed, little research has been conducted on quantifying the volume of food consumption, which has been shown to correlate with weight gain. Though countless manual data collections have been proposed such as food records and 24-hour recall, these approaches suffer from poor accuracy, high user burden, and low compliance. Wireless health-monitoring technologies have the potential to pro mote healthy lifestyle behavior and address the ultimate goal of enabling better lifestyle choices. This thesis explores the application of hardware, software, and algorithms to the domain of food intake monitoring and medication adherence. Moreover, we propose several new methods to improve the processing and segmentation of time-series data based on our nutrition monitoring dataset