Skip to main content
SpringerLink
Log in

Noise removal in electroencephalogram signals using an artificial neural network based on the simultaneous perturbation method

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Electroencephalogram (EEG) recordings often experience interference by different kinds of noise, including white, muscle and baseline, severely limiting its utility. Artificial neural networks (ANNs) are effective and powerful tools for removing interference from EEGs. Several methods have been developed, but ANNs appear to be the most effective for reducing muscle and baseline contamination, especially when the contamination is greater in amplitude than the brain signal. An ANN as a filter for EEG recordings is proposed in this paper, developing a novel framework for investigating and comparing the relative performance of an ANN incorporating real EEG recordings. This method is based on a growing ANN that optimized the number of nodes in the hidden layer and the coefficient matrices, which are optimized by the simultaneous perturbation method. The ANN improves the results obtained with the conventional EEG filtering techniques: wavelet, singular value decomposition, principal component analysis, adaptive filtering and independent components analysis. The system has been evaluated within a wide range of EEG signals. The present study introduces a new method of reducing all EEG interference signals in one step with low EEG distortion and high noise reduction.

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

Access this article

Log in via an institution

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  1. Sörnmo L, Laguna P (2005) Bioelectrical signal processing in cardiac an neurological applications. Elsevier Academic Press, Amsterdam

    Google Scholar 

  2. Bronzino J (2000) The biomedical engineering handbook, 2nd edn. CRC Press, Springer, Berlin

    Google Scholar 

  3. Rangayyan RM (2002) Biomedical signal analysis: a case-study approach. IEEE Press Series in Biomedical Engineering, New York

    Google Scholar 

  4. Shao SY, Shen KQ, Ong CJ, Wilder-Smith EPV, Li XP (2009) Automatic EEG artifact removal: a weighted support vector machine approach with error correction. IEEE Trans Biomed Eng 56(2):336–344

    Article  Google Scholar 

  5. Luo S, Johnston P (2010) A review of electrocardiogram filtering. J Electrocardiol 43(6):486–496

    Article  Google Scholar 

  6. Fatourechi M, Bashashati A, Ward RK, Birch GE (2007) EMG and EOG artifacts in brain computer interface systems: a survey. Clin Neurophysiol 118:480–494

    Article  Google Scholar 

  7. Nottage JF, Morrison PD, Williams SCR, Dfytche DH (2013) A novel method for reducing the effect of tonic muscle activity on the gamma band of the scalp eeg. Brain Topogr 26(1):50–61

    Article  Google Scholar 

  8. Aydin U, Dogrusoz YS (2011) A Kalman filter-based approach to reduce the effects of geometric errors and the measurement noise in the inverse ecg problem. Med Biol Eng Comput 49(9):1003–1013

    Article  Google Scholar 

  9. Vullings R, de Vries B, Bergmans J (2011) An adaptive Kalman filter for ECG signal enhancement. IEEE Trans Biomed Eng 58(4):1094–1103

    Article  Google Scholar 

  10. Sameni R, Shamsollahi MB, Jutten C (2008) Model-based Bayesian filtering of cardiac contaminants from biomedical recordings. Physiol Meas 29(5):595–613

    Article  Google Scholar 

  11. Sameni R, Shamsollahi MB, Jutten C, Clifford GD (2007) A nonlinear Bayesian filtering framework for ECG denoising. IEEE Trans Biomed Eng 54(12):2172–2185

    Article  MATH  Google Scholar 

  12. Paul JS, Reddy MR, Kumar VJ (2000) A transform domain SVD filter for suppression of muscle noise artefacts in exercise ECG’s. IEEE Trans Biomed Eng 47(5):654–663

    Article  Google Scholar 

  13. Willink TJ (2008) Efficient adaptive SVD algorithm for MIMO applications. IEEE Trans Signal Process 56(2):615–622

    Article  MathSciNet  Google Scholar 

  14. Liu Z, de Zwart JA, van Gelderen P, Kuo L-W, Duyn JH (2012) Statistical feature extraction for artifact removal from concurrent FMRI-EEG recordings. NeuroImage 59(3):2073–2087

    Article  Google Scholar 

  15. Wu Y, Rangayyan RM, Zhouc Y, Ngd SC (2009) Filtering electrocardiographic signals using an unbiased and normalized adaptive noise reduction system. Med Eng Phys 31(1):17–26

    Article  Google Scholar 

  16. Sansone M, Mirarchi L, Bracale M (2010) Adaptive removal of gradients-induced artefacts on ECG in MRI: a performance analysis of RLS filtering. Med Biol Eng Comput 48(5):475–482

    Article  Google Scholar 

  17. Boudet S, Peyrodie L, Forzy G, Pinti A, Toumi H, Gallois P (2012) Improvements of adaptive filtering by optimal projection to filter different artifact types on long duration EEG recordings. Comput Methods Progr Biomed 108(1):234–249

    Article  Google Scholar 

  18. Ahirwal MK, Kumar A, Singh GK (2013) EEG/ERP adaptive noise canceller design with controlled search space (CSS) approach in cuckoo and other optimization algorithms. IEEE/ACM Trans Comput Biol Bioinform 10(6):1491–1504

    Article  Google Scholar 

  19. Acir N (2013) Estimation of brainstem auditory evoked potentials using a nonlinear adaptive filtering algorithm. Neural Comput Appl 22(6):1201–1209

    Article  Google Scholar 

  20. Yang H, Bukkapatnam ST, Komanduri R (2007) Nonlinear adaptive wavelet analysis of electrocardiogram signals. Phys Rev 76(2):026214-1–026214-8

