Unsupervised, dynamic identification of physiological and activity context in wearable computing

TLDR

Context‑aware computing describes how a wearable or mobile computer adapts its behavior based on the user’s state and surroundings. The study designed, implemented, and evaluated a wearable system that determines typical user context and context‑transition probabilities online without external supervision. The system uses machine learning, statistical analysis, and graph algorithms to enable online classification and prediction of user context. Results show that the method can build a meaningful user context model using only data from a comfortable physiological sensor device.

Abstract

Context-aware computing describes the situationwhere a wearable / mobile computer is aware of itsuser's state and surroundings and modifies its behaviorbased on this information. We designed, implemented andevaluated a wearable system which can determine typicaluser context and context transition probabilities onlineand without external supervision. The system relies ontechniques from machine learning, statistical analysisand graph algorithms. It can be used for onlineclassification and prediction. Our results indicate thepower of our method to determine a meaningful usercontext model while only requiring data from acomfortable physiological sensor device.