On the investigation of artificial immune systems on imbalanced data classification for power distribution system fault cause identification

Le Xu; Mo Yuen Chow; Jon Timmis; Leroy S. Taylor; Andrew Watkins

On the investigation of artificial immune systems on imbalanced data classification for power distribution system fault cause identification

Le Xu^*, Mo Yuen Chow, Jon Timmis, Leroy S. Taylor, Andrew Watkins

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

2 Citations (Scopus)

Abstract

Imbalanced data are often encountered in real-world applications, they may incline the performance of classification to be biased. The immune-based algorithm Artificial Immune Recognition System (AIRS) is applied to Duke Energy distribution systems outage data and we investigate its capability to classify imbalanced data. The performance of AIRS is compared with an Artificial Neural Network (ANN). Two major distribution fault causes, tree and lightning strike, are used as prototypes and a tailor-made measure for imbalanced data, g-mean, is used as the major performance measure. The results indicate that AIRS is able to achieve a more balanced performance on imbalanced data than ANN.

Original language	English
Title of host publication	2006 IEEE Congress on Evolutionary Computation, CEC 2006
Pages	522-527
Number of pages	6
Publication status	Published - 2006
Event	2006 IEEE Congress on Evolutionary Computation, CEC 2006 - Vancouver, BC, Canada Duration: 16 Jul 2006 → 21 Jul 2006

Publication series

Name	2006 IEEE Congress on Evolutionary Computation, CEC 2006

Conference

Conference	2006 IEEE Congress on Evolutionary Computation, CEC 2006
Country/Territory	Canada
City	Vancouver, BC
Period	16 Jul 2006 → 21 Jul 2006

Permanent link

Persistent link

Cite this

@inproceedings{fb02092ba58844779a421d02d180cf64,

title = "On the investigation of artificial immune systems on imbalanced data classification for power distribution system fault cause identification",

abstract = "Imbalanced data are often encountered in real-world applications, they may incline the performance of classification to be biased. The immune-based algorithm Artificial Immune Recognition System (AIRS) is applied to Duke Energy distribution systems outage data and we investigate its capability to classify imbalanced data. The performance of AIRS is compared with an Artificial Neural Network (ANN). Two major distribution fault causes, tree and lightning strike, are used as prototypes and a tailor-made measure for imbalanced data, g-mean, is used as the major performance measure. The results indicate that AIRS is able to achieve a more balanced performance on imbalanced data than ANN.",

author = "Le Xu and Chow, {Mo Yuen} and Jon Timmis and Taylor, {Leroy S.} and Andrew Watkins",

year = "2006",

language = "English",

isbn = "0780394879",

series = "2006 IEEE Congress on Evolutionary Computation, CEC 2006",

pages = "522--527",

booktitle = "2006 IEEE Congress on Evolutionary Computation, CEC 2006",

note = "2006 IEEE Congress on Evolutionary Computation, CEC 2006 ; Conference date: 16-07-2006 Through 21-07-2006",

}

Xu, L, Chow, MY, Timmis, J, Taylor, LS & Watkins, A 2006, On the investigation of artificial immune systems on imbalanced data classification for power distribution system fault cause identification. in 2006 IEEE Congress on Evolutionary Computation, CEC 2006., 1688354, 2006 IEEE Congress on Evolutionary Computation, CEC 2006, pp. 522-527, 2006 IEEE Congress on Evolutionary Computation, CEC 2006, Vancouver, BC, Canada, 16 Jul 2006.

On the investigation of artificial immune systems on imbalanced data classification for power distribution system fault cause identification. / Xu, Le; Chow, Mo Yuen; Timmis, Jon et al.
2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. p. 522-527 1688354 (2006 IEEE Congress on Evolutionary Computation, CEC 2006).

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (Non-Journal item)

TY - GEN

T1 - On the investigation of artificial immune systems on imbalanced data classification for power distribution system fault cause identification

AU - Xu, Le

AU - Chow, Mo Yuen

AU - Timmis, Jon

AU - Taylor, Leroy S.

AU - Watkins, Andrew

PY - 2006

Y1 - 2006

N2 - Imbalanced data are often encountered in real-world applications, they may incline the performance of classification to be biased. The immune-based algorithm Artificial Immune Recognition System (AIRS) is applied to Duke Energy distribution systems outage data and we investigate its capability to classify imbalanced data. The performance of AIRS is compared with an Artificial Neural Network (ANN). Two major distribution fault causes, tree and lightning strike, are used as prototypes and a tailor-made measure for imbalanced data, g-mean, is used as the major performance measure. The results indicate that AIRS is able to achieve a more balanced performance on imbalanced data than ANN.

AB - Imbalanced data are often encountered in real-world applications, they may incline the performance of classification to be biased. The immune-based algorithm Artificial Immune Recognition System (AIRS) is applied to Duke Energy distribution systems outage data and we investigate its capability to classify imbalanced data. The performance of AIRS is compared with an Artificial Neural Network (ANN). Two major distribution fault causes, tree and lightning strike, are used as prototypes and a tailor-made measure for imbalanced data, g-mean, is used as the major performance measure. The results indicate that AIRS is able to achieve a more balanced performance on imbalanced data than ANN.

UR - http://www.scopus.com/inward/record.url?scp=34547348152&partnerID=8YFLogxK

M3 - Conference Proceeding (Non-Journal item)

AN - SCOPUS:34547348152

SN - 0780394879

SN - 9780780394872

T3 - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

SP - 522

EP - 527

BT - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

T2 - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

Y2 - 16 July 2006 through 21 July 2006

ER -

On the investigation of artificial immune systems on imbalanced data classification for power distribution system fault cause identification

Abstract

Publication series

Conference

Permanent link

Other files and links

Fingerprint

Cite this