The paper is coauthored by:
Henning Idsøe, Mohamed Hamid, Thomas Jordbru, Linga Reddy Cenkeramaddi and Baltasar Beferull-Lozano.
In this paper, we experimentally validate the functionality of a developed algorithm for spectrum cartography using adaptive Gaussian radial basis functions (RBF). The RBF are strategically centered around representative centroid locations in a machine learning context. We assume no prior knowledge about neither the power spectral densities (PSD) of the transmitters nor their locations. Instead, the received signal power at each location is estimated as a linear combination of different RBFs. The weights of the RBFs, their Gaussian decaying parameters and locations are jointly optimized using expectation maximization with a least squares loss function and a quadratic regularizer. The performance of adaptive RBFs based spectrum cartography is shown through measurements using a universal software radio peripheral, a customized node and LabView framework. The obtained results verify the ability of adaptive RBF to construct spectrum maps with an acceptable performance measured by normalized mean square error (NMSE).