Estimation of mixed spectrum using genetic algorithm

A. Sano, Y. Ashida, K. Ohnishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper proposes a method for estimating the mixed spectrum which is composed of line and continuous spectra, the latter of which is characterized by an AR or ARMA noise model. Line spectrum is represented by multiple sinusoids. In order to avoid simultaneous minimization of a prediction error criterion with respect to all unknown parameters, we give an efficient iterative algorithm for estimating the frequencies of the sinusoids and other parameters separately. By adopting the genetic algorithm in choice of initial values of the AR or ARMA parameters in the iterative estimation, we can attain a globally optimal estimates of unknown parameters. The frequency estimate is given by a modified Toeplitz approximation method using a shifted correlation matrix of observed signals. The effectiveness of the proposed algorithm is validated in numerical simulations.

Original languageEnglish
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages1625-1628
Number of pages4
Volume3
Publication statusPublished - 1995
EventProceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 2 (of 5) - Detroit, MI, USA
Duration: 1995 May 91995 May 12

Other

OtherProceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 2 (of 5)
CityDetroit, MI, USA
Period95/5/995/5/12

Fingerprint

genetic algorithms
Genetic algorithms
autoregressive moving average
sine waves
line spectra
estimating
continuous spectra
Computer simulation
estimates
optimization
predictions
approximation
simulation

ASJC Scopus subject areas

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

Cite this

Sano, A., Ashida, Y., & Ohnishi, K. (1995). Estimation of mixed spectrum using genetic algorithm. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 3, pp. 1625-1628)

Estimation of mixed spectrum using genetic algorithm. / Sano, A.; Ashida, Y.; Ohnishi, K.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 3 1995. p. 1625-1628.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sano, A, Ashida, Y & Ohnishi, K 1995, Estimation of mixed spectrum using genetic algorithm. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 3, pp. 1625-1628, Proceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 2 (of 5), Detroit, MI, USA, 95/5/9.
Sano A, Ashida Y, Ohnishi K. Estimation of mixed spectrum using genetic algorithm. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 3. 1995. p. 1625-1628
Sano, A. ; Ashida, Y. ; Ohnishi, K. / Estimation of mixed spectrum using genetic algorithm. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 3 1995. pp. 1625-1628
@inproceedings{b58899dcb07342be959f0a80624c9de7,
title = "Estimation of mixed spectrum using genetic algorithm",
abstract = "This paper proposes a method for estimating the mixed spectrum which is composed of line and continuous spectra, the latter of which is characterized by an AR or ARMA noise model. Line spectrum is represented by multiple sinusoids. In order to avoid simultaneous minimization of a prediction error criterion with respect to all unknown parameters, we give an efficient iterative algorithm for estimating the frequencies of the sinusoids and other parameters separately. By adopting the genetic algorithm in choice of initial values of the AR or ARMA parameters in the iterative estimation, we can attain a globally optimal estimates of unknown parameters. The frequency estimate is given by a modified Toeplitz approximation method using a shifted correlation matrix of observed signals. The effectiveness of the proposed algorithm is validated in numerical simulations.",
author = "A. Sano and Y. Ashida and K. Ohnishi",
year = "1995",
language = "English",
volume = "3",
pages = "1625--1628",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Estimation of mixed spectrum using genetic algorithm

AU - Sano, A.

AU - Ashida, Y.

AU - Ohnishi, K.

PY - 1995

Y1 - 1995

N2 - This paper proposes a method for estimating the mixed spectrum which is composed of line and continuous spectra, the latter of which is characterized by an AR or ARMA noise model. Line spectrum is represented by multiple sinusoids. In order to avoid simultaneous minimization of a prediction error criterion with respect to all unknown parameters, we give an efficient iterative algorithm for estimating the frequencies of the sinusoids and other parameters separately. By adopting the genetic algorithm in choice of initial values of the AR or ARMA parameters in the iterative estimation, we can attain a globally optimal estimates of unknown parameters. The frequency estimate is given by a modified Toeplitz approximation method using a shifted correlation matrix of observed signals. The effectiveness of the proposed algorithm is validated in numerical simulations.

AB - This paper proposes a method for estimating the mixed spectrum which is composed of line and continuous spectra, the latter of which is characterized by an AR or ARMA noise model. Line spectrum is represented by multiple sinusoids. In order to avoid simultaneous minimization of a prediction error criterion with respect to all unknown parameters, we give an efficient iterative algorithm for estimating the frequencies of the sinusoids and other parameters separately. By adopting the genetic algorithm in choice of initial values of the AR or ARMA parameters in the iterative estimation, we can attain a globally optimal estimates of unknown parameters. The frequency estimate is given by a modified Toeplitz approximation method using a shifted correlation matrix of observed signals. The effectiveness of the proposed algorithm is validated in numerical simulations.

UR - http://www.scopus.com/inward/record.url?scp=0028996332&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028996332&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028996332

VL - 3

SP - 1625

EP - 1628

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

ER -