Functional near infrared spectroscopy based congitive task classification using support vector machines

Berdakh Abibullaev; Won Seok Kang; Seung Hyun Lee; Jinung An

doi:10.1109/HIBIT.2010.5478913

Functional near infrared spectroscopy based congitive task classification using support vector machines

Berdakh Abibullaev, Won Seok Kang, Seung Hyun Lee, Jinung An

Department of Robotics and Mechatronics

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

Abstract

the present study analyzes brain hemodynamic concentration of frontal cortex during four cognitive mental tasks. The analysis procedure consists of three sequential steps. First, the strong brain activation regions have been investigated thoroughly from all subjects in order to And a proper electrode location that generates important brain stimuli. Second, a feature extraction method that is based on wavelet transforms and denoising technique for extraction of important task-relevant features. Finally, support vector machines have been using in the classification of mental tasks with wavelet input coefficients. By applying the methodology for 4-subjects in average we achieved 92 % classification rates. However, the results depend on the type of the task that subject were performing. It is expect that the proposed method can be a basic technology for brain-computer interface by combining wavelets with support vector machines.

Original language	English
Title of host publication	2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010
Pages	7-12
Number of pages	6
DOIs	https://doi.org/10.1109/HIBIT.2010.5478913
Publication status	Published - Jul 16 2010
Event	2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010 - Antalya, Turkey Duration: Apr 20 2010 → Apr 22 2010

Publication series

Name	2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010

Other

Other	2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010
Country	Turkey
City	Antalya
Period	4/20/10 → 4/22/10

Keywords

BCI
Component
Functional near-infrared spectroscopy
Mental task classification
Support vector machines
Wavelets

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.1109/HIBIT.2010.5478913

Fingerprint Dive into the research topics of 'Functional near infrared spectroscopy based congitive task classification using support vector machines'. Together they form a unique fingerprint.

Cite this

Abibullaev, B., Kang, W. S., Lee, S. H., & An, J. (2010). Functional near infrared spectroscopy based congitive task classification using support vector machines. In 2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010 (pp. 7-12). [5478913] (2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010). https://doi.org/10.1109/HIBIT.2010.5478913

Functional near infrared spectroscopy based congitive task classification using support vector machines. / Abibullaev, Berdakh; Kang, Won Seok; Lee, Seung Hyun; An, Jinung.

2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010. 2010. p. 7-12 5478913 (2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010).

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

Abibullaev, B, Kang, WS, Lee, SH & An, J 2010, Functional near infrared spectroscopy based congitive task classification using support vector machines. in 2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010., 5478913, 2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010, pp. 7-12, 2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010, Antalya, Turkey, 4/20/10. https://doi.org/10.1109/HIBIT.2010.5478913

Abibullaev B, Kang WS, Lee SH, An J. Functional near infrared spectroscopy based congitive task classification using support vector machines. In 2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010. 2010. p. 7-12. 5478913. (2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010). https://doi.org/10.1109/HIBIT.2010.5478913

@inproceedings{4c14c050ba3a43629c001e33259cdf9d,

title = "Functional near infrared spectroscopy based congitive task classification using support vector machines",

abstract = "the present study analyzes brain hemodynamic concentration of frontal cortex during four cognitive mental tasks. The analysis procedure consists of three sequential steps. First, the strong brain activation regions have been investigated thoroughly from all subjects in order to And a proper electrode location that generates important brain stimuli. Second, a feature extraction method that is based on wavelet transforms and denoising technique for extraction of important task-relevant features. Finally, support vector machines have been using in the classification of mental tasks with wavelet input coefficients. By applying the methodology for 4-subjects in average we achieved 92 % classification rates. However, the results depend on the type of the task that subject were performing. It is expect that the proposed method can be a basic technology for brain-computer interface by combining wavelets with support vector machines.",

keywords = "BCI, Component, Functional near-infrared spectroscopy, Mental task classification, Support vector machines, Wavelets",

author = "Berdakh Abibullaev and Kang, {Won Seok} and Lee, {Seung Hyun} and Jinung An",

year = "2010",

month = jul,

day = "16",

doi = "10.1109/HIBIT.2010.5478913",

language = "English",

isbn = "9781424459704",

series = "2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010",

pages = "7--12",

booktitle = "2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010",

note = "2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010 ; Conference date: 20-04-2010 Through 22-04-2010",

}

TY - GEN

T1 - Functional near infrared spectroscopy based congitive task classification using support vector machines

AU - Abibullaev, Berdakh

AU - Kang, Won Seok

AU - Lee, Seung Hyun

AU - An, Jinung

PY - 2010/7/16

Y1 - 2010/7/16

N2 - the present study analyzes brain hemodynamic concentration of frontal cortex during four cognitive mental tasks. The analysis procedure consists of three sequential steps. First, the strong brain activation regions have been investigated thoroughly from all subjects in order to And a proper electrode location that generates important brain stimuli. Second, a feature extraction method that is based on wavelet transforms and denoising technique for extraction of important task-relevant features. Finally, support vector machines have been using in the classification of mental tasks with wavelet input coefficients. By applying the methodology for 4-subjects in average we achieved 92 % classification rates. However, the results depend on the type of the task that subject were performing. It is expect that the proposed method can be a basic technology for brain-computer interface by combining wavelets with support vector machines.

AB - the present study analyzes brain hemodynamic concentration of frontal cortex during four cognitive mental tasks. The analysis procedure consists of three sequential steps. First, the strong brain activation regions have been investigated thoroughly from all subjects in order to And a proper electrode location that generates important brain stimuli. Second, a feature extraction method that is based on wavelet transforms and denoising technique for extraction of important task-relevant features. Finally, support vector machines have been using in the classification of mental tasks with wavelet input coefficients. By applying the methodology for 4-subjects in average we achieved 92 % classification rates. However, the results depend on the type of the task that subject were performing. It is expect that the proposed method can be a basic technology for brain-computer interface by combining wavelets with support vector machines.

KW - BCI

KW - Component

KW - Functional near-infrared spectroscopy

KW - Mental task classification

KW - Support vector machines

KW - Wavelets

UR - http://www.scopus.com/inward/record.url?scp=77954476071&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954476071&partnerID=8YFLogxK

U2 - 10.1109/HIBIT.2010.5478913

DO - 10.1109/HIBIT.2010.5478913

M3 - Conference contribution

AN - SCOPUS:77954476071

SN - 9781424459704

T3 - 2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010

SP - 7

EP - 12

BT - 2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010

T2 - 2010 5th International Symposium on Health Informatics and Bioinformatics, HIBIT 2010

Y2 - 20 April 2010 through 22 April 2010

ER -