A neural network and post-processing for estimating the values of error data

Jihoon Lee, Yousok Kim, Se Woon Choi, Hyo Seon Park

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

Abstract

A sensor network is a key factor for successful structural health monitoring (SHM). Although stable sensor network system is deployed in the structure for measurement, it is often inevitable to face measurement faults. In order to secure the continuous evaluation of targeted structure in cases where the measurement faults occur, appropriate techniques to estimate omitted or error data are necessary. In this research, back-propagation neural network is adopted as a basic estimation method. Then, a concept of post-processing is proposed to improve an accuracy of estimation obtained from the neural network. The results of simulation to verify performance of estimation are also shown.

Original languageEnglish
Title of host publicationSENSORNETS 2013 - Proceedings of the 2nd International Conference on Sensor Networks
Pages205-208
Number of pages4
Publication statusPublished - 2013 May 30
Event2nd International Conference on Sensor Networks, SENSORNETS 2013 - Barcelona, Spain
Duration: 2013 Feb 192013 Feb 21

Other

Other2nd International Conference on Sensor Networks, SENSORNETS 2013
CountrySpain
CityBarcelona
Period13/2/1913/2/21

Fingerprint

Neural networks
Sensor networks
Processing
Structural health monitoring
Backpropagation

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Lee, J., Kim, Y., Choi, S. W., & Park, H. S. (2013). A neural network and post-processing for estimating the values of error data. In SENSORNETS 2013 - Proceedings of the 2nd International Conference on Sensor Networks (pp. 205-208)
Lee, Jihoon ; Kim, Yousok ; Choi, Se Woon ; Park, Hyo Seon. / A neural network and post-processing for estimating the values of error data. SENSORNETS 2013 - Proceedings of the 2nd International Conference on Sensor Networks. 2013. pp. 205-208
@inproceedings{73f8f2b47a76431c8686046d8d067859,
title = "A neural network and post-processing for estimating the values of error data",
abstract = "A sensor network is a key factor for successful structural health monitoring (SHM). Although stable sensor network system is deployed in the structure for measurement, it is often inevitable to face measurement faults. In order to secure the continuous evaluation of targeted structure in cases where the measurement faults occur, appropriate techniques to estimate omitted or error data are necessary. In this research, back-propagation neural network is adopted as a basic estimation method. Then, a concept of post-processing is proposed to improve an accuracy of estimation obtained from the neural network. The results of simulation to verify performance of estimation are also shown.",
author = "Jihoon Lee and Yousok Kim and Choi, {Se Woon} and Park, {Hyo Seon}",
year = "2013",
month = "5",
day = "30",
language = "English",
isbn = "9789898565457",
pages = "205--208",
booktitle = "SENSORNETS 2013 - Proceedings of the 2nd International Conference on Sensor Networks",

}

Lee, J, Kim, Y, Choi, SW & Park, HS 2013, A neural network and post-processing for estimating the values of error data. in SENSORNETS 2013 - Proceedings of the 2nd International Conference on Sensor Networks. pp. 205-208, 2nd International Conference on Sensor Networks, SENSORNETS 2013, Barcelona, Spain, 13/2/19.

A neural network and post-processing for estimating the values of error data. / Lee, Jihoon; Kim, Yousok; Choi, Se Woon; Park, Hyo Seon.

SENSORNETS 2013 - Proceedings of the 2nd International Conference on Sensor Networks. 2013. p. 205-208.

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

TY - GEN

T1 - A neural network and post-processing for estimating the values of error data

AU - Lee, Jihoon

AU - Kim, Yousok

AU - Choi, Se Woon

AU - Park, Hyo Seon

PY - 2013/5/30

Y1 - 2013/5/30

N2 - A sensor network is a key factor for successful structural health monitoring (SHM). Although stable sensor network system is deployed in the structure for measurement, it is often inevitable to face measurement faults. In order to secure the continuous evaluation of targeted structure in cases where the measurement faults occur, appropriate techniques to estimate omitted or error data are necessary. In this research, back-propagation neural network is adopted as a basic estimation method. Then, a concept of post-processing is proposed to improve an accuracy of estimation obtained from the neural network. The results of simulation to verify performance of estimation are also shown.

AB - A sensor network is a key factor for successful structural health monitoring (SHM). Although stable sensor network system is deployed in the structure for measurement, it is often inevitable to face measurement faults. In order to secure the continuous evaluation of targeted structure in cases where the measurement faults occur, appropriate techniques to estimate omitted or error data are necessary. In this research, back-propagation neural network is adopted as a basic estimation method. Then, a concept of post-processing is proposed to improve an accuracy of estimation obtained from the neural network. The results of simulation to verify performance of estimation are also shown.

UR - http://www.scopus.com/inward/record.url?scp=84878205268&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878205268&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789898565457

SP - 205

EP - 208

BT - SENSORNETS 2013 - Proceedings of the 2nd International Conference on Sensor Networks

ER -

Lee J, Kim Y, Choi SW, Park HS. A neural network and post-processing for estimating the values of error data. In SENSORNETS 2013 - Proceedings of the 2nd International Conference on Sensor Networks. 2013. p. 205-208