A Coarse/Fine Dual-Stage Motion Artifacts Removal Algorithm for Wearable NIRS Systems

Linfeng Zhou; Cheng Chen; Zhenhong Liu; Yinying Hu; Mingyi Chen; Yongfu Li; Yi Hu; Guoxing Wang; Jian Zhao

doi:10.1109/JSEN.2021.3069553

A Coarse/Fine Dual-Stage Motion Artifacts Removal Algorithm for Wearable NIRS Systems

Linfeng Zhou
, Cheng Chen
, Zhenhong Liu
, Yinying Hu
, Mingyi Chen
, Yongfu Li
, Yi Hu
, Guoxing Wang
, Jian Zhao^*

^*Corresponding author for this work

School of Psychology and Cognitive Science

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

Motivation: This paper proposes a motion artifact removal (MAR) algorithm and its evaluation method for wearable functional near infrared spectroscopy (fNIRS) system. Methods: Two types of motion artifacts (MAs) and their characteristics have been investigated, and a coarse/fine dual-stage MAR method is proposed, which can remove the MAs with different features and magnitudes to protect the original data from damage. In addition, an evaluation method is also proposed based on the classification of 4 mental tasks, which objectively quantize the performance of the MAR algorithms. Results: With the proposed MAR algorithm, the mental-task classification accuracy increased from 74.73% to 83.70% in average.

Original language	English
Article number	9389534
Pages (from-to)	13574-13583
Number of pages	10
Journal	IEEE Sensors Journal
Volume	21
Issue number	12
DOIs	https://doi.org/10.1109/JSEN.2021.3069553
State	Published - 15 Jun 2021

Keywords

Functional near-infrared spectroscopy (fNIRS)
motion artifacts (MAs)
moving standard deviation (MSD)
spline interpolation

Access to Document

10.1109/JSEN.2021.3069553

Cite this

@article{7ebd1779a5644186b105abd88d10bc4d,

title = "A Coarse/Fine Dual-Stage Motion Artifacts Removal Algorithm for Wearable NIRS Systems",

abstract = "Motivation: This paper proposes a motion artifact removal (MAR) algorithm and its evaluation method for wearable functional near infrared spectroscopy (fNIRS) system. Methods: Two types of motion artifacts (MAs) and their characteristics have been investigated, and a coarse/fine dual-stage MAR method is proposed, which can remove the MAs with different features and magnitudes to protect the original data from damage. In addition, an evaluation method is also proposed based on the classification of 4 mental tasks, which objectively quantize the performance of the MAR algorithms. Results: With the proposed MAR algorithm, the mental-task classification accuracy increased from 74.73\% to 83.70\% in average.",

keywords = "Functional near-infrared spectroscopy (fNIRS), motion artifacts (MAs), moving standard deviation (MSD), spline interpolation",

author = "Linfeng Zhou and Cheng Chen and Zhenhong Liu and Yinying Hu and Mingyi Chen and Yongfu Li and Yi Hu and Guoxing Wang and Jian Zhao",

note = "Publisher Copyright: {\textcopyright} 2001-2012 IEEE.",

year = "2021",

month = jun,

day = "15",

doi = "10.1109/JSEN.2021.3069553",

language = "英语",

volume = "21",

pages = "13574--13583",

journal = "IEEE Sensors Journal",

issn = "1530-437X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "12",

}

TY - JOUR

T1 - A Coarse/Fine Dual-Stage Motion Artifacts Removal Algorithm for Wearable NIRS Systems

AU - Zhou, Linfeng

AU - Chen, Cheng

AU - Liu, Zhenhong

AU - Hu, Yinying

AU - Chen, Mingyi

AU - Li, Yongfu

AU - Hu, Yi

AU - Wang, Guoxing

AU - Zhao, Jian

PY - 2021/6/15

Y1 - 2021/6/15

N2 - Motivation: This paper proposes a motion artifact removal (MAR) algorithm and its evaluation method for wearable functional near infrared spectroscopy (fNIRS) system. Methods: Two types of motion artifacts (MAs) and their characteristics have been investigated, and a coarse/fine dual-stage MAR method is proposed, which can remove the MAs with different features and magnitudes to protect the original data from damage. In addition, an evaluation method is also proposed based on the classification of 4 mental tasks, which objectively quantize the performance of the MAR algorithms. Results: With the proposed MAR algorithm, the mental-task classification accuracy increased from 74.73% to 83.70% in average.

AB - Motivation: This paper proposes a motion artifact removal (MAR) algorithm and its evaluation method for wearable functional near infrared spectroscopy (fNIRS) system. Methods: Two types of motion artifacts (MAs) and their characteristics have been investigated, and a coarse/fine dual-stage MAR method is proposed, which can remove the MAs with different features and magnitudes to protect the original data from damage. In addition, an evaluation method is also proposed based on the classification of 4 mental tasks, which objectively quantize the performance of the MAR algorithms. Results: With the proposed MAR algorithm, the mental-task classification accuracy increased from 74.73% to 83.70% in average.

KW - Functional near-infrared spectroscopy (fNIRS)

KW - motion artifacts (MAs)

KW - moving standard deviation (MSD)

KW - spline interpolation

UR - https://www.scopus.com/pages/publications/85103799052

U2 - 10.1109/JSEN.2021.3069553

DO - 10.1109/JSEN.2021.3069553

M3 - 文章

AN - SCOPUS:85103799052

SN - 1530-437X

VL - 21

SP - 13574

EP - 13583

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

IS - 12

M1 - 9389534

ER -

A Coarse/Fine Dual-Stage Motion Artifacts Removal Algorithm for Wearable NIRS Systems

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this