Radio Signature Based Posture Recognition Using WBSN
Abstract
A Body Network of IMUs is a well known solution for posture recognition based on accelerometer and magnetometer
data fusion. However sensors and especially the magnetometer can be disturbed by the environment. Considering a
wireless body sensor network, we propose to use available radio measurements as an alternative to the magnetometer.
We show with simulation and real data, that the radio signal used for WSBN communications can also provide useful
information despite highly noisy Received Signal Strength Indications (RSSI). We propose a solution for the
static case that leads a very simple algorithmic solution.