Resonance-based signal decomposition: A new sparsity-enabled signal analysis method

Research output: Contribution to journalArticle

Abstract

Numerous signals arising from physiological and physical processes, in addition to being non-stationary, are moreover a mixture of sustained oscillations and non-oscillatory transients that are difficult to disentangle by linear methods. Examples of such signals include speech, biomedical, and geophysical signals. Therefore, this paper describes a new nonlinear signal analysis method based on signal resonance, rather than on frequency or scale, as provided by the Fourier and wavelet transforms. This method expresses a signal as the sum of a 'high-resonance' and a 'low-resonance' component - a high-resonance component being a signal consisting of multiple simultaneous sustained oscillations; a low-resonance component being a signal consisting of non-oscillatory transients of unspecified shape and duration. The resonance-based signal decomposition algorithm presented in this paper utilizes sparse signal representations, morphological component analysis, and constant-Q (wavelet) transforms with adjustable Q-factor.

Original languageEnglish (US)
Pages (from-to)2793-2809
Number of pages17
JournalSignal Processing
Volume91
Issue number12
DOIs
StatePublished - Dec 2011

Fingerprint

Signal analysis
Decomposition
Wavelet transforms
Fourier transforms

Keywords

  • Constant-Q transform
  • Morphological component analysis
  • Sparse signal representation
  • Wavelet transform

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Resonance-based signal decomposition : A new sparsity-enabled signal analysis method. / Selesnick, Ivan.

In: Signal Processing, Vol. 91, No. 12, 12.2011, p. 2793-2809.

Research output: Contribution to journalArticle

@article{c64051dce6d5405588d5231d6aa0187d,
title = "Resonance-based signal decomposition: A new sparsity-enabled signal analysis method",
abstract = "Numerous signals arising from physiological and physical processes, in addition to being non-stationary, are moreover a mixture of sustained oscillations and non-oscillatory transients that are difficult to disentangle by linear methods. Examples of such signals include speech, biomedical, and geophysical signals. Therefore, this paper describes a new nonlinear signal analysis method based on signal resonance, rather than on frequency or scale, as provided by the Fourier and wavelet transforms. This method expresses a signal as the sum of a 'high-resonance' and a 'low-resonance' component - a high-resonance component being a signal consisting of multiple simultaneous sustained oscillations; a low-resonance component being a signal consisting of non-oscillatory transients of unspecified shape and duration. The resonance-based signal decomposition algorithm presented in this paper utilizes sparse signal representations, morphological component analysis, and constant-Q (wavelet) transforms with adjustable Q-factor.",
keywords = "Constant-Q transform, Morphological component analysis, Sparse signal representation, Wavelet transform",
author = "Ivan Selesnick",
year = "2011",
month = "12",
doi = "10.1016/j.sigpro.2010.10.018",
language = "English (US)",
volume = "91",
pages = "2793--2809",
journal = "Signal Processing",
issn = "0165-1684",
publisher = "Elsevier",
number = "12",

}

TY - JOUR

T1 - Resonance-based signal decomposition

T2 - A new sparsity-enabled signal analysis method

AU - Selesnick, Ivan

PY - 2011/12

Y1 - 2011/12

N2 - Numerous signals arising from physiological and physical processes, in addition to being non-stationary, are moreover a mixture of sustained oscillations and non-oscillatory transients that are difficult to disentangle by linear methods. Examples of such signals include speech, biomedical, and geophysical signals. Therefore, this paper describes a new nonlinear signal analysis method based on signal resonance, rather than on frequency or scale, as provided by the Fourier and wavelet transforms. This method expresses a signal as the sum of a 'high-resonance' and a 'low-resonance' component - a high-resonance component being a signal consisting of multiple simultaneous sustained oscillations; a low-resonance component being a signal consisting of non-oscillatory transients of unspecified shape and duration. The resonance-based signal decomposition algorithm presented in this paper utilizes sparse signal representations, morphological component analysis, and constant-Q (wavelet) transforms with adjustable Q-factor.

AB - Numerous signals arising from physiological and physical processes, in addition to being non-stationary, are moreover a mixture of sustained oscillations and non-oscillatory transients that are difficult to disentangle by linear methods. Examples of such signals include speech, biomedical, and geophysical signals. Therefore, this paper describes a new nonlinear signal analysis method based on signal resonance, rather than on frequency or scale, as provided by the Fourier and wavelet transforms. This method expresses a signal as the sum of a 'high-resonance' and a 'low-resonance' component - a high-resonance component being a signal consisting of multiple simultaneous sustained oscillations; a low-resonance component being a signal consisting of non-oscillatory transients of unspecified shape and duration. The resonance-based signal decomposition algorithm presented in this paper utilizes sparse signal representations, morphological component analysis, and constant-Q (wavelet) transforms with adjustable Q-factor.

KW - Constant-Q transform

KW - Morphological component analysis

KW - Sparse signal representation

KW - Wavelet transform

UR - http://www.scopus.com/inward/record.url?scp=80051471430&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051471430&partnerID=8YFLogxK

U2 - 10.1016/j.sigpro.2010.10.018

DO - 10.1016/j.sigpro.2010.10.018

M3 - Article

AN - SCOPUS:80051471430

VL - 91

SP - 2793

EP - 2809

JO - Signal Processing

JF - Signal Processing

SN - 0165-1684

IS - 12

ER -