Removal of EOG Artifact in Electroencephalography with EEMD-ICA: A Semi-simulation Study on Identification of Artifactual Components

Jingzhou Xu; Wengyao Jiang; Wei Wang; Jianjun Chen; Yixiao Shen; Jun Qi

doi:10.1007/978-3-031-52216-1_10

Removal of EOG Artifact in Electroencephalography with EEMD-ICA: A Semi-simulation Study on Identification of Artifactual Components

Jingzhou Xu, Wengyao Jiang, Wei Wang, Jianjun Chen, Yixiao Shen, Jun Qi^*

^*Corresponding author for this work

Xi'an Jiaotong-Liverpool University

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

Abstract

Purpose: The electroencephalography (EEG) signals recorded in clinical settings are usually corrupted by electrooculography (EOG) artifacts. EEMD-ICA is a commonly used method for removing EOG artifacts. This study aims at exploring the performance of different methods of identification of artifactual components under the framework of EEMD-ICA. Methods: This study is conducted in a semi-simulated way. A EEG dataset covering signal of SNR from -1 to 2 is generated based on the EEG and EOG segments from two public datasets. Characterized by the artifactual components identification method, EEMD-ICA _kurt, EEMD-ICA _entropy, EEMD-ICA _autocor and EEMD-ICA _eogcor are proposed and evaluated in terms of Normalized Mean Square Error (NMSE), Cross Correlation (CC) and Structural Similarity Index (SSIM) on this dataset. Results: EEMD-ICA _autocor outperforms other three approaches and demonstrates the strongest versatility. Besides successfully eliminating EOAs from EEG signals, it loses the least neuron activities. Conclusion: Although performance metrics improve as SNR increases, the loss of structure information also improves (SNR > 1). In practice, it is vital to estimate the SNR of data before applying these approaches because when SNR is high, these methods may have a counterproductive.

Original language	English
Title of host publication	Internet of Things of Big Data for Healthcare - 5th International Workshop, IoTBDH 2023, Proceedings
Editors	Jun Qi, Po Yang
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	111-123
Number of pages	13
ISBN (Print)	9783031522154
DOIs	https://doi.org/10.1007/978-3-031-52216-1_10
Publication status	Published - 2024
Externally published	Yes
Event	5th International Workshop on Internet of Things of Big Data for Healthcare, IoTBDH 2023 - Birmingham, United Kingdom Duration: 21 Oct 2023 → 25 Oct 2023

Publication series

Name	Communications in Computer and Information Science
Volume	2019 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	5th International Workshop on Internet of Things of Big Data for Healthcare, IoTBDH 2023
Country/Territory	United Kingdom
City	Birmingham
Period	21/10/23 → 25/10/23

Keywords

Artifact
EEG
EEMD
ICA
Removal

Access to Document

10.1007/978-3-031-52216-1_10

Cite this

Xu, J., Jiang, W., Wang, W., Chen, J., Shen, Y., & Qi, J. (2024). Removal of EOG Artifact in Electroencephalography with EEMD-ICA: A Semi-simulation Study on Identification of Artifactual Components. In J. Qi, & P. Yang (Eds.), Internet of Things of Big Data for Healthcare - 5th International Workshop, IoTBDH 2023, Proceedings (pp. 111-123). (Communications in Computer and Information Science; Vol. 2019 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-52216-1_10

Xu, Jingzhou ; Jiang, Wengyao ; Wang, Wei et al. / Removal of EOG Artifact in Electroencephalography with EEMD-ICA : A Semi-simulation Study on Identification of Artifactual Components. Internet of Things of Big Data for Healthcare - 5th International Workshop, IoTBDH 2023, Proceedings. editor / Jun Qi ; Po Yang. Springer Science and Business Media Deutschland GmbH, 2024. pp. 111-123 (Communications in Computer and Information Science).

@inproceedings{f088a87df86249108bfa32413bca88b2,

title = "Removal of EOG Artifact in Electroencephalography with EEMD-ICA: A Semi-simulation Study on Identification of Artifactual Components",

abstract = "Purpose: The electroencephalography (EEG) signals recorded in clinical settings are usually corrupted by electrooculography (EOG) artifacts. EEMD-ICA is a commonly used method for removing EOG artifacts. This study aims at exploring the performance of different methods of identification of artifactual components under the framework of EEMD-ICA. Methods: This study is conducted in a semi-simulated way. A EEG dataset covering signal of SNR from -1 to 2 is generated based on the EEG and EOG segments from two public datasets. Characterized by the artifactual components identification method, EEMD-ICA kurt, EEMD-ICA entropy, EEMD-ICA autocor and EEMD-ICA eogcor are proposed and evaluated in terms of Normalized Mean Square Error (NMSE), Cross Correlation (CC) and Structural Similarity Index (SSIM) on this dataset. Results: EEMD-ICA autocor outperforms other three approaches and demonstrates the strongest versatility. Besides successfully eliminating EOAs from EEG signals, it loses the least neuron activities. Conclusion: Although performance metrics improve as SNR increases, the loss of structure information also improves (SNR > 1). In practice, it is vital to estimate the SNR of data before applying these approaches because when SNR is high, these methods may have a counterproductive.",

keywords = "Artifact, EEG, EEMD, ICA, Removal",

author = "Jingzhou Xu and Wengyao Jiang and Wei Wang and Jianjun Chen and Yixiao Shen and Jun Qi",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.; 5th International Workshop on Internet of Things of Big Data for Healthcare, IoTBDH 2023 ; Conference date: 21-10-2023 Through 25-10-2023",

year = "2024",

doi = "10.1007/978-3-031-52216-1_10",

language = "English",

isbn = "9783031522154",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "111--123",

editor = "Jun Qi and Po Yang",

booktitle = "Internet of Things of Big Data for Healthcare - 5th International Workshop, IoTBDH 2023, Proceedings",

