Skip to main content
Log in

Embedded Implementation of Second-Order Blind Identification (SOBI) for Real-Time Applications in Neuroscience

  • Published:
Cognitive Computation Aims and scope Submit manuscript

Abstract

Blind source separation (BSS) is an effective and powerful tool for signal processing and artifact removal in electroencephalographic signals. For real-time applications such as brain–computer interfaces, cognitive neuroscience or clinical neuromonitoring, it is of prime importance that BSS is effectively performed in real time. In order to improve in terms of speed considering the optimal parallelism environment that hardware provides, we build a high-level hardware/software co-simulation based on MATLAB/Simulink for BSS application. To illustrate our approach, we implement the most critical parts of the second-order blind identification algorithm with a fixed-point algorithm on a commercial field-programmable gate array development kit. The results obtained show that co-simulation environment reduces the computation time from 1.9 s to 12.8 ns and thus has great potential for real-time applications.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Bleck TP. Status epilepticus and the use of continuous EEG monitoring in the intensive care unit. Continuum. 2012;18(3):560–78.

    PubMed  Google Scholar 

  2. Vialatte FB, Solé-Casals J, Cichocki A. EEG windowed statistical wavelet scoring for evaluation and discrimination of muscular artifacts. Physiol Meas. 2008;29(12):1435–52.

    Article  PubMed  Google Scholar 

  3. Cichocki A, Washizawa Y, Rutkowski T, Bakardjian H, Phan A-H, Choi S, Lee H. Noninvasive BCIs: multiway signal-processing array decompositions. Computer. 2008;41(10):34–42.

    Article  Google Scholar 

  4. Hsu WY. Independent Component analysis and multiresolution asymmetry ratio for brain–computer interface. Clin EEG Neurosci. 2013;44(2):105–11.

    Article  PubMed  Google Scholar 

  5. Delorme A, Sejnowski T, Makeig S. Enhanced detection of artifacts in EEG data using higher-order statistics and independent component analysis. NeuroImage. 2007;34:1443–9.

    Article  PubMed Central  PubMed  Google Scholar 

  6. Winkler I, Haufe S, Tangermann M. Automatic classification of artifactual ICA-components for artifact removal in EEG signals. Behav Brain Funct. 2011;7:30.

    Article  PubMed Central  PubMed  Google Scholar 

  7. Cherry EC. Some experiments on the recognition of speech, with one and with two ears. J Acoust Soc Am. 1953;24:975–9.

    Article  Google Scholar 

  8. Haykin S, Chen Z. The cocktail party problem. Neural Comput. 2005;17(9):1875–902.

    Article  PubMed  Google Scholar 

  9. Brown GD, Yamada S, Sejnowski TJ. Independent component analysis at the neural cocktail party. Trends Neurosci. 2001;24(1):54–63.

    Article  CAS  PubMed  Google Scholar 

  10. Zou L, Xu S, Ma Z, Lu J, Su W. Automatic removal of artifacts from attention deficit hyperactivity disorder electroencephalograms based on independent component analysis. Cognit Comput. 2013;5(2):225–33.

    Article  Google Scholar 

  11. Yang L, Lv J, Xiang Y. Underdetermined blind source separation by parallel factor analysis in time-frequency domain. Cognit Comput. 2013;5(2):207–14.

    Article  CAS  Google Scholar 

  12. Fitzgibbon SP, Powers DMW, Pope KJ, Clark CR. Removal of EEG noise and artifact using blind source separation. J Clin Neurophysiol. 2007;24(3):232–43.

    Article  CAS  PubMed  Google Scholar 

  13. Koldovsky Z, Phan A-H, Tichavsky P, Cichocki A. A treatment of EEG motor imagery data by underdetermined blind source separation. In: Proceedings of 20th European signal processing conference (EUSIPCO), 2012; 1484–1488.

  14. ZKoldovsky Z, Tichavsky P, Phan A-H, Cichocki AA, Two-Stage MMSE. Beamformer for underdetermined signal separation. IEEE Signal Process Lett. 2013;20(12):1227–30.

    Article  Google Scholar 

  15. Li R, Principe JC. Blinking artifact removal in cognitive EEG data using ICA. Conf Proc IEEE Eng Med Biol Soc. 2006;1:5273–6.

    Article  PubMed  Google Scholar 

  16. Roth C, Gupta CN, Plis SM, Damaraju E, Khullar S, Calhoun VD, Bridwell DA. The influence of visuospatial attention on unattended auditory 40 Hz responses. Front Hum Neurosci. 2013;15(7):370.

    Google Scholar 

  17. Pichevar R, Rouat J. A 3 quantitative evaluation of a bio-inspired sound segregation technique for two- and three-source mixtures. In: Nonlinear speech modeling and applications, Berlin: Springer; 2005. p. 392–396.

  18. Engelbrecht AP. Computational intelligence: an introduction. 2nd ed. New York: Wiley; 2007.

    Book  Google Scholar 

  19. Mognon A, Jovicich J, Bruzzone L, Buiatti M. ADJUST: an automatic EEG artifact detector based on the joint use of spatial and temporal features. Psychophysiology. 2011;48(2):229–40.

