Minimum risk thresholds for data with heavy noise

M.H. Jansen

doi:10.1109/LSP.2006.870355

Minimum risk thresholds for data with heavy noise

M.H. Jansen

Statistics

Research output: Contribution to journal › Article › Academic › peer-review

23 Citations (Scopus)

Abstract

In the estimation of data with many zeros (sparse data), such as wavelet coefficients, thresholding is a common technique. This letter investigates the behavior of the minimum risk threshold for large values of the noise standard deviation. It finds that the threshold depends quadratically on the noise standard deviation. The relevance of this result is situated in the context of both Bayesian and universal thresholding.

Original language	English
Pages (from-to)	296-299
Journal	IEEE Signal Processing Letters
Volume	13
Issue number	5
DOIs	https://doi.org/10.1109/LSP.2006.870355
Publication status	Published - 2006

Access to Document

10.1109/LSP.2006.870355

Cite this

@article{324fd992127a4289aea0612d89776c94,

title = "Minimum risk thresholds for data with heavy noise",

abstract = "In the estimation of data with many zeros (sparse data), such as wavelet coefficients, thresholding is a common technique. This letter investigates the behavior of the minimum risk threshold for large values of the noise standard deviation. It finds that the threshold depends quadratically on the noise standard deviation. The relevance of this result is situated in the context of both Bayesian and universal thresholding.",

author = "M.H. Jansen",

year = "2006",

doi = "10.1109/LSP.2006.870355",

language = "English",

volume = "13",

pages = "296--299",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers",

number = "5",

}

TY - JOUR

T1 - Minimum risk thresholds for data with heavy noise

AU - Jansen, M.H.

PY - 2006

Y1 - 2006

N2 - In the estimation of data with many zeros (sparse data), such as wavelet coefficients, thresholding is a common technique. This letter investigates the behavior of the minimum risk threshold for large values of the noise standard deviation. It finds that the threshold depends quadratically on the noise standard deviation. The relevance of this result is situated in the context of both Bayesian and universal thresholding.

AB - In the estimation of data with many zeros (sparse data), such as wavelet coefficients, thresholding is a common technique. This letter investigates the behavior of the minimum risk threshold for large values of the noise standard deviation. It finds that the threshold depends quadratically on the noise standard deviation. The relevance of this result is situated in the context of both Bayesian and universal thresholding.

U2 - 10.1109/LSP.2006.870355

DO - 10.1109/LSP.2006.870355

M3 - Article

SN - 1070-9908

VL - 13

SP - 296

EP - 299

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 5

ER -

Minimum risk thresholds for data with heavy noise

Abstract

Access to Document

Fingerprint

Cite this