Detecting activities from body-worn accelerometers via instance-based algorithms

The automatic and unobtrusive identification of user activities is one of the most challenging goals of context-aware computing. This paper discusses and experimentally evaluates instance-based algorithms to infer user activities on the basis of data acquired from body-worn accelerometer sensors. We show that instance-based algorithms can classify simple and specific activities with high accuracy. In addition, due to their low requirements, we show how they can be implemented on severely resource-constrained devices. Finally, we propose mechanisms to take advantage of the temporal dimension of the signal, and to identify novel activities at run time.