Automatic Dietary Monitoring in lab and daily living: novel on-body and ambient approaches

Abstract: Today dietary assessments require manual information sampling in paper or electronic questionnaires on food type and other diet-related details. Low accuracies of 50% are confirmed for self-reporting, which weakens diet coaching effectiveness and is a major limitation for today's diet programs. Automatic Dietary Monitoring (ADM) using ubiquitous sensors was proposed to alleviate this problem.

In this presentation, I will introduce approaches and results of recent sensing and pattern analysis research performed on ADM. The talk will specifically address on-body sensor technology, integration, and expected information. In the second part, I will discuss current signal and pattern analysis research being performed based on the sensing concepts. Finally, I will provide an outlook on future developments in this area and currently starting projects at the ACTLab, TU Eindhoven.

-> Download presentation