Two results in statistical decision theory for detecting signals with unknown distributions and priors in white Gaussian noise
Résumé
Two recent advances in statistical decision and estimation theory are presented. These results concern the detection of signals whose amplitudes are above or equal to some bound and that are less present than absent in a background of white Gaussian noise. The first result describes the non parametric detection of such signals when the noise standard deviation is known whereas the second result affords to perform the detection when this standard deviation is unknown. For both results, the role played by thresholding tests on the observation norms is crucial. The detection of radar targets is a typical field of application of these results.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...