Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations

This paper proposed an effort to investigate the suitability of input features and classifier for identifying thermal faults within electrical installations. The features are extracted from the thermal images of electrical equipment and classified using a multilayered perceptron (MLP) artificial neu...

Full description

Bibliographic Details
Main Authors:	M. S., Jadin, Kamarul Hawari, Ghazali, Soib, Taib
Format:	Article
Published:	Elsevier Ltd 2014
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://umpir.ump.edu.my/id/eprint/6342/ http://umpir.ump.edu.my/id/eprint/6342/ http://umpir.ump.edu.my/id/eprint/6342/

id	ump-6342
recordtype	eprints
spelling	ump-63422018-02-21T05:10:35Z http://umpir.ump.edu.my/id/eprint/6342/ Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations M. S., Jadin Kamarul Hawari, Ghazali Soib, Taib TK Electrical engineering. Electronics Nuclear engineering This paper proposed an effort to investigate the suitability of input features and classifier for identifying thermal faults within electrical installations. The features are extracted from the thermal images of electrical equipment and classified using a multilayered perceptron (MLP) artificial neural network and support vector machine (SVM). In the experiments, the classification performances from various input features are evaluated. The commonly used classification performance indices, including sensitivity, specificity, accuracy, area under curve (AUC), receiver operating characteristic (ROC) and F-score are employed to identify the most suitable input feature as well as the best configuration of classifiers. The experimental results demonstrate that the combination of features set Tmax, Tdelta and DTbg produce the best input feature for thermal fault detection. In addition, the implementation of SVM using radial basis kernel function (RBF) produces slightly better performance than the MLP artificial neural network. Elsevier Ltd 2014 Article PeerReviewed M. S., Jadin and Kamarul Hawari, Ghazali and Soib, Taib (2014) Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations. Measurement, 57. pp. 15-24. ISSN 0263-2241 http://dx.doi.org/10.1016/j.measurement.2014.07.010 DOI: 10.1016/j.measurement.2014.07.010
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Malaysia Pahang
building	UMP Institutional Repository
collection	Online Access
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering M. S., Jadin Kamarul Hawari, Ghazali Soib, Taib Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations
description	This paper proposed an effort to investigate the suitability of input features and classifier for identifying thermal faults within electrical installations. The features are extracted from the thermal images of electrical equipment and classified using a multilayered perceptron (MLP) artificial neural network and support vector machine (SVM). In the experiments, the classification performances from various input features are evaluated. The commonly used classification performance indices, including sensitivity, specificity, accuracy, area under curve (AUC), receiver operating characteristic (ROC) and F-score are employed to identify the most suitable input feature as well as the best configuration of classifiers. The experimental results demonstrate that the combination of features set Tmax, Tdelta and DTbg produce the best input feature for thermal fault detection. In addition, the implementation of SVM using radial basis kernel function (RBF) produces slightly better performance than the MLP artificial neural network.
format	Article
author	M. S., Jadin Kamarul Hawari, Ghazali Soib, Taib
author_facet	M. S., Jadin Kamarul Hawari, Ghazali Soib, Taib
author_sort	M. S., Jadin
title	Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations
title_short	Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations
title_full	Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations
title_fullStr	Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations
title_full_unstemmed	Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations
title_sort	feature extraction and classification for detecting the thermal faults in electrical installations
publisher	Elsevier Ltd
publishDate	2014
url	http://umpir.ump.edu.my/id/eprint/6342/ http://umpir.ump.edu.my/id/eprint/6342/ http://umpir.ump.edu.my/id/eprint/6342/
first_indexed	2023-09-18T22:02:01Z
last_indexed	2023-09-18T22:02:01Z
_version_	1777414461648273408

Feature Extraction and Classification for Detecting the Thermal Faults in Electrical Installations

Similar Items