Naive bayes multi-label classification approach for high-voltage condition monitoring

Imene Mitiche; Alan Nesbitt; Philip  Boreham; Brian G. Stewart; Gordon Morison

doi:10.1109/IOTAIS.2018.8600914

Naive bayes multi-label classification approach for high-voltage condition monitoring

Imene Mitiche, Alan Nesbitt, Philip Boreham, Brian G. Stewart, Gordon Morison

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

54 Downloads (Pure)

Abstract

This paper addresses for the first time the multilabel classification of High-Voltage (HV) discharges captured using the Electromagnetic Interference (EMI) method for HV machines. The approach involves feature extraction from EMI
time signals, emitted during the discharge events, by means of 1D-Local Binary Pattern (LBP) and 1D-Histogram of Oriented Gradients (HOG) techniques. Their combination provides a feature vector that is implemented in a naive Bayes classifier designed to identify the labels of two or more discharge sources
contained within a single signal. The performance of this novel approach is measured using various metrics including average precision, accuracy, specificity, hamming loss etc. Results demonstrate a successful performance that is in line with similar application to other fields such as biology and image processing. This first attempt of multi-label classification of EMI discharge
sources opens a new research topic in HV condition monitoring.

Original language	English
Title of host publication	2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS)
Publisher	IEEE
Pages	162-166
Number of pages	5
ISBN (Electronic)	9781538673584
DOIs	https://doi.org/10.1109/IOTAIS.2018.8600914
Publication status	Published - 7 Jan 2019

Keywords

high voltage
condition monitoring

Documents and Links

10.1109/IOTAIS.2018.8600914

Mitiche, I. et al (2018) Naive Bayes Multi-Label Classification Approach for High-Voltage Condition Monitoring
Copyright © 2018 IEEE. This is a post-peer review, pre-copy edited version of the article and may differ slightly from the final published version of the work. This work is made available in line with the publisher policy. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Accepted author manuscript, 735 KB

Fingerprint Dive into the research topics of 'Naive bayes multi-label classification approach for high-voltage condition monitoring'. Together they form a unique fingerprint.

Cite this

Mitiche, I., Nesbitt, A., Boreham, P., Stewart, B. G., & Morison, G. (2019). Naive bayes multi-label classification approach for high-voltage condition monitoring. In 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS) (pp. 162-166). IEEE. https://doi.org/10.1109/IOTAIS.2018.8600914

@inproceedings{344b835de8514ee48ed764d93bf53f41,

title = "Naive bayes multi-label classification approach for high-voltage condition monitoring",

abstract = "This paper addresses for the first time the multilabel classification of High-Voltage (HV) discharges captured using the Electromagnetic Interference (EMI) method for HV machines. The approach involves feature extraction from EMItime signals, emitted during the discharge events, by means of 1D-Local Binary Pattern (LBP) and 1D-Histogram of Oriented Gradients (HOG) techniques. Their combination provides a feature vector that is implemented in a naive Bayes classifier designed to identify the labels of two or more discharge sourcescontained within a single signal. The performance of this novel approach is measured using various metrics including average precision, accuracy, specificity, hamming loss etc. Results demonstrate a successful performance that is in line with similar application to other fields such as biology and image processing. This first attempt of multi-label classification of EMI dischargesources opens a new research topic in HV condition monitoring.",

keywords = "high voltage , condition monitoring",

author = "Imene Mitiche and Alan Nesbitt and Philip Boreham and Stewart, {Brian G.} and Gordon Morison",

note = "Acceptance in SAN AAM: no embargo No ISSN found for output, out of policy scope. ST 13/11/19",

year = "2019",

month = jan,

day = "7",

doi = "10.1109/IOTAIS.2018.8600914",

language = "English",

pages = "162--166",

booktitle = "2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS)",

publisher = "IEEE",

}

Naive bayes multi-label classification approach for high-voltage condition monitoring. / Mitiche, Imene ; Nesbitt, Alan; Boreham, Philip ; Stewart, Brian G.; Morison, Gordon.

2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS). IEEE, 2019. p. 162-166.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Naive bayes multi-label classification approach for high-voltage condition monitoring

AU - Mitiche, Imene

AU - Nesbitt, Alan

AU - Boreham, Philip

AU - Stewart, Brian G.

AU - Morison, Gordon

N1 - Acceptance in SAN AAM: no embargo No ISSN found for output, out of policy scope. ST 13/11/19

PY - 2019/1/7

Y1 - 2019/1/7

N2 - This paper addresses for the first time the multilabel classification of High-Voltage (HV) discharges captured using the Electromagnetic Interference (EMI) method for HV machines. The approach involves feature extraction from EMItime signals, emitted during the discharge events, by means of 1D-Local Binary Pattern (LBP) and 1D-Histogram of Oriented Gradients (HOG) techniques. Their combination provides a feature vector that is implemented in a naive Bayes classifier designed to identify the labels of two or more discharge sourcescontained within a single signal. The performance of this novel approach is measured using various metrics including average precision, accuracy, specificity, hamming loss etc. Results demonstrate a successful performance that is in line with similar application to other fields such as biology and image processing. This first attempt of multi-label classification of EMI dischargesources opens a new research topic in HV condition monitoring.

AB - This paper addresses for the first time the multilabel classification of High-Voltage (HV) discharges captured using the Electromagnetic Interference (EMI) method for HV machines. The approach involves feature extraction from EMItime signals, emitted during the discharge events, by means of 1D-Local Binary Pattern (LBP) and 1D-Histogram of Oriented Gradients (HOG) techniques. Their combination provides a feature vector that is implemented in a naive Bayes classifier designed to identify the labels of two or more discharge sourcescontained within a single signal. The performance of this novel approach is measured using various metrics including average precision, accuracy, specificity, hamming loss etc. Results demonstrate a successful performance that is in line with similar application to other fields such as biology and image processing. This first attempt of multi-label classification of EMI dischargesources opens a new research topic in HV condition monitoring.

KW - high voltage

KW - condition monitoring

U2 - 10.1109/IOTAIS.2018.8600914

DO - 10.1109/IOTAIS.2018.8600914

M3 - Conference contribution

SP - 162

EP - 166

BT - 2018 IEEE International Conference on Internet of Things and Intelligence System (IOTAIS)

PB - IEEE

ER -