A novel feature selection and extraction method for neural network based transfer capability assessment of power systems

M. M. Othman, Azah Mohamed, Aini Hussain

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

1 Citation (Scopus)

Abstract

A new feature selection and extraction method is presented in this paper for the neural network (NN) based available transfer capability assessment in the deregulated power system. The objective of feature - selection and extraction is to speed up the NN training process and to achieve a more accurate NN results. The proposed method is known as the SDFT method in which it is a combination of the sensitivity and discrete Fourier transform methods. The sensitivity analysis is first used in selecting the input features and then followed by the discrete Fourier transform (DFT) method for extracting NN input features. The hypothesis set of pre-selected data performed by the sensitivity method only offers no improvement in the NN training performance in such cases where many features are highly correlated. Thus, the DFT method is considered so as to extract the preselected data to a set of meaningful extracted data. To illustrate the effectiveness of the proposed method, a comparative study of the SDFT, DFT and sensitivity methods is made so as to investigate the effectiveness of the methods in extracting and selecting the NN features. In this study, the NN based available transfer capability assessment has been performed on the Malaysian power system.

Original languageEnglish
Title of host publicationStudent Conference on Research and Development: Networking the Future Mind in Convergence Technology, SCOReD 2003 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages401-406
Number of pages6
ISBN (Print)0780381734, 9780780381735
DOIs
Publication statusPublished - 2003
EventStudent Conference on Research and Development, SCOReD 2003 - Putrajaya, Malaysia
Duration: 25 Aug 200326 Aug 2003

Other

OtherStudent Conference on Research and Development, SCOReD 2003
CountryMalaysia
CityPutrajaya
Period25/8/0326/8/03

Fingerprint

Feature extraction
Neural networks
Discrete Fourier transforms
Sensitivity analysis

Keywords

  • Artificial neural network
  • Available transfer capability
  • Feature extraction
  • Feature selection

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Media Technology
  • Signal Processing

Cite this

Othman, M. M., Mohamed, A., & Hussain, A. (2003). A novel feature selection and extraction method for neural network based transfer capability assessment of power systems. In Student Conference on Research and Development: Networking the Future Mind in Convergence Technology, SCOReD 2003 - Proceedings (pp. 401-406). [1459731] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SCORED.2003.1459731

A novel feature selection and extraction method for neural network based transfer capability assessment of power systems. / Othman, M. M.; Mohamed, Azah; Hussain, Aini.

Student Conference on Research and Development: Networking the Future Mind in Convergence Technology, SCOReD 2003 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2003. p. 401-406 1459731.

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

Othman, MM, Mohamed, A & Hussain, A 2003, A novel feature selection and extraction method for neural network based transfer capability assessment of power systems. in Student Conference on Research and Development: Networking the Future Mind in Convergence Technology, SCOReD 2003 - Proceedings., 1459731, Institute of Electrical and Electronics Engineers Inc., pp. 401-406, Student Conference on Research and Development, SCOReD 2003, Putrajaya, Malaysia, 25/8/03. https://doi.org/10.1109/SCORED.2003.1459731
Othman MM, Mohamed A, Hussain A. A novel feature selection and extraction method for neural network based transfer capability assessment of power systems. In Student Conference on Research and Development: Networking the Future Mind in Convergence Technology, SCOReD 2003 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2003. p. 401-406. 1459731 https://doi.org/10.1109/SCORED.2003.1459731
Othman, M. M. ; Mohamed, Azah ; Hussain, Aini. / A novel feature selection and extraction method for neural network based transfer capability assessment of power systems. Student Conference on Research and Development: Networking the Future Mind in Convergence Technology, SCOReD 2003 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2003. pp. 401-406
@inproceedings{a634834b69794deb8ac8b448da28e6d4,
title = "A novel feature selection and extraction method for neural network based transfer capability assessment of power systems",
abstract = "A new feature selection and extraction method is presented in this paper for the neural network (NN) based available transfer capability assessment in the deregulated power system. The objective of feature - selection and extraction is to speed up the NN training process and to achieve a more accurate NN results. The proposed method is known as the SDFT method in which it is a combination of the sensitivity and discrete Fourier transform methods. The sensitivity analysis is first used in selecting the input features and then followed by the discrete Fourier transform (DFT) method for extracting NN input features. The hypothesis set of pre-selected data performed by the sensitivity method only offers no improvement in the NN training performance in such cases where many features are highly correlated. Thus, the DFT method is considered so as to extract the preselected data to a set of meaningful extracted data. To illustrate the effectiveness of the proposed method, a comparative study of the SDFT, DFT and sensitivity methods is made so as to investigate the effectiveness of the methods in extracting and selecting the NN features. In this study, the NN based available transfer capability assessment has been performed on the Malaysian power system.",
keywords = "Artificial neural network, Available transfer capability, Feature extraction, Feature selection",
author = "Othman, {M. M.} and Azah Mohamed and Aini Hussain",
year = "2003",
doi = "10.1109/SCORED.2003.1459731",
language = "English",
isbn = "0780381734",
pages = "401--406",
booktitle = "Student Conference on Research and Development: Networking the Future Mind in Convergence Technology, SCOReD 2003 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A novel feature selection and extraction method for neural network based transfer capability assessment of power systems

