Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS

Thi Kieu Khanh Ho; Jeonghwan Gwak; Chang Min Park; Ashish Khare; Jong In Song

doi:10.1007/978-981-13-2685-1_41

Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS

Thi Kieu Khanh Ho, Jeonghwan Gwak, Chang Min Park, Ashish Khare, Jong In Song

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

9 Scopus citations

Abstract

As a non-invasive optical neuroimaging technique, functional near infrared spectroscopy (fNIRS) is currently used to assess brain dynamics during the performance of complex works and everyday tasks. However, the deep learning approaches to distinguish stress levels based on the changes of hemoglobin concentrations have not yet been extensively investigated. In this paper, we evaluated the efficiencies of advanced methods differentiating the rest and task periods during stroop task experiments. First, we explored that the apparent changes of oxy-hemoglobin (HbO) and deoxy-hemoglobin (HbR) concentrations associated with two mental stages did exist across each participant. Then, a novel discrimination framework was studied. Deep learning approaches, including convolutional neural network (CNN), deep belief networks (DBN), have enabled better classification accuracies of 84.26 ± 9.10% and 65.43 ± 1.59% as our preliminary study.

Original language	English
Title of host publication	Recent Trends in Communication, Computing, and Electronics - Select Proceedings of IC3E 2018
Editors	Ishwar K. Sethi, Ashish Khare, Nar Singh, Uma Shankar Tiwary
Publisher	Springer Verlag
Pages	431-440
Number of pages	10
ISBN (Print)	9789811326844
DOIs	https://doi.org/10.1007/978-981-13-2685-1_41
State	Published - 2019
Event	International Conference on Emerging Trends in Communication, Computing and Electronics, IC3E 2018 - [city ]Allahabad, India Duration: 13 Apr 2019 → 15 Apr 2019

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	524
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Other

Other	International Conference on Emerging Trends in Communication, Computing and Electronics, IC3E 2018
Country/Territory	India
City	[city ]Allahabad
Period	13/04/19 → 15/04/19

Keywords

Convolutional neural networks
Deep belief networks
Functional near infrared spectroscopy
Stroop task experiments

Access to Document

10.1007/978-981-13-2685-1_41

Cite this

Ho, T. K. K., Gwak, J., Park, C. M., Khare, A., & Song, J. I. (2019). Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS. In I. K. Sethi, A. Khare, N. Singh, & U. S. Tiwary (Eds.), Recent Trends in Communication, Computing, and Electronics - Select Proceedings of IC3E 2018 (pp. 431-440). (Lecture Notes in Electrical Engineering; Vol. 524). Springer Verlag. https://doi.org/10.1007/978-981-13-2685-1_41

Ho, Thi Kieu Khanh ; Gwak, Jeonghwan ; Park, Chang Min et al. / Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS. Recent Trends in Communication, Computing, and Electronics - Select Proceedings of IC3E 2018. editor / Ishwar K. Sethi ; Ashish Khare ; Nar Singh ; Uma Shankar Tiwary. Springer Verlag, 2019. pp. 431-440 (Lecture Notes in Electrical Engineering).

@inproceedings{8224cfd71a2f4620bda23bff379de12a,

title = "Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS",

abstract = "As a non-invasive optical neuroimaging technique, functional near infrared spectroscopy (fNIRS) is currently used to assess brain dynamics during the performance of complex works and everyday tasks. However, the deep learning approaches to distinguish stress levels based on the changes of hemoglobin concentrations have not yet been extensively investigated. In this paper, we evaluated the efficiencies of advanced methods differentiating the rest and task periods during stroop task experiments. First, we explored that the apparent changes of oxy-hemoglobin (HbO) and deoxy-hemoglobin (HbR) concentrations associated with two mental stages did exist across each participant. Then, a novel discrimination framework was studied. Deep learning approaches, including convolutional neural network (CNN), deep belief networks (DBN), have enabled better classification accuracies of 84.26 ± 9.10% and 65.43 ± 1.59% as our preliminary study.",

keywords = "Convolutional neural networks, Deep belief networks, Functional near infrared spectroscopy, Stroop task experiments",

author = "Ho, {Thi Kieu Khanh} and Jeonghwan Gwak and Park, {Chang Min} and Ashish Khare and Song, {Jong In}",

note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd. 2019.; null ; Conference date: 13-04-2019 Through 15-04-2019",

year = "2019",

doi = "10.1007/978-981-13-2685-1_41",

language = "English",

isbn = "9789811326844",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "431--440",

editor = "Sethi, {Ishwar K.} and Ashish Khare and Nar Singh and Tiwary, {Uma Shankar}",

booktitle = "Recent Trends in Communication, Computing, and Electronics - Select Proceedings of IC3E 2018",

