High order moment features for NIRS-based classification problems

Tuan Hoang, Dat Tran, Khoa Truong, Phuoc Nguyen, Toi Vo Van, Xu Huang, Dharmendra SHARMA

Research output: A Conference proceeding or a Chapter in BookConference contribution

2 Citations (Scopus)

Abstract

This paper aims to experiment high order moment features in two well-known problems which are motor imagery and person authentication in Brain Computer Interface (BCI) systems using Near Infrared Spectroscopy (NIRS) technique. To improve performance of the systems, we propose a new feature by combining 2 nd order and 4th order moments of signal together. Our results show that such the feature not only achieves very high recall and precision ratios but also is practical for online NIRS-based BCI systems. Our systems can achieve recall and precision ratio at 99.2% for the left-hand and right-hand imagery problem, and up to 100% for the person authentication problem.

Original languageEnglish
Title of host publication4th International Conference on Biomedical Engineering in Vietnam
EditorsToi Van Vo, Nguyen Bao Toan, Troung Quang Dang Khoa, Tran Ha Lien Phoung
Place of PublicationVietnam
PublisherSpringer
Pages4-7
Number of pages4
Volume40 IFMBE
ISBN (Electronic)9783642321832
ISBN (Print)9783642321825
DOIs
Publication statusPublished - 1 Jan 2013
Event4th International Conference on the Development of Biomedical Engineering in Vietnam - Ho Chi Minh City, Viet Nam
Duration: 8 Jan 201210 Jan 2012

Conference

Conference4th International Conference on the Development of Biomedical Engineering in Vietnam
CountryViet Nam
CityHo Chi Minh City
Period8/01/1210/01/12

Fingerprint

Brain computer interface
Near infrared spectroscopy
Authentication
Experiments

Cite this

Hoang, T., Tran, D., Truong, K., Nguyen, P., Vo Van, T., Huang, X., & SHARMA, D. (2013). High order moment features for NIRS-based classification problems. In T. Van Vo, N. B. Toan, T. Q. D. Khoa, & T. H. L. Phoung (Eds.), 4th International Conference on Biomedical Engineering in Vietnam (Vol. 40 IFMBE, pp. 4-7). Vietnam: Springer. https://doi.org/10.1007/978-3-642-32183-2_2
Hoang, Tuan ; Tran, Dat ; Truong, Khoa ; Nguyen, Phuoc ; Vo Van, Toi ; Huang, Xu ; SHARMA, Dharmendra. / High order moment features for NIRS-based classification problems. 4th International Conference on Biomedical Engineering in Vietnam. editor / Toi Van Vo ; Nguyen Bao Toan ; Troung Quang Dang Khoa ; Tran Ha Lien Phoung. Vol. 40 IFMBE Vietnam : Springer, 2013. pp. 4-7
@inproceedings{26fb474b752144028887e687173b6f2b,
title = "High order moment features for NIRS-based classification problems",
abstract = "This paper aims to experiment high order moment features in two well-known problems which are motor imagery and person authentication in Brain Computer Interface (BCI) systems using Near Infrared Spectroscopy (NIRS) technique. To improve performance of the systems, we propose a new feature by combining 2 nd order and 4th order moments of signal together. Our results show that such the feature not only achieves very high recall and precision ratios but also is practical for online NIRS-based BCI systems. Our systems can achieve recall and precision ratio at 99.2{\%} for the left-hand and right-hand imagery problem, and up to 100{\%} for the person authentication problem.",
keywords = "Brain Computer Interface, high order moment, motor imagery, NIRS-based BCI, person authentication",
author = "Tuan Hoang and Dat Tran and Khoa Truong and Phuoc Nguyen and {Vo Van}, Toi and Xu Huang and Dharmendra SHARMA",
year = "2013",
month = "1",
day = "1",
doi = "10.1007/978-3-642-32183-2_2",
language = "English",
isbn = "9783642321825",
volume = "40 IFMBE",
pages = "4--7",
editor = "{Van Vo}, Toi and Toan, {Nguyen Bao} and Khoa, {Troung Quang Dang} and Phoung, {Tran Ha Lien}",
booktitle = "4th International Conference on Biomedical Engineering in Vietnam",
publisher = "Springer",
address = "Netherlands",

}

Hoang, T, Tran, D, Truong, K, Nguyen, P, Vo Van, T, Huang, X & SHARMA, D 2013, High order moment features for NIRS-based classification problems. in T Van Vo, NB Toan, TQD Khoa & THL Phoung (eds), 4th International Conference on Biomedical Engineering in Vietnam. vol. 40 IFMBE, Springer, Vietnam, pp. 4-7, 4th International Conference on the Development of Biomedical Engineering in Vietnam, Ho Chi Minh City, Viet Nam, 8/01/12. https://doi.org/10.1007/978-3-642-32183-2_2

High order moment features for NIRS-based classification problems. / Hoang, Tuan; Tran, Dat; Truong, Khoa; Nguyen, Phuoc; Vo Van, Toi; Huang, Xu; SHARMA, Dharmendra.

4th International Conference on Biomedical Engineering in Vietnam. ed. / Toi Van Vo; Nguyen Bao Toan; Troung Quang Dang Khoa; Tran Ha Lien Phoung. Vol. 40 IFMBE Vietnam : Springer, 2013. p. 4-7.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - High order moment features for NIRS-based classification problems

AU - Hoang, Tuan

AU - Tran, Dat

AU - Truong, Khoa

AU - Nguyen, Phuoc

AU - Vo Van, Toi

AU - Huang, Xu

AU - SHARMA, Dharmendra

PY - 2013/1/1

Y1 - 2013/1/1

N2 - This paper aims to experiment high order moment features in two well-known problems which are motor imagery and person authentication in Brain Computer Interface (BCI) systems using Near Infrared Spectroscopy (NIRS) technique. To improve performance of the systems, we propose a new feature by combining 2 nd order and 4th order moments of signal together. Our results show that such the feature not only achieves very high recall and precision ratios but also is practical for online NIRS-based BCI systems. Our systems can achieve recall and precision ratio at 99.2% for the left-hand and right-hand imagery problem, and up to 100% for the person authentication problem.

AB - This paper aims to experiment high order moment features in two well-known problems which are motor imagery and person authentication in Brain Computer Interface (BCI) systems using Near Infrared Spectroscopy (NIRS) technique. To improve performance of the systems, we propose a new feature by combining 2 nd order and 4th order moments of signal together. Our results show that such the feature not only achieves very high recall and precision ratios but also is practical for online NIRS-based BCI systems. Our systems can achieve recall and precision ratio at 99.2% for the left-hand and right-hand imagery problem, and up to 100% for the person authentication problem.

KW - Brain Computer Interface

KW - high order moment

KW - motor imagery

KW - NIRS-based BCI

KW - person authentication

UR - http://www.scopus.com/inward/record.url?scp=84871552134&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-32183-2_2

DO - 10.1007/978-3-642-32183-2_2

M3 - Conference contribution

SN - 9783642321825

VL - 40 IFMBE

SP - 4

EP - 7

BT - 4th International Conference on Biomedical Engineering in Vietnam

A2 - Van Vo, Toi

A2 - Toan, Nguyen Bao

A2 - Khoa, Troung Quang Dang

A2 - Phoung, Tran Ha Lien

PB - Springer

CY - Vietnam

ER -

Hoang T, Tran D, Truong K, Nguyen P, Vo Van T, Huang X et al. High order moment features for NIRS-based classification problems. In Van Vo T, Toan NB, Khoa TQD, Phoung THL, editors, 4th International Conference on Biomedical Engineering in Vietnam. Vol. 40 IFMBE. Vietnam: Springer. 2013. p. 4-7 https://doi.org/10.1007/978-3-642-32183-2_2