Abstract
Detecting artifacts produced in electroencephalographic (EEG) data by muscle activity, eye blinks and electrical noise, etc., is an important problem in EEG signal processing research. These artifacts must be corrected before further analysis because it renders subsequent analysis very error-prone. One solution is to reject the data segment if artifact is present during the observation interval, however, the rejected data segment could contain important information masked by the artifact. It has already been demonstrated that independent component analysis (ICA) can be an effective and applicable method for EEG de-noising. The goal of this paper is to propose a framework, based on ICA and wavelet denoising (WD), to improve the pre-processing of EEG signals. In particular we employ the concept of spatially-constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any brain activity from extracted artifacts, and finally project back the artifacts to be subtracted from EEG signals to get clean EEG data. The main advantage of the proposed approach is faster computation, as all ICs are not identified in the usual manner due to the square mixing assumption. Simulation results demonstrate the effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.
Original language | English |
---|---|
Title of host publication | Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society |
Subtitle of host publication | Engineering the Future of Biomedicine, EMBC 2009 |
Pages | 4027-4030 |
Number of pages | 4 |
DOIs | |
Publication status | Published - Dec 1 2009 |
Event | 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009 - Minneapolis, MN, United States Duration: Sep 2 2009 → Sep 6 2009 |
Publication series
Name | Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009 |
---|
Conference
Conference | 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009 |
---|---|
Country | United States |
City | Minneapolis, MN |
Period | 9/2/09 → 9/6/09 |
Fingerprint
Keywords
- Algorithms
- Artifacts
- Artificial Intelligence
- Brain
- Brain Mapping
- Brain Mapping: methods
- Brain: pathology
- Computer Simulation
- Data Interpretation, Statistical
- Electroencephalography
- Electroencephalography: instrumentation
- Electroencephalography: methods
- Humans
- Pattern Recognition, Automated
- Pattern Recognition, Automated: methods
- Signal Processing, Computer-Assisted
- Software
- Time Factors
ASJC Scopus subject areas
- Cell Biology
- Developmental Biology
- Biomedical Engineering
- Medicine(all)
Cite this
Focal artifact removal from ongoing EEG - A hybrid approach based on spatially-constrained ICA and wavelet de-noising. / Akhtar, Muhammad Tahir; James, Christopher J.
Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009. 2009. p. 4027-4030 5333725 (Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Focal artifact removal from ongoing EEG - A hybrid approach based on spatially-constrained ICA and wavelet de-noising
AU - Akhtar, Muhammad Tahir
AU - James, Christopher J.
PY - 2009/12/1
Y1 - 2009/12/1
N2 - Detecting artifacts produced in electroencephalographic (EEG) data by muscle activity, eye blinks and electrical noise, etc., is an important problem in EEG signal processing research. These artifacts must be corrected before further analysis because it renders subsequent analysis very error-prone. One solution is to reject the data segment if artifact is present during the observation interval, however, the rejected data segment could contain important information masked by the artifact. It has already been demonstrated that independent component analysis (ICA) can be an effective and applicable method for EEG de-noising. The goal of this paper is to propose a framework, based on ICA and wavelet denoising (WD), to improve the pre-processing of EEG signals. In particular we employ the concept of spatially-constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any brain activity from extracted artifacts, and finally project back the artifacts to be subtracted from EEG signals to get clean EEG data. The main advantage of the proposed approach is faster computation, as all ICs are not identified in the usual manner due to the square mixing assumption. Simulation results demonstrate the effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.
AB - Detecting artifacts produced in electroencephalographic (EEG) data by muscle activity, eye blinks and electrical noise, etc., is an important problem in EEG signal processing research. These artifacts must be corrected before further analysis because it renders subsequent analysis very error-prone. One solution is to reject the data segment if artifact is present during the observation interval, however, the rejected data segment could contain important information masked by the artifact. It has already been demonstrated that independent component analysis (ICA) can be an effective and applicable method for EEG de-noising. The goal of this paper is to propose a framework, based on ICA and wavelet denoising (WD), to improve the pre-processing of EEG signals. In particular we employ the concept of spatially-constrained ICA (SCICA) to extract artifact-only independent components (ICs) from the given EEG data, use WD to remove any brain activity from extracted artifacts, and finally project back the artifacts to be subtracted from EEG signals to get clean EEG data. The main advantage of the proposed approach is faster computation, as all ICs are not identified in the usual manner due to the square mixing assumption. Simulation results demonstrate the effectiveness of the proposed approach in removing focal artifacts that can be well separated by SCICA.
KW - Algorithms
KW - Artifacts
KW - Artificial Intelligence
KW - Brain
KW - Brain Mapping
KW - Brain Mapping: methods
KW - Brain: pathology
KW - Computer Simulation
KW - Data Interpretation, Statistical
KW - Electroencephalography
KW - Electroencephalography: instrumentation
KW - Electroencephalography: methods
KW - Humans
KW - Pattern Recognition, Automated
KW - Pattern Recognition, Automated: methods
KW - Signal Processing, Computer-Assisted
KW - Software
KW - Time Factors
UR - http://www.scopus.com/inward/record.url?scp=77950968956&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77950968956&partnerID=8YFLogxK
U2 - 10.1109/IEMBS.2009.5333725
DO - 10.1109/IEMBS.2009.5333725
M3 - Conference contribution
C2 - 19964336
AN - SCOPUS:77950968956
SN - 9781424432967
T3 - Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society: Engineering the Future of Biomedicine, EMBC 2009
SP - 4027
EP - 4030
BT - Proceedings of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society
ER -