A Structured Low Rank Matrix Pencil for Spectral Estimation and System Identification

Simple item page
dc.contributor.authorRazavilar, J.en_US
dc.contributor.authorLi, Yeen_US
dc.contributor.authorLiu, K.J. Rayen_US
dc.contributor.departmentISRen_US
dc.date.accessioned2007-05-23T10:01:35Z
dc.date.available2007-05-23T10:01:35Z
dc.date.issued1996en_US
dc.description.abstractIn this paper we propose a new parameter estimation algorithm for damped sinusoidal signals. Parameter estimation for damped sinusoidal signals with additive white noise is a problem of significant interests in many signal processing applications, such as analysis of NMR data and system identification. The proposed algorithm estimates the signal parameters using a matrix pencil constructed from the measured data. To reduce the noise effect, rank deficient Hankel approximation of prediction matrix is used. We show that the performance of the estimation can be significantly improved by structured low rank approximation of the prediction matrix. Computer simulations also show that the noise threshold of our new matrix pencil algorithm is significantly low than those of the existing algorithms.en_US
dc.format.extent335403 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/5754
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 1996-35en_US
dc.subjectfilteringen_US
dc.subjectsignal processingen_US
dc.subjectSystems Integration Methodologyen_US
dc.titleA Structured Low Rank Matrix Pencil for Spectral Estimation and System Identificationen_US
dc.typeTechnical Reporten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
TR_96-35.pdf
Size:
327.54 KB
Format:
Adobe Portable Document Format
Download

Collections

Institute for Systems Research Technical Reports