FPGA implementation of 4-channel ICA for on-line EEG signal separation

Wei Chung Huang; Shao Hang Hung; Jen Feng Chung; Meng Hsiu Chang; Lan-Da Van; Chin Teng Lin

doi:10.1109/BIOCAS.2008.4696875

FPGA implementation of 4-channel ICA for on-line EEG signal separation

Wei Chung Huang^*, Shao Hang Hung, Jen Feng Chung, Meng Hsiu Chang, Lan-Da Van, Chin Teng Lin

^*Corresponding author for this work

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

38 Scopus citations

Abstract

Blind source separation of independent sources from their mixtures is a common problem for multi-sensor applications in real world, for example, speech or biomedical signal processing. This paper presents an independent component analysis (ICA) method with information maximiz ation (Infomax) update applied into 4-channel one-line EEG signal separation. This can be implemented on FPGA with a fixed-point number representation, and then the separated signals are transmitted via Bluetooth. As experimental results, the proposed design is faster 56 times than soft performance, and the correlation coefficients at least 80% with the absolute value are compared with off-line processing results. Finally, live demonstration is shown in the DE2 FPGA board, and the design is consisted of 16,605 logic elements.

Original language	English
Title of host publication	2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008
Pages	65-68
Number of pages	4
DOIs	https://doi.org/10.1109/BIOCAS.2008.4696875
State	Published - 1 Dec 2008
Event	2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008 - Baltimore, MD, United States Duration: 20 Nov 2008 → 22 Nov 2008

Publication series

Name	2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008

Conference

Conference	2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008
Country/Territory	United States
City	Baltimore, MD
Period	20/11/08 → 22/11/08

Keywords

Biomedical signal
Blind source separation
Bluetooth
Fixed-point
ICA
Information maximization
Multi-sensor

Access to Document

10.1109/BIOCAS.2008.4696875

Cite this

Huang, W. C., Hung, S. H., Chung, J. F., Chang, M. H., Van, L-D., & Lin, C. T. (2008). FPGA implementation of 4-channel ICA for on-line EEG signal separation. In 2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008 (pp. 65-68). Article 4696875 (2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008). https://doi.org/10.1109/BIOCAS.2008.4696875

@inproceedings{4203f79d10564302ace8e9dd2e3ca4e2,

title = "FPGA implementation of 4-channel ICA for on-line EEG signal separation",

abstract = "Blind source separation of independent sources from their mixtures is a common problem for multi-sensor applications in real world, for example, speech or biomedical signal processing. This paper presents an independent component analysis (ICA) method with information maximiz ation (Infomax) update applied into 4-channel one-line EEG signal separation. This can be implemented on FPGA with a fixed-point number representation, and then the separated signals are transmitted via Bluetooth. As experimental results, the proposed design is faster 56 times than soft performance, and the correlation coefficients at least 80% with the absolute value are compared with off-line processing results. Finally, live demonstration is shown in the DE2 FPGA board, and the design is consisted of 16,605 logic elements.",

keywords = "Biomedical signal, Blind source separation, Bluetooth, Fixed-point, ICA, Information maximization, Multi-sensor",

author = "Huang, {Wei Chung} and Hung, {Shao Hang} and Chung, {Jen Feng} and Chang, {Meng Hsiu} and Lan-Da Van and Lin, {Chin Teng}",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/BIOCAS.2008.4696875",

language = "English",

isbn = "9781424428793",

series = "2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008",

pages = "65--68",

booktitle = "2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008",

note = "2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008 ; Conference date: 20-11-2008 Through 22-11-2008",

}

Huang, WC, Hung, SH, Chung, JF, Chang, MH, Van, L-D & Lin, CT 2008, FPGA implementation of 4-channel ICA for on-line EEG signal separation. in 2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008., 4696875, 2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008, pp. 65-68, 2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008, Baltimore, MD, United States, 20/11/08. https://doi.org/10.1109/BIOCAS.2008.4696875

FPGA implementation of 4-channel ICA for on-line EEG signal separation. / Huang, Wei Chung; Hung, Shao Hang; Chung, Jen Feng et al.
2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008. 2008. p. 65-68 4696875 (2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008).

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

TY - GEN

T1 - FPGA implementation of 4-channel ICA for on-line EEG signal separation

AU - Huang, Wei Chung

AU - Hung, Shao Hang

AU - Chung, Jen Feng

AU - Chang, Meng Hsiu

AU - Van, Lan-Da

AU - Lin, Chin Teng

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Blind source separation of independent sources from their mixtures is a common problem for multi-sensor applications in real world, for example, speech or biomedical signal processing. This paper presents an independent component analysis (ICA) method with information maximiz ation (Infomax) update applied into 4-channel one-line EEG signal separation. This can be implemented on FPGA with a fixed-point number representation, and then the separated signals are transmitted via Bluetooth. As experimental results, the proposed design is faster 56 times than soft performance, and the correlation coefficients at least 80% with the absolute value are compared with off-line processing results. Finally, live demonstration is shown in the DE2 FPGA board, and the design is consisted of 16,605 logic elements.

AB - Blind source separation of independent sources from their mixtures is a common problem for multi-sensor applications in real world, for example, speech or biomedical signal processing. This paper presents an independent component analysis (ICA) method with information maximiz ation (Infomax) update applied into 4-channel one-line EEG signal separation. This can be implemented on FPGA with a fixed-point number representation, and then the separated signals are transmitted via Bluetooth. As experimental results, the proposed design is faster 56 times than soft performance, and the correlation coefficients at least 80% with the absolute value are compared with off-line processing results. Finally, live demonstration is shown in the DE2 FPGA board, and the design is consisted of 16,605 logic elements.

KW - Biomedical signal

KW - Blind source separation

KW - Bluetooth

KW - Fixed-point

KW - ICA

KW - Information maximization

KW - Multi-sensor

UR - http://www.scopus.com/inward/record.url?scp=63649142593&partnerID=8YFLogxK

U2 - 10.1109/BIOCAS.2008.4696875

DO - 10.1109/BIOCAS.2008.4696875

M3 - Conference contribution

AN - SCOPUS:63649142593

SN - 9781424428793

T3 - 2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008

SP - 65

EP - 68

BT - 2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008

T2 - 2008 IEEE-BIOCAS Biomedical Circuits and Systems Conference, BIOCAS 2008

Y2 - 20 November 2008 through 22 November 2008

ER -

FPGA implementation of 4-channel ICA for on-line EEG signal separation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this