Classification of the motion artifacts in near-infrared spectroscopy based on wavelet statistical feature

Seung Bo Lee, Hakseung Kim, Seho Lee, Hyun Ji Kim, Seong Whan Lee, Dong Joo Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Near-infrared spectroscopy (NIRS) is receiving much attention in the fields of brain-computer interface (BCI) due to its noninvasiveness, usability, and high performance. However, NIRS is susceptible to the motion artifacts, and its high morphological variety hinders the existing signals artifacts elimination techniques from being applied to NIRS. This study proposes a novel feature extraction method for classifying motion artifacts. NIRS data from an open access dataset containing five types of motion artifact (i.e., eye blinking, head movement, eyes movement, teeth clenching, and mouth opening) from 28 healthy subjects were analyzed. The efficacy of the proposed wavelet statistical feature extraction method in artifact classification was compared to various existing feature extraction methods for BCI designs. Each feature was learned by four conventional machine learning models for classifying NIRS motion artifacts. Shrinkage regularized linear discriminant analysis (SRLDA) with the proposed features derived from oxy and deoxy-hemoglobin NIRS signal achieved 90% accuracy and 0.85 Cohen's kappa coefficient for classifying types of motion artifacts. Mann-Whitney U test and paired T-test indicate that SRLDA with the proposed feature had significantly higher classification performance compared to the other models. The proposed method can reliably classify the motion artifacts to standardize the morphology types of NIRS artifact. It could be used to augment signal quality control technique with further extension in future NIRS-based BCI systems.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2144-2148
Number of pages5
ISBN (Electronic)9781728145693
DOIs
Publication statusPublished - 2019 Oct
Event2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019 - Bari, Italy
Duration: 2019 Oct 62019 Oct 9

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume2019-October
ISSN (Print)1062-922X

Conference

Conference2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019
CountryItaly
CityBari
Period19/10/619/10/9

Fingerprint

Near infrared spectroscopy
Brain computer interface
Feature extraction
Discriminant analysis
Eye movements
Hemoglobin
Quality control
Learning systems

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Human-Computer Interaction

Cite this

Lee, S. B., Kim, H., Lee, S., Kim, H. J., Lee, S. W., & Kim, D. J. (2019). Classification of the motion artifacts in near-infrared spectroscopy based on wavelet statistical feature. In 2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019 (pp. 2144-2148). [8914331] (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics; Vol. 2019-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SMC.2019.8914331

Classification of the motion artifacts in near-infrared spectroscopy based on wavelet statistical feature. / Lee, Seung Bo; Kim, Hakseung; Lee, Seho; Kim, Hyun Ji; Lee, Seong Whan; Kim, Dong Joo.

2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2144-2148 8914331 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics; Vol. 2019-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, SB, Kim, H, Lee, S, Kim, HJ, Lee, SW & Kim, DJ 2019, Classification of the motion artifacts in near-infrared spectroscopy based on wavelet statistical feature. in 2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019., 8914331, Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, vol. 2019-October, Institute of Electrical and Electronics Engineers Inc., pp. 2144-2148, 2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019, Bari, Italy, 19/10/6. https://doi.org/10.1109/SMC.2019.8914331
Lee SB, Kim H, Lee S, Kim HJ, Lee SW, Kim DJ. Classification of the motion artifacts in near-infrared spectroscopy based on wavelet statistical feature. In 2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2144-2148. 8914331. (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). https://doi.org/10.1109/SMC.2019.8914331
Lee, Seung Bo ; Kim, Hakseung ; Lee, Seho ; Kim, Hyun Ji ; Lee, Seong Whan ; Kim, Dong Joo. / Classification of the motion artifacts in near-infrared spectroscopy based on wavelet statistical feature. 2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 2144-2148 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).
@inproceedings{93b14f6e789b490f9ac0508c8ffdf1d9,
title = "Classification of the motion artifacts in near-infrared spectroscopy based on wavelet statistical feature",
abstract = "Near-infrared spectroscopy (NIRS) is receiving much attention in the fields of brain-computer interface (BCI) due to its noninvasiveness, usability, and high performance. However, NIRS is susceptible to the motion artifacts, and its high morphological variety hinders the existing signals artifacts elimination techniques from being applied to NIRS. This study proposes a novel feature extraction method for classifying motion artifacts. NIRS data from an open access dataset containing five types of motion artifact (i.e., eye blinking, head movement, eyes movement, teeth clenching, and mouth opening) from 28 healthy subjects were analyzed. The efficacy of the proposed wavelet statistical feature extraction method in artifact classification was compared to various existing feature extraction methods for BCI designs. Each feature was learned by four conventional machine learning models for classifying NIRS motion artifacts. Shrinkage regularized linear discriminant analysis (SRLDA) with the proposed features derived from oxy and deoxy-hemoglobin NIRS signal achieved 90{\%} accuracy and 0.85 Cohen's kappa coefficient for classifying types of motion artifacts. Mann-Whitney U test and paired T-test indicate that SRLDA with the proposed feature had significantly higher classification performance compared to the other models. The proposed method can reliably classify the motion artifacts to standardize the morphology types of NIRS artifact. It could be used to augment signal quality control technique with further extension in future NIRS-based BCI systems.",
author = "Lee, {Seung Bo} and Hakseung Kim and Seho Lee and Kim, {Hyun Ji} and Lee, {Seong Whan} and Kim, {Dong Joo}",
year = "2019",
month = "10",
doi = "10.1109/SMC.2019.8914331",
language = "English",
series = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2144--2148",
booktitle = "2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019",