}

Xu, J, Jiang, W, Wang, W , Chen, J, Shen, Y & Qi, J 2024, Removal of EOG Artifact in Electroencephalography with EEMD-ICA: A Semi-simulation Study on Identification of Artifactual Components. in J Qi & P Yang (eds), Internet of Things of Big Data for Healthcare - 5th International Workshop, IoTBDH 2023, Proceedings. Communications in Computer and Information Science, vol. 2019 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 111-123, 5th International Workshop on Internet of Things of Big Data for Healthcare, IoTBDH 2023, Birmingham, United Kingdom, 21/10/23. https://doi.org/10.1007/978-3-031-52216-1_10

Removal of EOG Artifact in Electroencephalography with EEMD-ICA: A Semi-simulation Study on Identification of Artifactual Components. / Xu, Jingzhou; Jiang, Wengyao; Wang, Wei et al.
Internet of Things of Big Data for Healthcare - 5th International Workshop, IoTBDH 2023, Proceedings. ed. / Jun Qi; Po Yang. Springer Science and Business Media Deutschland GmbH, 2024. p. 111-123 (Communications in Computer and Information Science; Vol. 2019 CCIS).

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

TY - GEN

T1 - Removal of EOG Artifact in Electroencephalography with EEMD-ICA

T2 - 5th International Workshop on Internet of Things of Big Data for Healthcare, IoTBDH 2023

AU - Xu, Jingzhou

AU - Jiang, Wengyao

AU - Wang, Wei

AU - Chen, Jianjun

AU - Shen, Yixiao

AU - Qi, Jun

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

PY - 2024

Y1 - 2024

N2 - Purpose: The electroencephalography (EEG) signals recorded in clinical settings are usually corrupted by electrooculography (EOG) artifacts. EEMD-ICA is a commonly used method for removing EOG artifacts. This study aims at exploring the performance of different methods of identification of artifactual components under the framework of EEMD-ICA. Methods: This study is conducted in a semi-simulated way. A EEG dataset covering signal of SNR from -1 to 2 is generated based on the EEG and EOG segments from two public datasets. Characterized by the artifactual components identification method, EEMD-ICA kurt, EEMD-ICA entropy, EEMD-ICA autocor and EEMD-ICA eogcor are proposed and evaluated in terms of Normalized Mean Square Error (NMSE), Cross Correlation (CC) and Structural Similarity Index (SSIM) on this dataset. Results: EEMD-ICA autocor outperforms other three approaches and demonstrates the strongest versatility. Besides successfully eliminating EOAs from EEG signals, it loses the least neuron activities. Conclusion: Although performance metrics improve as SNR increases, the loss of structure information also improves (SNR > 1). In practice, it is vital to estimate the SNR of data before applying these approaches because when SNR is high, these methods may have a counterproductive.

AB - Purpose: The electroencephalography (EEG) signals recorded in clinical settings are usually corrupted by electrooculography (EOG) artifacts. EEMD-ICA is a commonly used method for removing EOG artifacts. This study aims at exploring the performance of different methods of identification of artifactual components under the framework of EEMD-ICA. Methods: This study is conducted in a semi-simulated way. A EEG dataset covering signal of SNR from -1 to 2 is generated based on the EEG and EOG segments from two public datasets. Characterized by the artifactual components identification method, EEMD-ICA kurt, EEMD-ICA entropy, EEMD-ICA autocor and EEMD-ICA eogcor are proposed and evaluated in terms of Normalized Mean Square Error (NMSE), Cross Correlation (CC) and Structural Similarity Index (SSIM) on this dataset. Results: EEMD-ICA autocor outperforms other three approaches and demonstrates the strongest versatility. Besides successfully eliminating EOAs from EEG signals, it loses the least neuron activities. Conclusion: Although performance metrics improve as SNR increases, the loss of structure information also improves (SNR > 1). In practice, it is vital to estimate the SNR of data before applying these approaches because when SNR is high, these methods may have a counterproductive.

KW - Artifact

KW - EEG

KW - EEMD

KW - ICA

KW - Removal

UR - http://www.scopus.com/inward/record.url?scp=85184803985&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-52216-1_10

DO - 10.1007/978-3-031-52216-1_10

M3 - Conference Proceeding

AN - SCOPUS:85184803985

SN - 9783031522154

T3 - Communications in Computer and Information Science

SP - 111

EP - 123

BT - Internet of Things of Big Data for Healthcare - 5th International Workshop, IoTBDH 2023, Proceedings

A2 - Qi, Jun

A2 - Yang, Po

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 21 October 2023 through 25 October 2023

ER -

Xu J, Jiang W, Wang W , Chen J, Shen Y, Qi J. Removal of EOG Artifact in Electroencephalography with EEMD-ICA: A Semi-simulation Study on Identification of Artifactual Components. In Qi J, Yang P, editors, Internet of Things of Big Data for Healthcare - 5th International Workshop, IoTBDH 2023, Proceedings. Springer Science and Business Media Deutschland GmbH. 2024. p. 111-123. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-52216-1_10