Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication

Nga Tran; Dat Tran; Shuangzhe Liu; Linh Trinh; Tien Pham

doi:10.1007/978-3-030-20005-3_6

Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication

Nga Tran, Dat Tran, Shuangzhe Liu, Linh Trinh, Tien Pham

Information Systems

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

5 Citations (Scopus)

Abstract

Support Vector Machine (SVM) has been widely used in EEG-based person authentication. Current EEG datasets are often imbalanced due to the frequency of genuine clients and impostors, and this issue heavily impacts on the performance of EEG-based person authentication using SVM. In this paper, we propose a new bias method for SVM binary classification to improve the performance of the minority class in imbalanced datasets. Our experiments on EEG datasets and UCI datasets with the proposed method show promising results.

Original language	English
Title of host publication	International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2019) and 10th International Conference on EUropean Transnational Education (ICEUTE 2019). CISIS 2019, ICEUTE 2019
Editors	José António Sáez Muñoz, Emilio Corchado, Francisco Martínez Álvarez, Alicia Troncoso Lora, Héctor Quintián
Place of Publication	Switzerland
Publisher	Springer
Pages	57-66
Number of pages	10
ISBN (Electronic)	9783030200053
ISBN (Print)	9783030200046
DOIs	https://doi.org/10.1007/978-3-030-20005-3_6
Publication status	Published - 1 Jan 2020
Event	International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2019 and 10th International Conference on European Transnational Education, ICEUTE 2019 - Seville, Spain Duration: 13 May 2019 → 15 May 2019

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	951
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2019 and 10th International Conference on European Transnational Education, ICEUTE 2019
Country/Territory	Spain
City	Seville
Period	13/05/19 → 15/05/19

Access to Document

10.1007/978-3-030-20005-3_6

Cite this

Tran, N., Tran, D., Liu, S., Trinh, L., & Pham, T. (2020). Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication. In J. A. Sáez Muñoz, E. Corchado, F. Martínez Álvarez, A. Troncoso Lora, & H. Quintián (Eds.), International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2019) and 10th International Conference on EUropean Transnational Education (ICEUTE 2019). CISIS 2019, ICEUTE 2019 (pp. 57-66). (Advances in Intelligent Systems and Computing; Vol. 951). Springer. https://doi.org/10.1007/978-3-030-20005-3_6

Tran, Nga ; Tran, Dat ; Liu, Shuangzhe et al. / Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication. International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2019) and 10th International Conference on EUropean Transnational Education (ICEUTE 2019). CISIS 2019, ICEUTE 2019. editor / José António Sáez Muñoz ; Emilio Corchado ; Francisco Martínez Álvarez ; Alicia Troncoso Lora ; Héctor Quintián. Switzerland : Springer, 2020. pp. 57-66 (Advances in Intelligent Systems and Computing).

@inproceedings{d134a2b6df194f49902d4ea5a4eb650b,

title = "Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication",

abstract = "Support Vector Machine (SVM) has been widely used in EEG-based person authentication. Current EEG datasets are often imbalanced due to the frequency of genuine clients and impostors, and this issue heavily impacts on the performance of EEG-based person authentication using SVM. In this paper, we propose a new bias method for SVM binary classification to improve the performance of the minority class in imbalanced datasets. Our experiments on EEG datasets and UCI datasets with the proposed method show promising results.",

keywords = "Authentication, Biometrics, EEG, Security, SVM",

author = "Nga Tran and Dat Tran and Shuangzhe Liu and Linh Trinh and Tien Pham",

note = "{\textcopyright}2020 Springer Nature ; International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2019 and 10th International Conference on European Transnational Education, ICEUTE 2019 ; Conference date: 13-05-2019 Through 15-05-2019",

year = "2020",

month = jan,

day = "1",

doi = "10.1007/978-3-030-20005-3_6",

language = "English",

isbn = "9783030200046",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "57--66",

editor = "{S{\'a}ez Mu{\~n}oz}, {Jos{\'e} Ant{\'o}nio} and Emilio Corchado and {Mart{\'i}nez {\'A}lvarez}, Francisco and {Troncoso Lora}, Alicia and H{\'e}ctor Quinti{\'a}n",

