Signal extrapolation based on generalized singular value decomposition using prior information

Akira Sano, Hiroyuki Tsuji, Hiromitsu Ohmori

研究成果: Conference contribution

抄録

Extrapolation of band-limited signals in noisy conditions is an ill-posed least-squares estimation problem. To stabilize the extrapolation, derivative smoothness of signals to be extrapolated is introduced to a weighted-least-squares error criterion as prior information. One can adjust the weighting of the smoothness by employing multiple regularization parameters to be determined optimally. The extrapolated signal is given by using the generalized singular value decomposition, which is modified by the regularization. On the basis of a Bayesian statistical approach, a new information-theoretic criterion is presented to determined the optimal regularization parameters, which can give optimal balance between the smoothness prior and the observed signal data to attain stabilized extrapolation by optimal regularization.

元の言語English
ホスト出版物のタイトルProceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
出版者Publ by IEEE
ページ1749-1752
ページ数4
3
ISBN(印刷物)078030033
出版物ステータスPublished - 1991
外部発表Yes
イベントProceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91 - Toronto, Ont, Can
継続期間: 1991 5 141991 5 17

Other

OtherProceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91
Toronto, Ont, Can
期間91/5/1491/5/17

Fingerprint

Singular value decomposition
Extrapolation
extrapolation
decomposition
Derivatives

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

これを引用

Sano, A., Tsuji, H., & Ohmori, H. (1991). Signal extrapolation based on generalized singular value decomposition using prior information. : Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing (巻 3, pp. 1749-1752). Publ by IEEE.

Signal extrapolation based on generalized singular value decomposition using prior information. / Sano, Akira; Tsuji, Hiroyuki; Ohmori, Hiromitsu.

Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. 巻 3 Publ by IEEE, 1991. p. 1749-1752.

研究成果: Conference contribution

Sano, A, Tsuji, H & Ohmori, H 1991, Signal extrapolation based on generalized singular value decomposition using prior information. : Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. 巻. 3, Publ by IEEE, pp. 1749-1752, Proceedings of the 1991 International Conference on Acoustics, Speech, and Signal Processing - ICASSP 91, Toronto, Ont, Can, 91/5/14.
Sano A, Tsuji H, Ohmori H. Signal extrapolation based on generalized singular value decomposition using prior information. : Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. 巻 3. Publ by IEEE. 1991. p. 1749-1752
Sano, Akira ; Tsuji, Hiroyuki ; Ohmori, Hiromitsu. / Signal extrapolation based on generalized singular value decomposition using prior information. Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. 巻 3 Publ by IEEE, 1991. pp. 1749-1752
@inproceedings{c5e57746a5c349fbb9ac36b77fcc56dd,
title = "Signal extrapolation based on generalized singular value decomposition using prior information",
abstract = "Extrapolation of band-limited signals in noisy conditions is an ill-posed least-squares estimation problem. To stabilize the extrapolation, derivative smoothness of signals to be extrapolated is introduced to a weighted-least-squares error criterion as prior information. One can adjust the weighting of the smoothness by employing multiple regularization parameters to be determined optimally. The extrapolated signal is given by using the generalized singular value decomposition, which is modified by the regularization. On the basis of a Bayesian statistical approach, a new information-theoretic criterion is presented to determined the optimal regularization parameters, which can give optimal balance between the smoothness prior and the observed signal data to attain stabilized extrapolation by optimal regularization.",
author = "Akira Sano and Hiroyuki Tsuji and Hiromitsu Ohmori",
year = "1991",
language = "English",
isbn = "078030033",
volume = "3",
pages = "1749--1752",
booktitle = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Signal extrapolation based on generalized singular value decomposition using prior information

AU - Sano, Akira

AU - Tsuji, Hiroyuki

AU - Ohmori, Hiromitsu

PY - 1991

Y1 - 1991

N2 - Extrapolation of band-limited signals in noisy conditions is an ill-posed least-squares estimation problem. To stabilize the extrapolation, derivative smoothness of signals to be extrapolated is introduced to a weighted-least-squares error criterion as prior information. One can adjust the weighting of the smoothness by employing multiple regularization parameters to be determined optimally. The extrapolated signal is given by using the generalized singular value decomposition, which is modified by the regularization. On the basis of a Bayesian statistical approach, a new information-theoretic criterion is presented to determined the optimal regularization parameters, which can give optimal balance between the smoothness prior and the observed signal data to attain stabilized extrapolation by optimal regularization.

AB - Extrapolation of band-limited signals in noisy conditions is an ill-posed least-squares estimation problem. To stabilize the extrapolation, derivative smoothness of signals to be extrapolated is introduced to a weighted-least-squares error criterion as prior information. One can adjust the weighting of the smoothness by employing multiple regularization parameters to be determined optimally. The extrapolated signal is given by using the generalized singular value decomposition, which is modified by the regularization. On the basis of a Bayesian statistical approach, a new information-theoretic criterion is presented to determined the optimal regularization parameters, which can give optimal balance between the smoothness prior and the observed signal data to attain stabilized extrapolation by optimal regularization.

UR - http://www.scopus.com/inward/record.url?scp=0026287634&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026287634&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026287634

SN - 078030033

VL - 3

SP - 1749

EP - 1752

BT - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

PB - Publ by IEEE

ER -