Robust blind extraction of a signal with the best match to a prescribed autocorrelation

B.B.A.J. Bloemendal; J. Laar, van de; P.C.W. Sommen

Robust blind extraction of a signal with the best match to a prescribed autocorrelation

B.B.A.J. Bloemendal, J. Laar, van de, P.C.W. Sommen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Several blind extraction algorithms have been proposed that extract some signal of interest from a mixture of signals. We propose a novel blind extraction algorithm that extracts the signal that has an autocorrelation closest to a prescribed autocorrelation that serves as a mold. Based on the mold we perform a linear transformation of sensor correlation matri- ces. This transformation allows for the construction of a matrix with a specific eigenstructure. Each eigenvalue is related to the Euclidean distance between the mold and the actual autocorrelation of one of the source signals. The extraction filter that extracts the source signal with an auto-correlation closest to the mold is identified as the eigenvector that corresponds to the smallest eigenvalue. We show that this approach is more robust to noise than methods from literature, while it exploits comparable a priori information.The results are validated by means of simulations.

Original language	English
Title of host publication	Proceedings of the 18th European Signal Processing Conference (EUSIPCO 2010), 23-27 August 2010, Aalborg, Denmark
Pages	1811-1815
Publication status	Published - 2010

Fingerprint Dive into the research topics of 'Robust blind extraction of a signal with the best match to a prescribed autocorrelation'. Together they form a unique fingerprint.

Cite this

@inproceedings{7cb6f4b7f5ad48ff8ca3a01987b82793,

title = "Robust blind extraction of a signal with the best match to a prescribed autocorrelation",

abstract = "Several blind extraction algorithms have been proposed that extract some signal of interest from a mixture of signals. We propose a novel blind extraction algorithm that extracts the signal that has an autocorrelation closest to a prescribed autocorrelation that serves as a mold. Based on the mold we perform a linear transformation of sensor correlation matri- ces. This transformation allows for the construction of a matrix with a specific eigenstructure. Each eigenvalue is related to the Euclidean distance between the mold and the actual autocorrelation of one of the source signals. The extraction filter that extracts the source signal with an auto-correlation closest to the mold is identified as the eigenvector that corresponds to the smallest eigenvalue. We show that this approach is more robust to noise than methods from literature, while it exploits comparable a priori information.The results are validated by means of simulations.",

author = "B.B.A.J. Bloemendal and {Laar, van de}, J. and P.C.W. Sommen",

year = "2010",

language = "English",

pages = "1811--1815",

booktitle = "Proceedings of the 18th European Signal Processing Conference (EUSIPCO 2010), 23-27 August 2010, Aalborg, Denmark",

}

Robust blind extraction of a signal with the best match to a prescribed autocorrelation. / Bloemendal, B.B.A.J.; Laar, van de, J.; Sommen, P.C.W.

Proceedings of the 18th European Signal Processing Conference (EUSIPCO 2010), 23-27 August 2010, Aalborg, Denmark. 2010. p. 1811-1815.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Robust blind extraction of a signal with the best match to a prescribed autocorrelation

AU - Bloemendal, B.B.A.J.

AU - Laar, van de, J.

AU - Sommen, P.C.W.

PY - 2010

Y1 - 2010

N2 - Several blind extraction algorithms have been proposed that extract some signal of interest from a mixture of signals. We propose a novel blind extraction algorithm that extracts the signal that has an autocorrelation closest to a prescribed autocorrelation that serves as a mold. Based on the mold we perform a linear transformation of sensor correlation matri- ces. This transformation allows for the construction of a matrix with a specific eigenstructure. Each eigenvalue is related to the Euclidean distance between the mold and the actual autocorrelation of one of the source signals. The extraction filter that extracts the source signal with an auto-correlation closest to the mold is identified as the eigenvector that corresponds to the smallest eigenvalue. We show that this approach is more robust to noise than methods from literature, while it exploits comparable a priori information.The results are validated by means of simulations.

AB - Several blind extraction algorithms have been proposed that extract some signal of interest from a mixture of signals. We propose a novel blind extraction algorithm that extracts the signal that has an autocorrelation closest to a prescribed autocorrelation that serves as a mold. Based on the mold we perform a linear transformation of sensor correlation matri- ces. This transformation allows for the construction of a matrix with a specific eigenstructure. Each eigenvalue is related to the Euclidean distance between the mold and the actual autocorrelation of one of the source signals. The extraction filter that extracts the source signal with an auto-correlation closest to the mold is identified as the eigenvector that corresponds to the smallest eigenvalue. We show that this approach is more robust to noise than methods from literature, while it exploits comparable a priori information.The results are validated by means of simulations.

M3 - Conference contribution

SP - 1811

EP - 1815

BT - Proceedings of the 18th European Signal Processing Conference (EUSIPCO 2010), 23-27 August 2010, Aalborg, Denmark

ER -