An optimal sphere and two large margins approach for novelty detection

Dat Tran; Wanli Ma; Dharmendra Sharma

doi:10.1109/IJCNN.2010.5596456

An optimal sphere and two large margins approach for novelty detection

Dat Tran, Wanli Ma, Dharmendra Sharma

Information Systems

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

23 Citations (Scopus)

47 Downloads (Pure)

Abstract

We introduce a new model to deal with imbalanced data sets for novelty detection problems where the normal class of training data set can be majority or minority class. The key idea is to construct an optimal hypersphere such that the inside margin between the surface of this sphere and the normal data and the outside margin between that surface and the abnormal data are as large as possible. Depending on a specific real application of novelty detection, the two margins can be adjusted to achieve the best true positive and false positive rates. Experimental results on a number of data sets showed that the proposed model can provide better performance comparing with current models for novelty detection

Original language	English
Title of host publication	2010 International Joint Conference on Neural Networks (IJCNN)
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781424469185
ISBN (Print)	9781424469161
DOIs	https://doi.org/10.1109/IJCNN.2010.5596456
Publication status	Published - 2010
Event	2010 IEEE World Congress on Computational Intelligence (FUZZ-IEEE 2010) - Barcelona, Barcelona, Spain Duration: 18 Jul 2010 → 23 Jul 2010

Conference

Conference	2010 IEEE World Congress on Computational Intelligence (FUZZ-IEEE 2010)
Country/Territory	Spain
City	Barcelona
Period	18/07/10 → 23/07/10

Access to Document

10.1109/IJCNN.2010.5596456

Conference ContributionFinal published version, 498 KB

Cite this

@inproceedings{ea13785d80414abfad03244a832b12d9,

title = "An optimal sphere and two large margins approach for novelty detection",

abstract = "We introduce a new model to deal with imbalanced data sets for novelty detection problems where the normal class of training data set can be majority or minority class. The key idea is to construct an optimal hypersphere such that the inside margin between the surface of this sphere and the normal data and the outside margin between that surface and the abnormal data are as large as possible. Depending on a specific real application of novelty detection, the two margins can be adjusted to achieve the best true positive and false positive rates. Experimental results on a number of data sets showed that the proposed model can provide better performance comparing with current models for novelty detection",

author = "Dat Tran and Wanli Ma and Dharmendra Sharma",

year = "2010",

doi = "10.1109/IJCNN.2010.5596456",

language = "English",

isbn = "9781424469161",

pages = "1--6",

booktitle = "2010 International Joint Conference on Neural Networks (IJCNN)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2010 IEEE World Congress on Computational Intelligence (FUZZ-IEEE 2010) ; Conference date: 18-07-2010 Through 23-07-2010",

}

Tran, D , Ma, W & Sharma, D 2010, An optimal sphere and two large margins approach for novelty detection. in 2010 International Joint Conference on Neural Networks (IJCNN). IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 1-6, 2010 IEEE World Congress on Computational Intelligence (FUZZ-IEEE 2010), Barcelona, Spain, 18/07/10. https://doi.org/10.1109/IJCNN.2010.5596456

An optimal sphere and two large margins approach for novelty detection. / Tran, Dat ; Ma, Wanli ; Sharma, Dharmendra.
2010 International Joint Conference on Neural Networks (IJCNN). United States: IEEE, Institute of Electrical and Electronics Engineers, 2010. p. 1-6.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - An optimal sphere and two large margins approach for novelty detection

AU - Tran, Dat

AU - Ma, Wanli

AU - Sharma, Dharmendra

PY - 2010

Y1 - 2010

N2 - We introduce a new model to deal with imbalanced data sets for novelty detection problems where the normal class of training data set can be majority or minority class. The key idea is to construct an optimal hypersphere such that the inside margin between the surface of this sphere and the normal data and the outside margin between that surface and the abnormal data are as large as possible. Depending on a specific real application of novelty detection, the two margins can be adjusted to achieve the best true positive and false positive rates. Experimental results on a number of data sets showed that the proposed model can provide better performance comparing with current models for novelty detection

AB - We introduce a new model to deal with imbalanced data sets for novelty detection problems where the normal class of training data set can be majority or minority class. The key idea is to construct an optimal hypersphere such that the inside margin between the surface of this sphere and the normal data and the outside margin between that surface and the abnormal data are as large as possible. Depending on a specific real application of novelty detection, the two margins can be adjusted to achieve the best true positive and false positive rates. Experimental results on a number of data sets showed that the proposed model can provide better performance comparing with current models for novelty detection

U2 - 10.1109/IJCNN.2010.5596456

DO - 10.1109/IJCNN.2010.5596456

M3 - Conference contribution

SN - 9781424469161

SP - 1

EP - 6

BT - 2010 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - 2010 IEEE World Congress on Computational Intelligence (FUZZ-IEEE 2010)

Y2 - 18 July 2010 through 23 July 2010

ER -