}

Ho, TKK, Gwak, J, Park, CM, Khare, A & Song, JI 2019, Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS. in IK Sethi, A Khare, N Singh & US Tiwary (eds), Recent Trends in Communication, Computing, and Electronics - Select Proceedings of IC3E 2018. Lecture Notes in Electrical Engineering, vol. 524, Springer Verlag, pp. 431-440, International Conference on Emerging Trends in Communication, Computing and Electronics, IC3E 2018, [city ]Allahabad, India, 13/04/19. https://doi.org/10.1007/978-981-13-2685-1_41

Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS. / Ho, Thi Kieu Khanh; Gwak, Jeonghwan; Park, Chang Min et al.

Recent Trends in Communication, Computing, and Electronics - Select Proceedings of IC3E 2018. ed. / Ishwar K. Sethi; Ashish Khare; Nar Singh; Uma Shankar Tiwary. Springer Verlag, 2019. p. 431-440 (Lecture Notes in Electrical Engineering; Vol. 524).

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

TY - GEN

T1 - Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS

AU - Ho, Thi Kieu Khanh

AU - Gwak, Jeonghwan

AU - Park, Chang Min

AU - Khare, Ashish

AU - Song, Jong In

N1 - Publisher Copyright: © Springer Nature Singapore Pte Ltd. 2019.

PY - 2019

Y1 - 2019

N2 - As a non-invasive optical neuroimaging technique, functional near infrared spectroscopy (fNIRS) is currently used to assess brain dynamics during the performance of complex works and everyday tasks. However, the deep learning approaches to distinguish stress levels based on the changes of hemoglobin concentrations have not yet been extensively investigated. In this paper, we evaluated the efficiencies of advanced methods differentiating the rest and task periods during stroop task experiments. First, we explored that the apparent changes of oxy-hemoglobin (HbO) and deoxy-hemoglobin (HbR) concentrations associated with two mental stages did exist across each participant. Then, a novel discrimination framework was studied. Deep learning approaches, including convolutional neural network (CNN), deep belief networks (DBN), have enabled better classification accuracies of 84.26 ± 9.10% and 65.43 ± 1.59% as our preliminary study.

AB - As a non-invasive optical neuroimaging technique, functional near infrared spectroscopy (fNIRS) is currently used to assess brain dynamics during the performance of complex works and everyday tasks. However, the deep learning approaches to distinguish stress levels based on the changes of hemoglobin concentrations have not yet been extensively investigated. In this paper, we evaluated the efficiencies of advanced methods differentiating the rest and task periods during stroop task experiments. First, we explored that the apparent changes of oxy-hemoglobin (HbO) and deoxy-hemoglobin (HbR) concentrations associated with two mental stages did exist across each participant. Then, a novel discrimination framework was studied. Deep learning approaches, including convolutional neural network (CNN), deep belief networks (DBN), have enabled better classification accuracies of 84.26 ± 9.10% and 65.43 ± 1.59% as our preliminary study.

KW - Convolutional neural networks

KW - Deep belief networks

KW - Functional near infrared spectroscopy

KW - Stroop task experiments

UR - http://www.scopus.com/inward/record.url?scp=85058549794&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-2685-1_41

DO - 10.1007/978-981-13-2685-1_41

M3 - Conference contribution

AN - SCOPUS:85058549794

SN - 9789811326844

T3 - Lecture Notes in Electrical Engineering

SP - 431

EP - 440

BT - Recent Trends in Communication, Computing, and Electronics - Select Proceedings of IC3E 2018

A2 - Sethi, Ishwar K.

A2 - Khare, Ashish

A2 - Singh, Nar

A2 - Tiwary, Uma Shankar

PB - Springer Verlag

Y2 - 13 April 2019 through 15 April 2019

ER -

Ho TKK, Gwak J, Park CM, Khare A, Song JI. Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS. In Sethi IK, Khare A, Singh N, Tiwary US, editors, Recent Trends in Communication, Computing, and Electronics - Select Proceedings of IC3E 2018. Springer Verlag. 2019. p. 431-440. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-13-2685-1_41

Deep leaning-based approach for mental workload discrimination from multi-channel fNIRS

Abstract

Publication series

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this