A smart antenna for the estimation of the directions of arrival of electromagnetic waves is considered. The approach, which is based on a support vector regression, is studied with reference to two important aspects related to real applications. In particular, the performances of the smart antenna in presence of electromagnetic waves with arbitrary propagation directions are evaluated. Moreover, the capabilities of the proposed approach when dealing with reflected electromagnetic waves in near field conditions are assessed both in noiseless and noisy environments by means of several numerical simulations. The reported results indicate that the accuracy of the estimation decreases if the actual operation conditions differ from the “ideal” assumptions usually made in the training phase. This fact can be suitably taken into account in designing smart antennas for specific applications.

Direction finding with a linear array using Support Vector Machines: Effects of the elevation angle and detection of scattered waves in near field conditions

PASTORINO, MATTEO;RANDAZZO, ANDREA
2006-01-01

Abstract

A smart antenna for the estimation of the directions of arrival of electromagnetic waves is considered. The approach, which is based on a support vector regression, is studied with reference to two important aspects related to real applications. In particular, the performances of the smart antenna in presence of electromagnetic waves with arbitrary propagation directions are evaluated. Moreover, the capabilities of the proposed approach when dealing with reflected electromagnetic waves in near field conditions are assessed both in noiseless and noisy environments by means of several numerical simulations. The reported results indicate that the accuracy of the estimation decreases if the actual operation conditions differ from the “ideal” assumptions usually made in the training phase. This fact can be suitably taken into account in designing smart antennas for specific applications.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/257469
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact