Application of an improved independent component analysis to artifacts removal from EEG

Zhihong Peng; Junping Luo

Application of an improved independent component analysis to artifacts removal from EEG

Zhihong Peng^*, Junping Luo

^*Corresponding author for this work

School of Automation

Beijing Institute of Technology

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

Abstract

EEG data can be easily influenced by other components in the process of recording, which would thus interfere the analysis. Independent Component Analysis (ICA) is a valid method for blind source separation. It can estimate original signals' independent components from observed signals even the original signals and mixing model are unknown. Considering the shortcomings of the application of two ICA algorithms, FastICA and extended Infomax, to EEG artifacts removal, we propose a novel InfastICA algorithm by combing FastICA and extended Infomax. By appling to removal of the EOG artifacts from EEG, test results show that this new algorithm has no special requests to the matrix W's default values and study steps, and has a fast convergence speed, with simple operation and practical application.

Original language	English
Title of host publication	Proceedings of the 29th Chinese Control Conference, CCC'10
Pages	2784-2787
Number of pages	4
Publication status	Published - 2010
Event	29th Chinese Control Conference, CCC'10 - Beijing, China Duration: 29 Jul 2010 → 31 Jul 2010

Publication series

Name	Proceedings of the 29th Chinese Control Conference, CCC'10

Conference

Conference	29th Chinese Control Conference, CCC'10
Country/Territory	China
City	Beijing
Period	29/07/10 → 31/07/10

Keywords

Artifacts removal
Electro-oculogram (EOG)
Electroencephalo-graph (EEG)
Independent component analysis (ICA)

Cite this

@inproceedings{15df6d28d94e4d9a971e43b38920d90a,

title = "Application of an improved independent component analysis to artifacts removal from EEG",

abstract = "EEG data can be easily influenced by other components in the process of recording, which would thus interfere the analysis. Independent Component Analysis (ICA) is a valid method for blind source separation. It can estimate original signals' independent components from observed signals even the original signals and mixing model are unknown. Considering the shortcomings of the application of two ICA algorithms, FastICA and extended Infomax, to EEG artifacts removal, we propose a novel InfastICA algorithm by combing FastICA and extended Infomax. By appling to removal of the EOG artifacts from EEG, test results show that this new algorithm has no special requests to the matrix W's default values and study steps, and has a fast convergence speed, with simple operation and practical application.",

keywords = "Artifacts removal, Electro-oculogram (EOG), Electroencephalo-graph (EEG), Independent component analysis (ICA)",

author = "Zhihong Peng and Junping Luo",

year = "2010",

language = "English",

isbn = "9787894631046",

series = "Proceedings of the 29th Chinese Control Conference, CCC'10",

pages = "2784--2787",

booktitle = "Proceedings of the 29th Chinese Control Conference, CCC'10",

note = "29th Chinese Control Conference, CCC'10 ; Conference date: 29-07-2010 Through 31-07-2010",

}

Application of an improved independent component analysis to artifacts removal from EEG. / Peng, Zhihong; Luo, Junping.
Proceedings of the 29th Chinese Control Conference, CCC'10. 2010. p. 2784-2787 5572430 (Proceedings of the 29th Chinese Control Conference, CCC'10).

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

TY - GEN

T1 - Application of an improved independent component analysis to artifacts removal from EEG

AU - Peng, Zhihong

AU - Luo, Junping

PY - 2010

Y1 - 2010

N2 - EEG data can be easily influenced by other components in the process of recording, which would thus interfere the analysis. Independent Component Analysis (ICA) is a valid method for blind source separation. It can estimate original signals' independent components from observed signals even the original signals and mixing model are unknown. Considering the shortcomings of the application of two ICA algorithms, FastICA and extended Infomax, to EEG artifacts removal, we propose a novel InfastICA algorithm by combing FastICA and extended Infomax. By appling to removal of the EOG artifacts from EEG, test results show that this new algorithm has no special requests to the matrix W's default values and study steps, and has a fast convergence speed, with simple operation and practical application.

AB - EEG data can be easily influenced by other components in the process of recording, which would thus interfere the analysis. Independent Component Analysis (ICA) is a valid method for blind source separation. It can estimate original signals' independent components from observed signals even the original signals and mixing model are unknown. Considering the shortcomings of the application of two ICA algorithms, FastICA and extended Infomax, to EEG artifacts removal, we propose a novel InfastICA algorithm by combing FastICA and extended Infomax. By appling to removal of the EOG artifacts from EEG, test results show that this new algorithm has no special requests to the matrix W's default values and study steps, and has a fast convergence speed, with simple operation and practical application.

KW - Artifacts removal

KW - Electro-oculogram (EOG)

KW - Electroencephalo-graph (EEG)

KW - Independent component analysis (ICA)

UR - http://www.scopus.com/inward/record.url?scp=78650241625&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:78650241625

SN - 9787894631046

T3 - Proceedings of the 29th Chinese Control Conference, CCC'10

SP - 2784

EP - 2787

BT - Proceedings of the 29th Chinese Control Conference, CCC'10

T2 - 29th Chinese Control Conference, CCC'10

Y2 - 29 July 2010 through 31 July 2010

ER -

Application of an improved independent component analysis to artifacts removal from EEG

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this