A human-centered wearable sensing platform with intelligent automated data annotation capabilities

Abstract

Wearable computers provide significant opportunities for sensing and data collection in user's natural environment (NE). However, they require both raw data and annotations to train their respective signal processing algorithms. Collecting these annotations is often burdensome for the users. Our proposed methodology leverages the notion of location from nearable sensors in Internet of Things (IoT) platforms and learns users' patterns of behavior without any prior knowledge. It also requests users for annotations and labels only when the algorithms are unable to automatically annotate the data. We validate our proposed approach in the context of diet monitoring, a significant application that often requires considerable user compliance. Our approach improves eating detection accuracy by 2.4% with requested annotations restricted to 20 per day.