In this article, the usefulness of the Generalised Additive Model for mean path loss estimation in Body Area Networks is investigated. The research concerns a narrow-band indoor off-body network operating at 2.45 GHz, being based on measurements performed with four different users. The mean path loss is modelled as a sum of four components that depend on path length, antenna orientation angle, absolute difference between transmitting and receiving antenna heights and relative polarisation of both antennas. It is proved that the Generalised Additive Model allows for mean path loss estimation with a higher accuracy in comparison with Linear Regression. The obtained mean error is 0 dB, the root mean square error is 5.52 dB and the adjusted coefficient of determination is 61.2%.

No abstract