PadNET: wearable physical activity detection network

Abstract

This paper describes a low power, distributed platform that combines a wide range of different sensors in a wearable, hierarchical network. The architecture simplifies integration of the sensors into the user's outfit by structuring the hi- erarchy according to the anatomy of the human body. To date, acceleration and magnetic field sensors were used with the platform for a series of context recognition experiments. Other devices including gyroscopes and force resistive sen- sors are now being integrated. All designs are available over the internet under GPL licence.