    Article  Google Scholar 

  20. Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G, Vaughan TM. Brain–computer interfaces for communication and control. Clin Neurophysiol. 2002;113(6):767–91.

    Article  PubMed  Google Scholar 

  21. Gao J, Zheng C, Wang P. Online removal of muscle artifact from electroencephalogram signals based on canonical correlation analysis. Clin EEG Neurosci. 2010;41(1):53–9.

    Article  PubMed  Google Scholar 

  22. Zander TO, Kothe C. Towards passive brain–computer interfaces: applying brain–computer interface technology to human–machine systems in general. J Neural Eng. 2011;8(2):025005.

    Article  PubMed  Google Scholar 

  23. Delorme A, Makeig S, Fabre-Thorpe M, Sejnowski T. From single-trials EEG to brain area dynamics. Neurocomputing. 2002;44–46:1057–64.

    Article  Google Scholar 

  24. Hyvärinen A. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans Neural Netw. 1999;10(3):626–34.

    Article  PubMed  Google Scholar 

  25. Hyvärinen A, Karhunen J, Oja E. Independent component analysis. Hoboken: Wiley; 2001.

    Book  Google Scholar 

  26. Bell AJ, Sejnowski TJ. An information-maximization approach to blind separation and blind deconvolution. Neural Comput. 1995;7(6):1129–59.

    Article  CAS  PubMed  Google Scholar 

  27. Shayegh F, Erfanian A. Real-time ocular artifacts suppression from EEG signals using an unsupervised adaptive blind source separation. Conf Proc IEEE Eng Med Biol Soc. 2006;1:5269–72.

    Article  PubMed  Google Scholar 

  28. Joyce CA, Gorodnitsky IF, Kutasb M. Automatic removal of eye movement and blink artifacts from EEG data using blind component separation. Psychophysiology. 2004;41:313–25.

    Article  PubMed  Google Scholar 

  29. Belouchrani A, Abed-Meraim K, Cardoso J-F, Moulines E. A blind source separation technique using second order statistics. IEEE Trans Signal Process. 1997;45(2):434–44.

    Article  Google Scholar 

  30. Huang W-C, Hung S-H, Chung J-F, Chang M-H, Van L-D, Lin C-T. FPGA implementation of 4-channel ICA for on-line EEG signal separation. IEEE Biomed Circuits Syst Conf. 2008;20–22:65–8.

    Google Scholar 

  31. Shyu K–K, Lee M-H, Wu Y-T, Lee P-L. Implementation of pipelined FastICA on FPGA for real-time blind source separation. IEEE Trans Neural Netw. 2008;19(6):958–70.

    Article  PubMed  Google Scholar 

  32. Cichocki A, Amari S-I, Siwek K, Tanaka T, Phan AH et al. ICALAB Toolboxes, http://www.bsp.brain.riken.jp/ICALAB.

  33. Kim C-M, Park H-M, Kim T, Choi Y-K, Lee S-Y. FPGA implementation of ICA algorithm for blind signal separation and adaptive noise canceling. IEEE Trans Neural Netw. 2003;14(5):1038–46.

    Article  PubMed  Google Scholar 

  34. Li Z, Lin Q. FPGA implementation of Infomax BSS algorithm with fixed-point number representation, ICNN&B’05 an international conference on neural networks and brain, 13–15 Oct 2005.

  35. Du H, Qi H. An FPGA implementation of parallel ICA for dimensionality reduction in hyperspectral images. In: Proceeding 2004 IEEE international geoscience and remote sensing symposium, 2004.

  36. Wang Y, Sutherland MT, Sanfratello LL, Tang CC. Single-trial classification of Erps using second-order blind identification (SOBI). In: Proceedings of the international conference on machine learning and cybernetics, 2004; 7.

  37. Vorobyov SA. Blind unitary prewhitening with a real-valued eigendecomposition. Circuits Syst Signal Process. 2006;25(3):421–9.

    Article  Google Scholar 

  38. Tichavský P, Doron E, Yeredor A, Nielsen J. A computationally affordable implementation an asymptotically optimal BSS algorithm for AR sources. In: Proceedings EUSIPCO, Florence, Italy, 2006.

  39. Tong L, Soon VC, Liu R, Huang Y. AMUSE: a new blind identification algorithm. In: Proceedings ISCAS, New Orleans, LA, 1990.

  40. Belouchrani A, Abed-Meraim K, Cardoso J-F, Moulines E. Second-order blind separation of correlated sources, In: Proceedings International Conference Digital Signal Processing, Cyprus, 1993;346–351.

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to François-Benoît Vialatte.

Additional information

Xun Zhang and François-Benoît Vialatte are co-first authors of this manuscript.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, X., Vialatte, FB., Chen, C. et al. Embedded Implementation of Second-Order Blind Identification (SOBI) for Real-Time Applications in Neuroscience. Cogn Comput 7, 56–63 (2015). https://doi.org/10.1007/s12559-014-9282-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12559-014-9282-z

Keywords

Navigation