}

TY - GEN

T1 - Classification of the motion artifacts in near-infrared spectroscopy based on wavelet statistical feature

AU - Lee, Seung Bo

AU - Kim, Hakseung

AU - Lee, Seho

AU - Kim, Hyun Ji

AU - Lee, Seong Whan

AU - Kim, Dong Joo

PY - 2019/10

Y1 - 2019/10

N2 - Near-infrared spectroscopy (NIRS) is receiving much attention in the fields of brain-computer interface (BCI) due to its noninvasiveness, usability, and high performance. However, NIRS is susceptible to the motion artifacts, and its high morphological variety hinders the existing signals artifacts elimination techniques from being applied to NIRS. This study proposes a novel feature extraction method for classifying motion artifacts. NIRS data from an open access dataset containing five types of motion artifact (i.e., eye blinking, head movement, eyes movement, teeth clenching, and mouth opening) from 28 healthy subjects were analyzed. The efficacy of the proposed wavelet statistical feature extraction method in artifact classification was compared to various existing feature extraction methods for BCI designs. Each feature was learned by four conventional machine learning models for classifying NIRS motion artifacts. Shrinkage regularized linear discriminant analysis (SRLDA) with the proposed features derived from oxy and deoxy-hemoglobin NIRS signal achieved 90% accuracy and 0.85 Cohen's kappa coefficient for classifying types of motion artifacts. Mann-Whitney U test and paired T-test indicate that SRLDA with the proposed feature had significantly higher classification performance compared to the other models. The proposed method can reliably classify the motion artifacts to standardize the morphology types of NIRS artifact. It could be used to augment signal quality control technique with further extension in future NIRS-based BCI systems.

AB - Near-infrared spectroscopy (NIRS) is receiving much attention in the fields of brain-computer interface (BCI) due to its noninvasiveness, usability, and high performance. However, NIRS is susceptible to the motion artifacts, and its high morphological variety hinders the existing signals artifacts elimination techniques from being applied to NIRS. This study proposes a novel feature extraction method for classifying motion artifacts. NIRS data from an open access dataset containing five types of motion artifact (i.e., eye blinking, head movement, eyes movement, teeth clenching, and mouth opening) from 28 healthy subjects were analyzed. The efficacy of the proposed wavelet statistical feature extraction method in artifact classification was compared to various existing feature extraction methods for BCI designs. Each feature was learned by four conventional machine learning models for classifying NIRS motion artifacts. Shrinkage regularized linear discriminant analysis (SRLDA) with the proposed features derived from oxy and deoxy-hemoglobin NIRS signal achieved 90% accuracy and 0.85 Cohen's kappa coefficient for classifying types of motion artifacts. Mann-Whitney U test and paired T-test indicate that SRLDA with the proposed feature had significantly higher classification performance compared to the other models. The proposed method can reliably classify the motion artifacts to standardize the morphology types of NIRS artifact. It could be used to augment signal quality control technique with further extension in future NIRS-based BCI systems.

UR - http://www.scopus.com/inward/record.url?scp=85076744056&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076744056&partnerID=8YFLogxK

U2 - 10.1109/SMC.2019.8914331

DO - 10.1109/SMC.2019.8914331

M3 - Conference contribution

AN - SCOPUS:85076744056

T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SP - 2144

EP - 2148

BT - 2019 IEEE International Conference on Systems, Man and Cybernetics, SMC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -