Email this article 
Open Access
Subscription or Fee Access
Efficient Removal of Artifacts from EEG recordings by ICA and Fast ICA Techniques
Abstract
EEG, a highly complex signal, is one of the most common sources of information used to study brain function and neurological disorders. A vital problem in EEG analysis is the mixing of the signals with various other signals, such as eye blinks or pulse signals. These signals must be removed for precise analysis of EEG. One main challenge for EEG denoising is the identification of the artifactual components in EEG. ICA is a statistical method by which corrupted EEG signal is decomposed and artifacts in it can be detected. This paper illustrates the ICA and fast ICA technique for EEG artifact detection and removal. Before applying ICA, preprocessing of the EEG data is done using Centering and Sphering. From results we found that, time needed to separate the EEG signals from mixture of signals using ICA algorithm is very large. Therefore, Fast ICA algorithm is developed and results shows that time required to separate the components using our fast ICA algorithm is very less as compared to ICA. Almost same accuracy as in ICA is achieved by our Fast ICA technique, with some time improvement.
Keywords
References
J. Bayliss, “A Flexible Brain-Computer Interface”, Ph.D. Thesis, Computer Science Dept., U. Rochester, August 2001.
Back A. D. and Weigend A. S., “A first application of independent component analysis to extracting structure from stock returns”, Int. J. on Neural Systems, vol.8,No. 4,pp: 473–484,1997.
Michael Vinther, “Independent Component Analysis of Evoked Potentials in EEG”, December, 2002.
Astolfi, L. , Cincotti, F., Mattia, D., Babiloni, F., Marciani M., De F., Mattiocco M. , Miwakeichi, F. ; Yamaguchi, Y.; Martinez,
P. ,Salinari, S. ; Tocci, A. ; Bakardjian, H. ; Vialatte, F.B. ; Cichocki, Removal of ocular artifacts for high resolution EEG studies: a simulation study”,Top of FormBottom of FormProc. of 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2006. EMBS '06. , pp: 976 - 979, Sept.2006
Inuso G. , La Foresta F. , Mammone N. , Morabito F.C. , “Wavelet-ICA methodology for efficient artifact removal from Electroencephalographic
recordings”, Proc. of International Joint Conference on Top of FormBottom of Form
Neural Networks,
IJCNN 2007. Pp: 1524 - 1529 ,Aug. 2007
Akhtar, M., James C, Mitsuhashi W. ,“Modifying the
Spatially-Constrained ICA for Efficient Removal of Artifacts from EEG Data”, Proc. of 4th International Conference onTop of FormBottom of Form Bioinformatics and Biomedical Engineering (iCBBE) 2010, pp: 1 - 4, June 2010
Guerrero C., Navia A., “Automatic removal of ocular artefacts using adaptive filtering and independent component analysis for electroencephalogram data”, Vol: 6, No.2, pp. 99 – 106, April 2012.
J. Gao, C. Zheng, P. Wang, “Automatic Removal of Ocular Artifacts from EEG Signals” , Proc. 2nd International Conference on Biomedical Engineering and Informatics, 2009. (BMEI) , pp: 1 - 5 2009.
Romo R. ,Ranta R., Louis, V., Maquin D., “EEG Ocular Artefacts and Noise Removal” , proc. of 29th Annual International Conference of the IEEE , Engineering in Medicine and Biology Society, 2007.( EMBS). pp: 5445 - 5448 , 2007
Djuwari D. , Kumar D., Palaniswami, M. , “Limitations of ICA for Artefact Removal ” Proc. of IEEE 27th Annual International Conference of the Engineering in Medicine and Biology Society,(EMBS) 2005. pp 4685 - 4688
Jung T. ,Humphries, C. , Lee T., Makeig, S. , McKeown .J. ,Iragui,V. , Sejnowski, T.J. “Removing lectroencephalographic artifacts: comparison between ICA and PCA”, Proceedings of the 1998 IEEE Signal Processing Society Workshop on Neural Networks for Signal Processing VIII, 1998,pp: 63 - 72
Akhtar M.T. , James C.J., “ Focal artifact removal from ongoing EEG – a hybrid approach based on spatially-constrained ICA and wavelet de-noising”, Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2009.pp. 4027 - 4030 3-6 Sept. 2009.
James N. Knight,”Signal Fraction Analysis and Artifact Removal in EEG”, Master of Science thesis, Department of Computer Science, Colorado State University, Fort Collins, Colorado Fall, 2003.
John G. Proakis, Dimitris G. Manolakis, “Digital Signal Processing Principles, Algorithms, And Applications”,Third edition pp. 556-564. [18] EEG Database: http://www.cs.colostate.edu/eeg/eegSoftw are.html.
Abdulhamit Subasi, M. Ismail Gursoy,” EEG signal classification using PCA, ICA, LDA and support vector machines”, Expert Systems with Applications 37 ,8659–8666,2010.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.