Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset

Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset

Missing values are prevalent in real-world datasets and they may reduce predictive performance of a learning algorithm. Dissolved Gas Analysis (DGA), one of the most deployable methods for detecting and predicting incipient faults in power transformers is one of the casualties. Thus, this paper prop...

Full description

Saved in:
Bibliographic Details
Main Authors: Zahriah, Sahri, Rubiyah, Yusof
Format: Article
Language:English
Published: Scientific Research 2014
Subjects:
T Technology (General)
Online Access:http://eprints.utem.edu.my/id/eprint/16936/2/JCC_2014071111091466.pdf
http://eprints.utem.edu.my/id/eprint/16936/
http://www.scirp.org/journal/PaperInformation.aspx?PaperID=47715
http://dx.doi.org/10.4236/jcc.2014.29004
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Teknikal Malaysia Melaka
Language: English
id my.utem.eprints.16936
record_format eprints
spelling my.utem.eprints.169362021-09-07T03:15:44Z http://eprints.utem.edu.my/id/eprint/16936/ Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset Zahriah, Sahri Rubiyah, Yusof T Technology (General) Missing values are prevalent in real-world datasets and they may reduce predictive performance of a learning algorithm. Dissolved Gas Analysis (DGA), one of the most deployable methods for detecting and predicting incipient faults in power transformers is one of the casualties. Thus, this paper proposes filling-in the missing values found in a DGA dataset using the k-nearest neighbor imputation method with two different distance metrics: Euclidean and Cityblock. Thereafter, using these imputed datasets as inputs, this study applies Support Vector Machine (SVM) to built models which are used to classify transformer faults. Experimental results are provided to show the effectiveness of the proposed approach. Scientific Research 2014-07 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/16936/2/JCC_2014071111091466.pdf Zahriah, Sahri and Rubiyah, Yusof (2014) Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset. Journal Of Computer And Communications, 2. pp. 22-31. ISSN 2327-5219 http://www.scirp.org/journal/PaperInformation.aspx?PaperID=47715 http://dx.doi.org/10.4236/jcc.2014.29004
institution Universiti Teknikal Malaysia Melaka
building UTEM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknikal Malaysia Melaka
content_source UTEM Institutional Repository
url_provider http://eprints.utem.edu.my/
language English
topic T Technology (General)
spellingShingle T Technology (General)
Zahriah, Sahri
Rubiyah, Yusof
Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset
description Missing values are prevalent in real-world datasets and they may reduce predictive performance of a learning algorithm. Dissolved Gas Analysis (DGA), one of the most deployable methods for detecting and predicting incipient faults in power transformers is one of the casualties. Thus, this paper proposes filling-in the missing values found in a DGA dataset using the k-nearest neighbor imputation method with two different distance metrics: Euclidean and Cityblock. Thereafter, using these imputed datasets as inputs, this study applies Support Vector Machine (SVM) to built models which are used to classify transformer faults. Experimental results are provided to show the effectiveness of the proposed approach.
format Article
author Zahriah, Sahri
Rubiyah, Yusof
author_facet Zahriah, Sahri
Rubiyah, Yusof
author_sort Zahriah, Sahri
title Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset
title_short Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset
title_full Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset
title_fullStr Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset
title_full_unstemmed Support Vector Machine Based Fault Diagnosis Of Power Transformer Using k Nearest Neighbor Imputed DGA Dataset
title_sort support vector machine based fault diagnosis of power transformer using k nearest neighbor imputed dga dataset
publisher Scientific Research
publishDate 2014
url http://eprints.utem.edu.my/id/eprint/16936/2/JCC_2014071111091466.pdf
http://eprints.utem.edu.my/id/eprint/16936/
http://www.scirp.org/journal/PaperInformation.aspx?PaperID=47715
http://dx.doi.org/10.4236/jcc.2014.29004
_version_ 1710679408688234496

Similar Items