A method to classify the signals from artificially prepared defects in GIS using the decision tree method

H. Hirose, T. Ohhata, Y. Kotou, S. Matsuda, M. Hikita, T. Nishimura, S. Ohtsuka, Satoshi Matsumoto, S. Tsuru, J. Ichimaru

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

1 Citation (Scopus)

Abstract

On-line diagnosing of GIS (Gas Insulated Switchgears) requires the pattern classification and identification of signals that are emitted from GIS. To classify the patterns correctly, substantial data sets that are emitted by artificially mimicked defects in GIS are needed. Applying the neural networks to the data sets, in general, identification methods of defects in GIS have widely been developed. Some identification system shows a good success such that the misclassification rate is reduced to below 5%; the key features in identification, however, are not obviously revealed in neural networks systems because of nonlinear network structures. The decision tree method that classifies the signals using the feature rules in plain graphical representations can explains the classification rules in clear forms. We applied the decision tree classification method to the signals emitted from the signals by artificially prepared defects in GIS, and find that the method shows a good classification rates over 95% which are comparable to that in neural networks. We also discuss the robustness from noise, and compare the results of the misclassification rates by the two methods.

Original languageEnglish
Title of host publicationProceedings of the International Symposium on Electrical Insulating Materials
Pages885-888
Number of pages4
Volume3
Publication statusPublished - 2005
Externally publishedYes
Event2005 International Symposium on Electrical Insulating Materials, ISEIM 2005 - Kitakyushu
Duration: 2005 Jun 52005 Jun 9

Other

Other2005 International Symposium on Electrical Insulating Materials, ISEIM 2005
CityKitakyushu
Period05/6/505/6/9

Fingerprint

Electric switchgear
Decision trees
Gases
Defects
Neural networks
Nonlinear networks
Pattern recognition
Identification (control systems)

ASJC Scopus subject areas

  • Engineering(all)
  • Materials Science(all)

Cite this

Hirose, H., Ohhata, T., Kotou, Y., Matsuda, S., Hikita, M., Nishimura, T., ... Ichimaru, J. (2005). A method to classify the signals from artificially prepared defects in GIS using the decision tree method. In Proceedings of the International Symposium on Electrical Insulating Materials (Vol. 3, pp. 885-888)

A method to classify the signals from artificially prepared defects in GIS using the decision tree method. / Hirose, H.; Ohhata, T.; Kotou, Y.; Matsuda, S.; Hikita, M.; Nishimura, T.; Ohtsuka, S.; Matsumoto, Satoshi; Tsuru, S.; Ichimaru, J.

Proceedings of the International Symposium on Electrical Insulating Materials. Vol. 3 2005. p. 885-888.

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

Hirose, H, Ohhata, T, Kotou, Y, Matsuda, S, Hikita, M, Nishimura, T, Ohtsuka, S, Matsumoto, S, Tsuru, S & Ichimaru, J 2005, A method to classify the signals from artificially prepared defects in GIS using the decision tree method. in Proceedings of the International Symposium on Electrical Insulating Materials. vol. 3, pp. 885-888, 2005 International Symposium on Electrical Insulating Materials, ISEIM 2005, Kitakyushu, 05/6/5.
Hirose H, Ohhata T, Kotou Y, Matsuda S, Hikita M, Nishimura T et al. A method to classify the signals from artificially prepared defects in GIS using the decision tree method. In Proceedings of the International Symposium on Electrical Insulating Materials. Vol. 3. 2005. p. 885-888
Hirose, H. ; Ohhata, T. ; Kotou, Y. ; Matsuda, S. ; Hikita, M. ; Nishimura, T. ; Ohtsuka, S. ; Matsumoto, Satoshi ; Tsuru, S. ; Ichimaru, J. / A method to classify the signals from artificially prepared defects in GIS using the decision tree method. Proceedings of the International Symposium on Electrical Insulating Materials. Vol. 3 2005. pp. 885-888
@inproceedings{0ee3536a93c14764b3646b1b3e49fe3c,
title = "A method to classify the signals from artificially prepared defects in GIS using the decision tree method",
abstract = "On-line diagnosing of GIS (Gas Insulated Switchgears) requires the pattern classification and identification of signals that are emitted from GIS. To classify the patterns correctly, substantial data sets that are emitted by artificially mimicked defects in GIS are needed. Applying the neural networks to the data sets, in general, identification methods of defects in GIS have widely been developed. Some identification system shows a good success such that the misclassification rate is reduced to below 5{\%}; the key features in identification, however, are not obviously revealed in neural networks systems because of nonlinear network structures. The decision tree method that classifies the signals using the feature rules in plain graphical representations can explains the classification rules in clear forms. We applied the decision tree classification method to the signals emitted from the signals by artificially prepared defects in GIS, and find that the method shows a good classification rates over 95{\%} which are comparable to that in neural networks. We also discuss the robustness from noise, and compare the results of the misclassification rates by the two methods.",
author = "H. Hirose and T. Ohhata and Y. Kotou and S. Matsuda and M. Hikita and T. Nishimura and S. Ohtsuka and Satoshi Matsumoto and S. Tsuru and J. Ichimaru",
year = "2005",
language = "English",
volume = "3",
pages = "885--888",
booktitle = "Proceedings of the International Symposium on Electrical Insulating Materials",

}

TY - GEN

T1 - A method to classify the signals from artificially prepared defects in GIS using the decision tree method

AU - Hirose, H.

AU - Ohhata, T.

AU - Kotou, Y.

AU - Matsuda, S.

AU - Hikita, M.

AU - Nishimura, T.

AU - Ohtsuka, S.

AU - Matsumoto, Satoshi

AU - Tsuru, S.

AU - Ichimaru, J.

PY - 2005

Y1 - 2005

N2 - On-line diagnosing of GIS (Gas Insulated Switchgears) requires the pattern classification and identification of signals that are emitted from GIS. To classify the patterns correctly, substantial data sets that are emitted by artificially mimicked defects in GIS are needed. Applying the neural networks to the data sets, in general, identification methods of defects in GIS have widely been developed. Some identification system shows a good success such that the misclassification rate is reduced to below 5%; the key features in identification, however, are not obviously revealed in neural networks systems because of nonlinear network structures. The decision tree method that classifies the signals using the feature rules in plain graphical representations can explains the classification rules in clear forms. We applied the decision tree classification method to the signals emitted from the signals by artificially prepared defects in GIS, and find that the method shows a good classification rates over 95% which are comparable to that in neural networks. We also discuss the robustness from noise, and compare the results of the misclassification rates by the two methods.

AB - On-line diagnosing of GIS (Gas Insulated Switchgears) requires the pattern classification and identification of signals that are emitted from GIS. To classify the patterns correctly, substantial data sets that are emitted by artificially mimicked defects in GIS are needed. Applying the neural networks to the data sets, in general, identification methods of defects in GIS have widely been developed. Some identification system shows a good success such that the misclassification rate is reduced to below 5%; the key features in identification, however, are not obviously revealed in neural networks systems because of nonlinear network structures. The decision tree method that classifies the signals using the feature rules in plain graphical representations can explains the classification rules in clear forms. We applied the decision tree classification method to the signals emitted from the signals by artificially prepared defects in GIS, and find that the method shows a good classification rates over 95% which are comparable to that in neural networks. We also discuss the robustness from noise, and compare the results of the misclassification rates by the two methods.

UR - http://www.scopus.com/inward/record.url?scp=25644452937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=25644452937&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:25644452937

VL - 3

SP - 885

EP - 888

BT - Proceedings of the International Symposium on Electrical Insulating Materials

ER -