booktitle = "International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2019) and 10th International Conference on EUropean Transnational Education (ICEUTE 2019). CISIS 2019, ICEUTE 2019",

address = "Netherlands",

}

Tran, N, Tran, D , Liu, S, Trinh, L & Pham, T 2020, Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication. in JA Sáez Muñoz, E Corchado, F Martínez Álvarez, A Troncoso Lora & H Quintián (eds), International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2019) and 10th International Conference on EUropean Transnational Education (ICEUTE 2019). CISIS 2019, ICEUTE 2019. Advances in Intelligent Systems and Computing, vol. 951, Springer, Switzerland, pp. 57-66, International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2019 and 10th International Conference on European Transnational Education, ICEUTE 2019, Seville, Spain, 13/05/19. https://doi.org/10.1007/978-3-030-20005-3_6

Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication. / Tran, Nga; Tran, Dat ; Liu, Shuangzhe et al.
International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2019) and 10th International Conference on EUropean Transnational Education (ICEUTE 2019). CISIS 2019, ICEUTE 2019. ed. / José António Sáez Muñoz; Emilio Corchado; Francisco Martínez Álvarez; Alicia Troncoso Lora; Héctor Quintián. Switzerland: Springer, 2020. p. 57-66 (Advances in Intelligent Systems and Computing; Vol. 951).

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

TY - GEN

T1 - Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication

AU - Tran, Nga

AU - Tran, Dat

AU - Liu, Shuangzhe

AU - Trinh, Linh

AU - Pham, Tien

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Support Vector Machine (SVM) has been widely used in EEG-based person authentication. Current EEG datasets are often imbalanced due to the frequency of genuine clients and impostors, and this issue heavily impacts on the performance of EEG-based person authentication using SVM. In this paper, we propose a new bias method for SVM binary classification to improve the performance of the minority class in imbalanced datasets. Our experiments on EEG datasets and UCI datasets with the proposed method show promising results.

AB - Support Vector Machine (SVM) has been widely used in EEG-based person authentication. Current EEG datasets are often imbalanced due to the frequency of genuine clients and impostors, and this issue heavily impacts on the performance of EEG-based person authentication using SVM. In this paper, we propose a new bias method for SVM binary classification to improve the performance of the minority class in imbalanced datasets. Our experiments on EEG datasets and UCI datasets with the proposed method show promising results.

KW - Authentication

KW - Biometrics

KW - EEG

KW - Security

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=85065736519&partnerID=8YFLogxK

UR - http://www.mendeley.com/catalogue/improving-svm-classification-imbalanced-datasets-eegbased-person-authentication

U2 - 10.1007/978-3-030-20005-3_6

DO - 10.1007/978-3-030-20005-3_6

M3 - Conference contribution

AN - SCOPUS:85065736519

SN - 9783030200046

T3 - Advances in Intelligent Systems and Computing

SP - 57

EP - 66

BT - International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2019) and 10th International Conference on EUropean Transnational Education (ICEUTE 2019). CISIS 2019, ICEUTE 2019

A2 - Sáez Muñoz, José António

A2 - Corchado, Emilio

A2 - Martínez Álvarez, Francisco

A2 - Troncoso Lora, Alicia

A2 - Quintián, Héctor

PB - Springer

CY - Switzerland

T2 - International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems, CISIS 2019 and 10th International Conference on European Transnational Education, ICEUTE 2019

Y2 - 13 May 2019 through 15 May 2019

ER -

Tran N, Tran D , Liu S, Trinh L, Pham T. Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication. In Sáez Muñoz JA, Corchado E, Martínez Álvarez F, Troncoso Lora A, Quintián H, editors, International Joint Conference: 12th International Conference on Computational Intelligence in Security for Information Systems (CISIS 2019) and 10th International Conference on EUropean Transnational Education (ICEUTE 2019). CISIS 2019, ICEUTE 2019. Switzerland: Springer. 2020. p. 57-66. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-20005-3_6

Improving SVM Classification on Imbalanced Datasets for EEG-Based Person Authentication

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this