Data-Driven Assessments for Sensor Measurements of Eating Behavior

Abstract

Two major challenges in sensor-based measurement and assessment of healthy eating behavior are (a) choosing the behavioral indicators to be measured and (b) interpreting the measured values. While much of the work towards solving these problems belongs in the domain of behavioral science, there are several areas where technology can help. This paper outlines an approach for representing and interpreting eating and activity behavior based on sensor measurements and data available from a reference population. The main idea is to assess the “similarity” of an individual's behavior to previous data recordings of a relevant reference population. Thus, by appropriate selection of the indicators and reference data it is possible to perform comparative behavioral evaluation and support decisions, even in cases where no clear medical guidelines for the indicator values exist. We examine the simple, univariate case (one indicator) and then extend these ideas to the multivariate problem (several indicators) using one-class SVM to measure the distance from the reference population.