AU - Othman, M. M.

AU - Mohamed, Azah

AU - Hussain, Aini

PY - 2003

Y1 - 2003

N2 - A new feature selection and extraction method is presented in this paper for the neural network (NN) based available transfer capability assessment in the deregulated power system. The objective of feature - selection and extraction is to speed up the NN training process and to achieve a more accurate NN results. The proposed method is known as the SDFT method in which it is a combination of the sensitivity and discrete Fourier transform methods. The sensitivity analysis is first used in selecting the input features and then followed by the discrete Fourier transform (DFT) method for extracting NN input features. The hypothesis set of pre-selected data performed by the sensitivity method only offers no improvement in the NN training performance in such cases where many features are highly correlated. Thus, the DFT method is considered so as to extract the preselected data to a set of meaningful extracted data. To illustrate the effectiveness of the proposed method, a comparative study of the SDFT, DFT and sensitivity methods is made so as to investigate the effectiveness of the methods in extracting and selecting the NN features. In this study, the NN based available transfer capability assessment has been performed on the Malaysian power system.

AB - A new feature selection and extraction method is presented in this paper for the neural network (NN) based available transfer capability assessment in the deregulated power system. The objective of feature - selection and extraction is to speed up the NN training process and to achieve a more accurate NN results. The proposed method is known as the SDFT method in which it is a combination of the sensitivity and discrete Fourier transform methods. The sensitivity analysis is first used in selecting the input features and then followed by the discrete Fourier transform (DFT) method for extracting NN input features. The hypothesis set of pre-selected data performed by the sensitivity method only offers no improvement in the NN training performance in such cases where many features are highly correlated. Thus, the DFT method is considered so as to extract the preselected data to a set of meaningful extracted data. To illustrate the effectiveness of the proposed method, a comparative study of the SDFT, DFT and sensitivity methods is made so as to investigate the effectiveness of the methods in extracting and selecting the NN features. In this study, the NN based available transfer capability assessment has been performed on the Malaysian power system.

KW - Artificial neural network

KW - Available transfer capability

KW - Feature extraction

KW - Feature selection

UR - http://www.scopus.com/inward/record.url?scp=84945389126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945389126&partnerID=8YFLogxK

U2 - 10.1109/SCORED.2003.1459731

DO - 10.1109/SCORED.2003.1459731

M3 - Conference contribution

AN - SCOPUS:84945389126

SN - 0780381734

SN - 9780780381735

SP - 401

EP - 406

BT - Student Conference on Research and Development: Networking the Future Mind in Convergence Technology, SCOReD 2003 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -