On-line EEG Denoising and Cleaning Using Correlated Sparse Signal Recovery and Active Learning

  • Manish GuptaEmail author
  • Scott A. Beckett
  • Elizabeth B. Klerman


We have developed two new methods that use sparse recovery and active learning techniques for near real-time artifact identification and removal in electroencephalography (EEG) recordings. The first algorithm, called Correlated Sparse Signal Recovery addresses the problem of structured sparse signal recovery when statistical rather than exact properties describing the structure of the signal are appropriate, as in the elimination of eye movement artifacts; such tasks cannot be done efficiently using structured models that assume a common sparsity profile of fixed groups of components. Our algorithm learns structured sparse coefficients in a Bayesian paradigm. Using it, we have successfully identified and subtracted eye movement (structured) artifacts in real EEG recordings resulting in minimal data loss. Our method outperforms Independent Component Analysis and standard sparse recovery algorithms by preserving both spectral and complexity properties of the denoised EEG. Our second method uses a new active selection algorithm that we call Output-based Active Selection (OAS). When applied to the task of detection of EEG epochs containing other non-structured artifacts from an ensemble of detectors, OAS boosts accuracy of the ensemble from 91 to 97.5% with only 10% active labels. Our methods can also be applied to real-time artifact removal in magnetoencephalography and blood pressure signals.


EEG Structured compressive sensing Structured sparse representation Artifact Bayesian Active learning Ensemble learning Eye blinks Sparse Bayesian learning 


  1. 1.
    M. Gupta, S. Beckett and E. Klerman, “On-line EEG Denoising Using Correlated Sparse Recovery,” Proceedings of 2016 10th International Symposium on Medical Information and Communication (ISMICT 2016), IEEE, p. 123-127.Google Scholar
  2. 2.
    C. Erwin, “Al.(1973),” in Psychophysiologic indices of drowsiness. Detroit, Mich: International Automotive Engineering Congress.Google Scholar
  3. 3.
    C.-T. Lin, R.-C. Wu, S.-F. Liang, W.-H. Chao, Y.-J. Chen and T.-P. Jung, "EEG-based drowsiness estimation for safety driving using independent component analysis," IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 52, no. 12, pp. 2726–2738, dec 2005.Google Scholar
  4. 4.
    S. W. Lockley, C. P. Landrigan, L. K. Barger, and C. A. Czeisler, “When policy meets physiology: the challenge of reducing resident work hours.” Clinical orthopaedics and related research, vol. 449, pp. 116–127, 2006.Google Scholar
  5. 5.
    S. K. L. Lal, A. Craig, P. Boord, L. Kirkup and H. Nguyen, "Development of an algorithm for an EEG-based driver fatigue countermeasure," Journal of Safety Research, vol. 34, no. 3, pp. 321–328, 2003.Google Scholar
  6. 6.
    A. Vuckovic, V. Radivojevic, A . C . N. Chen and D. Popovic, "Automatic recognition of alertness and drowsiness from EEG by an artificial neural network." Medical engineering & physics, vol. 24, no. 5, pp. 349–360, jun 2002.Google Scholar
  7. 7.
    L.-L. Chen, Y. Zhao, J. Zhang and J.-Z. Zou, "Automatic detection of alertness/drowsiness from physiological signals using wavelet-based nonlinear features and machine learning," Expert Systems with Applications, vol. 42, no. 21, pp. 7344–7355, 2015.Google Scholar
  8. 8.
    S. Sareen, S. K. Sood, and S. Kumar, “An Automatic Prediction of Epileptic Seizures Using Cloud Computing and Wireless Sensor Networks,” Journal of Medical Systems, 2016.Google Scholar
  9. 9.
    K. Zeng, J. Yan, Y. Wang, A. Sik, G. Ouyang, and X. Li, “Automatic detection of absence seizures with compressive sensing EEG,” Neurocomputing, vol. 171, no. October 2016, pp. 497–502, 2016.Google Scholar
  10. 10.
    R. Cassani, T. Falk and F. Fraga, "The effects of automated artifact removal algorithms on electroencephalography-based Alzheimer’s disease diagnosis," Frontiers in aging..., vol. 7, no. 10, p. e44439, jan 2014.Google Scholar
  11. 11.
    I. Erkens and G. G. Molina, “Artifact detection and correction in Neurofeedback and BCI applications,” Electronics, 2008.Google Scholar
  12. 12.
    R. J. Farney, J. M. Walker, T. V. Cloward, K. C. Shilling, K. M. Boyle and R. G. Simons, "Polysomnography in hospitalized patients using a wireless wide area network," J Clin Sleep Med, vol. 2, no. 1, pp. 28–34, 2006.Google Scholar
  13. 13.
    V. Mihajlovic, B. Grundlehner, R. Vullers and J. Penders, "Wearable, wireless EEG solutions in daily life applications: What are we missing?" IEEE Journal of Biomedical and Health Informatics, vol. 19, no. 1, pp. 6–21, 2015.Google Scholar
  14. 14.
    P. Khatwani and A. Tiwari, "A survey on different noise removal techniques of EEG signals," Interntional Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), vol. 2, no. 2, pp. 1091–1095, jan 2013.Google Scholar
  15. 15.
    T.-P. P. Jung, S. Makeig, C. Humphries, T.-W. W. Lee, M. J. McKeown, V. Iragui and T. J. Sejnowski, Removing electroencephalographic artifacts by blind source separation, Tech. Rep., Vol. 2, jan 2000.Google Scholar
  16. 16.
    H. V. Semlitsch, P. Anderer, P. Schuster and O. Presslich, "A solution for reliable and valid reduction of ocular artifacts, applied to the P300 ERP." Psychophysiology, vol. 23, no. 6, pp. 695–703, 1986.Google Scholar
  17. 17.
    A. Delorme, S. Makeig and T. Sejnowski, "Automatic artifact rejection for EEG data using high-order statistics and independent component analysis," International workshop on ICA, vol. 7, no. 10, pp. 457–462, jan 2001.Google Scholar
  18. 18.
    D. Schachinger, K. Schindler, and T. Kluge, “Automatic reduction of artifacts in EEG-signals,” 2007 15th International Conference on Digital Signal Processing, DSP 2007, vol. 7, no. 10, pp. 143–146, jan 2007.Google Scholar
  19. 19.
    R. Baraniuk, “Compressive sensing,” 2008 42nd Annual Conference on Information Sciences and Systems, 2008.Google Scholar
  20. 20.
    L. Yu, H. Sun, J. P. Barbot and G. Zheng, "Bayesian compressive sensing for cluster structured sparse signals," Signal Processing, vol. 92, no. 1, pp. 259–269, 2012.Google Scholar
  21. 21.
    D. Wipf, D. Wipf, B. Rao and B. Rao, "Sparse bayesian learning for basis selection," IEEE Trans. on Signal Processing, Special Issue on Machine Learning Methods in Signal Processing, vol. 52, no. 8, pp. 2153–2164, 2004.Google Scholar
  22. 22.
    S. Ji, Y. Xue, and L. Carin, “Bayesian compressive sensing,” IEEE Transactions on Signal Processing, vol. 56, no. 6, pp. 2346–2356, 2008.Google Scholar
  23. 23.
    Z. Zhang and B. D. Rao, “Sparse Signal Recovery With Temporally Correlated Source Vectors Using Sparse Bayesian Learning,” IEEE Journal of Selected Topics in Signal Processing, vol. 5, no. 5, pp. 912–926, 2011.Google Scholar
  24. 24.
    ——, “Extension of SBL algorithms for the recovery of block sparse signals with intra-block correlation,” IEEE Transactions on Signal Processing, vol. 61, no. 8, pp. 2009–2015, 2013.Google Scholar
  25. 25.
    J. Barnard, R. McCulloch, and X.-L. Meng, “Modeling Covariance Matrices in Terms of Standard Deviations and Correlations, With Application To Shrinkage,” Statistica Sinica, vol. 10, pp. 1281–1311, 2000.Google Scholar
  26. 26.
    M. Gupta, “Complexity Reduction for Near Real-time High Dimensional Filtering and Estimation Applied to Biological Signals,” Ph.D. dissertation, Harvard University, May 2016.Google Scholar
  27. 27.
    B. Settles, “Active Learning Literature Survey,”Machine Learning, vol. 15, no. 2, pp. 201–221, 2010. Google Scholar
  28. 28.
    Y. Freund, H. S. Seung, E. Shamir, and N. Tishby, “Selective Sampling Using the Query by Committee Algorithm,” Machine Learning, vol. 168, no. 1997, pp. 133–168, 1997. Google Scholar
  29. 29.
    S.-J. Huang, R. Jin, and Z.-H. Zhou, “Active Learning by Querying Informative and Representative Examples,” Advances in Neural Information Processing Systems 23, vol. 36, no. 10, pp. 892–900, 2010. Google Scholar
  30. 30.
    S. C. H. Hoi, R. Jin, J. Zhu, and M. R. Lyu, “Semi-supervised SVM batch mode active learning for image retrieval,” Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on , pp. 1–7, 2008.Google Scholar
  31. 31.
    B. Settles and M. Craven, “An analysis of active learning strategies for sequence labeling tasks,” Proceedings of the Conference on Empirical Methods in Natural Language Processing EMNLP 08, no. October, p. 1070, 2008.Google Scholar
  32. 32.
    A. Beygelzimer, S. Dasgupta, and J. Langford, “Importance Weighted Active Learning,” Proceedings of the 26th Annual International Conference on Machine Learning ICML 09, vol. abs/0812.4, no. ii, pp. 1–8, 2008.Google Scholar
  33. 33.
    Z.-H. Zhou, Ensemble Methods: Foundations and Algorithms, 2012.Google Scholar
  34. 34.
    M. Costa, A. L. Goldberger, and C.-K. Peng, “Multiscale entropy analysis of complex physiologic time series.” Physical review letters, vol. 89, no. 6, p. 068102, 2002. Google Scholar
  35. 35.
    B. Settles, Active Learning. plus Morgan and Claypool, 2012, no. 1.Google Scholar
  36. 36.
    D. Cai and X. He, “Manifold adaptive experimental design for text categorization,” IEEE Transactions on Knowledge and Data Engineering, vol. 24, no. 4, pp. 707–719, 2012. Google Scholar
  37. 37.
    R. Polikar, “Ensemble based systems in decision making,” Circuits and Systems Magazine, pp. 21–45, 2006.Google Scholar
  38. 38.
    S. Hanneke, “Rates of Convergence in Active Learning,” The Annals of Statistics, vol. 39, no. 1, pp. 333–361, 2011. Google Scholar
  39. 39.
    M. Kääriäinen, “Active Learning in the Non-realizable Case,” Alt, pp. 63–77, 2006.Google Scholar
  40. 40.
    T. Dietterich, “Ensemble Learning,” vol. 2007, no. April 2007, pp. 1–16, 2002.Google Scholar
  41. 41.
    C.M. Bishop, “Pattern Recognition and Machine Learning (Information Science and Statistics,” Springer-Verlag New York, Inc., 2006.Google Scholar
  42. 42.
    X. Zhu, A.B. Goldberg, R. Brachman and T. Dietterich,“ Introduction to Semi-Supervised Learning,” Morgan and Claypool Publishers, 2009. Google Scholar
  43. 43.
    K. Kaida, M. Takahashi, T. Akerstedt, A. Nataka, Y. Otsuka, T. Haratani, K. Fukasawa, “Validation of the Karolinska sleepiness scale against performance and EEG variables.” Clin. Neurophysiol., vol. 117, no. 7, p. 1574-81, 2006. Google Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.Division of Sleep and Circadian Disorders, Departments of Medicine and NeurologyHarvard Medical School and Brigham and Women’s HospitalBostonUSA

Personalised recommendations