An artificial neural network based approach for power spectrum estimation subject to limited and/or missing data

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • L. A. Comerford
  • I. A. Kougioumtzoglou
  • M. Beer

External Research Organisations

  • University of Liverpool
View graph of relations

Details

Original languageEnglish
Title of host publicationSafety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures
Subtitle of host publicationProceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013
Place of PublicationBoca Raton
Pages1083-1090
Number of pages8
ISBN (electronic)978-1-315-88488-2
Publication statusPublished - 2013
Externally publishedYes
Event11th International Conference on Structural Safety and Reliability, ICOSSAR 2013 - New York, NY, United States
Duration: 16 Jun 201320 Jun 2013

Abstract

AnArtificial Neural Network (ANN) approach is presented as a possible solution to overcoming the problems associated with missing data in spectral analysis and/or simulation of stationary and non-stationary stochastic processes. By using an ANN to capture patterns present in the available data, gaps can then be filled or entirely new processes generated.A feed-forwardANN is used with ordered inputs and Gaussian white noise to represent missing data during learning. The solution is broadly applicable in many circumstances due to the fact that it assumes no prior knowledge of the underlying statistics of the process. Specifically, to present the method in context, this paper addresses some of the challenges associated with preparing data for environmental simulation load models (time dependent, 1-dimensional).

ASJC Scopus subject areas

Cite this

An artificial neural network based approach for power spectrum estimation subject to limited and/or missing data. / Comerford, L. A.; Kougioumtzoglou, I. A.; Beer, M.
Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures: Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013. Boca Raton, 2013. p. 1083-1090.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Comerford, LA, Kougioumtzoglou, IA & Beer, M 2013, An artificial neural network based approach for power spectrum estimation subject to limited and/or missing data. in Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures: Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013. Boca Raton, pp. 1083-1090, 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013, New York, NY, United States, 16 Jun 2013.
Comerford, L. A., Kougioumtzoglou, I. A., & Beer, M. (2013). An artificial neural network based approach for power spectrum estimation subject to limited and/or missing data. In Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures: Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013 (pp. 1083-1090).
Comerford LA, Kougioumtzoglou IA, Beer M. An artificial neural network based approach for power spectrum estimation subject to limited and/or missing data. In Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures: Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013. Boca Raton. 2013. p. 1083-1090
Comerford, L. A. ; Kougioumtzoglou, I. A. ; Beer, M. / An artificial neural network based approach for power spectrum estimation subject to limited and/or missing data. Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures: Proceedings of the 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013. Boca Raton, 2013. pp. 1083-1090
Download
@inproceedings{6c3e80ace30c4c9aaf3165e13d68a506,
title = "An artificial neural network based approach for power spectrum estimation subject to limited and/or missing data",
abstract = "AnArtificial Neural Network (ANN) approach is presented as a possible solution to overcoming the problems associated with missing data in spectral analysis and/or simulation of stationary and non-stationary stochastic processes. By using an ANN to capture patterns present in the available data, gaps can then be filled or entirely new processes generated.A feed-forwardANN is used with ordered inputs and Gaussian white noise to represent missing data during learning. The solution is broadly applicable in many circumstances due to the fact that it assumes no prior knowledge of the underlying statistics of the process. Specifically, to present the method in context, this paper addresses some of the challenges associated with preparing data for environmental simulation load models (time dependent, 1-dimensional).",
author = "Comerford, {L. A.} and Kougioumtzoglou, {I. A.} and M. Beer",
year = "2013",
language = "English",
isbn = "9781138000865",
pages = "1083--1090",
booktitle = "Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures",
note = "11th International Conference on Structural Safety and Reliability, ICOSSAR 2013 ; Conference date: 16-06-2013 Through 20-06-2013",

}

Download

TY - GEN

T1 - An artificial neural network based approach for power spectrum estimation subject to limited and/or missing data

AU - Comerford, L. A.

AU - Kougioumtzoglou, I. A.

AU - Beer, M.

PY - 2013

Y1 - 2013

N2 - AnArtificial Neural Network (ANN) approach is presented as a possible solution to overcoming the problems associated with missing data in spectral analysis and/or simulation of stationary and non-stationary stochastic processes. By using an ANN to capture patterns present in the available data, gaps can then be filled or entirely new processes generated.A feed-forwardANN is used with ordered inputs and Gaussian white noise to represent missing data during learning. The solution is broadly applicable in many circumstances due to the fact that it assumes no prior knowledge of the underlying statistics of the process. Specifically, to present the method in context, this paper addresses some of the challenges associated with preparing data for environmental simulation load models (time dependent, 1-dimensional).

AB - AnArtificial Neural Network (ANN) approach is presented as a possible solution to overcoming the problems associated with missing data in spectral analysis and/or simulation of stationary and non-stationary stochastic processes. By using an ANN to capture patterns present in the available data, gaps can then be filled or entirely new processes generated.A feed-forwardANN is used with ordered inputs and Gaussian white noise to represent missing data during learning. The solution is broadly applicable in many circumstances due to the fact that it assumes no prior knowledge of the underlying statistics of the process. Specifically, to present the method in context, this paper addresses some of the challenges associated with preparing data for environmental simulation load models (time dependent, 1-dimensional).

UR - http://www.scopus.com/inward/record.url?scp=84892387339&partnerID=8YFLogxK

UR - https://doi.org/10.1201/b16387

M3 - Conference contribution

AN - SCOPUS:84892387339

SN - 9781138000865

SP - 1083

EP - 1090

BT - Safety, Reliability, Risk and Life-Cycle Performance of Structures and Infrastructures

CY - Boca Raton

T2 - 11th International Conference on Structural Safety and Reliability, ICOSSAR 2013

Y2 - 16 June 2013 through 20 June 2013

ER -

By the same author(s)