Ricerc@Sapienza

In prediction problems both response and covariates may have high
correlation with a second group of influential regressors, that can be
considered as background variables. An important challenge is to
perform variable selection and importance assessment among the
covariates in the presence of these variables. A clinical example is
the prediction of the lean body mass (response) from bioimpedance
(covariates), where anthropometric measures play the role of background
variables. We introduce a reduced dataset in which the variables

In this paper, we consider the possibility to jointly exploit multiple frequency channels emitted by the same transmitter to improve target detection capability in a DVB-T based passive radar. In particular, appropriate multi-frequency techniques are presented for target detection to be effective in the considered application. The proposed approaches are validated and compared with reference to several experimental data for maritime surveillance applications.

In this paper we present a robust approach for target direction of arrival (DoA) estimation in passive radar that jointly exploits spatial and frequency diversity. Specifically we refer to a DVB-T based passive radar receiver equipped with a linear array of few antenna elements non-uniformly spaced in the horizontal dimension, able to collect multiple DVB-T channels simultaneously. We resort to a maximum likelihood (ML) approach to jointly exploit the target echoes collected across the antenna elements at multiple carrier frequencies.