Title :
Rapidly adaptive signal detection using the principal component inverse (PCI) method
Author :
Freburger, B.E. ; Tufts, D.W.
Author_Institution :
Dept. of Comput. & Electr. Eng., Rhode Island Univ., Kingston, RI, USA
Abstract :
This paper presents a review of the principal component inverse method of rapidly adaptive signal detection and contrasts this method with the cross spectral metric method of rank reduction. Rank reduction methods are most effective if (a) the vector representing the strong portion of the noise lies in a low-dimensional subspace, (b) the subspace remains nearly constant for a local set of interference vectors which is large enough for good estimation of both the dimension of the subspace and a set of basis vectors for the subspace, and (c) signal suppression is unlikely.
Keywords :
adaptive signal detection; interference (signal); inverse problems; noise; parameter estimation; statistical analysis; adaptive signal detection; constant subspace; cross spectral metric method; generalised sidelobe canceller; interference vectors; low-dimensional subspace; noise; principal component inverse method; rank reduction; signal suppression; statistics; subspace dimension estimation; Adaptive signal detection; Covariance matrix; Eigenvalues and eigenfunctions; Gaussian noise; Interference cancellation; Inverse problems; Phase noise; Statistical analysis; Statistical distributions; Testing;
Conference_Titel :
Signals, Systems & Computers, 1997. Conference Record of the Thirty-First Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-8186-8316-3
DOI :
10.1109/ACSSC.1997.680547
