Approximating the best linear unbiased estimator of non-gaussian signals with gaussian noise

Masashi Sugiyama, Motoaki Kawanabe, Gilles Blanchard, Klaus Muller

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Obtaining the best linear unbiased estimator (BLUE) of noisy signals is a traditional but powerful approach to noise reduction. Explicitly computing the BLUE usually requires the prior knowledge of the noise covariance matrix and the subspace to which the true signal belongs. However, such prior knowledge is often unavailable in reality, which prevents us from applying the BLUE to real-world problems. To cope with this problem, we give a practical procedure for approximating the BLUE without such prior knowledge. Our additional assumption is that the true signal follows a non-Gaussian distribution while the noise is Gaussian.

Original languageEnglish
Pages (from-to)1577-1580
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE91-D
Issue number5
DOIs
Publication statusPublished - 2008 May 1
Externally publishedYes

Fingerprint

Covariance matrix
Noise abatement

Keywords

  • Best linear unbiased estimator (BLUE)
  • Gaussian noise
  • Non-Gaussian component analysis (NGCA)
  • Signal denoising

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Approximating the best linear unbiased estimator of non-gaussian signals with gaussian noise. / Sugiyama, Masashi; Kawanabe, Motoaki; Blanchard, Gilles; Muller, Klaus.

In: IEICE Transactions on Information and Systems, Vol. E91-D, No. 5, 01.05.2008, p. 1577-1580.

Research output: Contribution to journalArticle

Sugiyama, Masashi ; Kawanabe, Motoaki ; Blanchard, Gilles ; Muller, Klaus. / Approximating the best linear unbiased estimator of non-gaussian signals with gaussian noise. In: IEICE Transactions on Information and Systems. 2008 ; Vol. E91-D, No. 5. pp. 1577-1580.
@article{2c1915b8a73a4f6bb2b8fcdb04673e63,
title = "Approximating the best linear unbiased estimator of non-gaussian signals with gaussian noise",
abstract = "Obtaining the best linear unbiased estimator (BLUE) of noisy signals is a traditional but powerful approach to noise reduction. Explicitly computing the BLUE usually requires the prior knowledge of the noise covariance matrix and the subspace to which the true signal belongs. However, such prior knowledge is often unavailable in reality, which prevents us from applying the BLUE to real-world problems. To cope with this problem, we give a practical procedure for approximating the BLUE without such prior knowledge. Our additional assumption is that the true signal follows a non-Gaussian distribution while the noise is Gaussian.",
keywords = "Best linear unbiased estimator (BLUE), Gaussian noise, Non-Gaussian component analysis (NGCA), Signal denoising",
author = "Masashi Sugiyama and Motoaki Kawanabe and Gilles Blanchard and Klaus Muller",
year = "2008",
month = "5",
day = "1",
doi = "10.1093/ietisy/e91-d.5.1577",
language = "English",
volume = "E91-D",
pages = "1577--1580",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "5",

}

TY - JOUR

T1 - Approximating the best linear unbiased estimator of non-gaussian signals with gaussian noise

AU - Sugiyama, Masashi

AU - Kawanabe, Motoaki

AU - Blanchard, Gilles

AU - Muller, Klaus

PY - 2008/5/1

Y1 - 2008/5/1

N2 - Obtaining the best linear unbiased estimator (BLUE) of noisy signals is a traditional but powerful approach to noise reduction. Explicitly computing the BLUE usually requires the prior knowledge of the noise covariance matrix and the subspace to which the true signal belongs. However, such prior knowledge is often unavailable in reality, which prevents us from applying the BLUE to real-world problems. To cope with this problem, we give a practical procedure for approximating the BLUE without such prior knowledge. Our additional assumption is that the true signal follows a non-Gaussian distribution while the noise is Gaussian.

AB - Obtaining the best linear unbiased estimator (BLUE) of noisy signals is a traditional but powerful approach to noise reduction. Explicitly computing the BLUE usually requires the prior knowledge of the noise covariance matrix and the subspace to which the true signal belongs. However, such prior knowledge is often unavailable in reality, which prevents us from applying the BLUE to real-world problems. To cope with this problem, we give a practical procedure for approximating the BLUE without such prior knowledge. Our additional assumption is that the true signal follows a non-Gaussian distribution while the noise is Gaussian.

KW - Best linear unbiased estimator (BLUE)

KW - Gaussian noise

KW - Non-Gaussian component analysis (NGCA)

KW - Signal denoising

UR - http://www.scopus.com/inward/record.url?scp=68149172379&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=68149172379&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e91-d.5.1577

DO - 10.1093/ietisy/e91-d.5.1577

M3 - Article

VL - E91-D

SP - 1577

EP - 1580

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 5

ER -