    Google Scholar 

  21. Sharma LN, Dandapat S, Mahanta A (2010) ECG signal denoising using higher order statistics in wavelet subbands. Biomed Signal Process Control 5(3):214–222

    Article  Google Scholar 

  22. Boubchir L, Boashash B (2013) Wavelet denoising based on the map estimation using the BKF prior with application to images and EEG signals. IEEE Trans Signal Process 61(8):1880–1894

    Article  MathSciNet  Google Scholar 

  23. Castillo E, Morales DP, Botella G, García A, Parrilla L, Palma AJ (2013) Efficient wavelet-based ECG processing for single-lead FHR extraction. Digital Signal Process 23(6):1897–1909

    Article  Google Scholar 

  24. Lagerlund TD, Sharbrough FW, Busacker NE (2004) Use of principal component analysis in the frequency domain for mapping electroencephalographic activities: Comparison with phase-encoded fourier spectral analysis. Brain Topogr 17(2):73–84

    Article  Google Scholar 

  25. Chawla MPS (2009) A comparative analysis of principal component and independent component techniques for electrocardiograms. Neural Comput Appl 18(6):539–556

    Article  MathSciNet  Google Scholar 

  26. ter Braack EM, de Jonge B, van Putten MJAM (2013) Reduction of TMS induced artifacts in EEG using principal component analysis. IEEE Trans Neural Syst Rehabil Eng 21(3):376–382

    Article  Google Scholar 

  27. Chawla MPS (2011) PCA and ICA processing methods for removal of artifacts and noise in electrocardiograms: a survey and comparison. Appl Soft Comput 11(2):2216–2226

    Article  Google Scholar 

  28. Lan-Da V, Di-You W, Chien-Shiun C (2011) Energy-efficient FastICA implementation for biomedical signal separation. IEEE Trans Neural Netw 22(11):1809–1822

    Article  Google Scholar 

  29. Gwin JT, Gramann K, Makeig S, Ferris DP (2010) Removal of movement artifact from high-density EEG recorded during walking and running. J Neurophysiol 103(6):3526–3534

    Article  Google Scholar 

  30. Akhtar MT, Mitsuhashi W, James CJ (2012) Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data. Signal Process 92(2):401–416

    Article  Google Scholar 

  31. Vázquez R Romo, Vélez-Pérez H, Ranta R, Dorr V Louis, Maquin D, Maillard L (2012) Blind source separation, wavelet denoising and discriminant analysis for EEG artefacts and noise cancelling. Biomed Signal Process Control 7(4):389–400

    Article  Google Scholar 

  32. Ma J, Tao P, Bayram S, Svetnik V (2012) Muscle artifacts in multichannel EEG: characteristics and reduction. Clin Neurophysiol 123(8):1676–1686

    Article  Google Scholar 

  33. Kachenoura A, Albera L, Senhadji L, Comon P (2008) ICA: a potential tool for BCI systems. IEEE Signal Process Mag 25(1):57–68

    Article  Google Scholar 

  34. Zarzoso V, Comon P (2010) Robust independent component analysis by iterative maximization of the kurtosis contrast with algebraic optimal step size. IEEE Trans Neural Netw 21(2):248–261

    Article  Google Scholar 

  35. Macnab CJB (2011) Neural-adaptive control using alternate weights. Neural Comput Appl 20(2):211–221

    Article  MathSciNet  Google Scholar 

  36. Campa G, Fravolini M-L, Mammarella M, Napolitano MR (2011) Bounding set calculation for neural network-based output feedback adaptive control systems. Neural Comput Appl 20(3):373–387

    Article  Google Scholar 

  37. Teixeira de Lima GR, Silva JDS, Saotome O (2010) Vehicle inductive signatures recognition using a Madaline neural network. Neural Comput Appl 19(3):421–436

    Article  Google Scholar 

  38. Yu-Quan Z, Ji-Shun O, Geng C, Hai-Ping Y (2011) Dynamic weighting ensemble classifiers based on cross-validation. Neural Comput Appl 20(3):309–317

    Article  Google Scholar 

  39. Mateo J, Torres AM, García MA (2014) Dynamic fuzzy neural network based learning algorithms for ocular artefact reduction in EEG recordings. Neural Process Lett 39(1):45–67

    Article  Google Scholar 

  40. Zhang L, He C (2012) Quantitative methods for detecting cerebral infarction from multiple channel EEG recordings. Neural Comput Appl 21(6):1159–1166

    Article  Google Scholar 

  41. Sokouti B, Haghipour S, Tabrizi A (2014) A framework for diagnosing cervical cancer disease based on feedforward MLP neural network and ThinPrep histopathological cell image features. Neural Comput Appl 24(1):221–232

    Article  Google Scholar 

  42. Cinar E, Sahin F (2013) New classification techniques for electroencephalogram (EEG) signals and a real-time EEG control of a robot. Neural Comput Appl 22(1):29–39

    Article  Google Scholar 

  43. Widrow B, Lehr MA (1990) 30 years of adaptive neural networks: perceptrons, madeline and backpropagation. Proc IEEE 78:1415–1442

    Article  Google Scholar 

  44. Graupe D (2007) Principles of artificial neural networks, 2nd edn. World Scientific, Singapore

    Book  MATH  Google Scholar 

  45. Kathirvalavakumar T (2010) Neural networks: FNN training algorithms: simultaneous perturbation, backpropagation and tunneling methods. VDM Verlag, Saarbrücken

    Google Scholar 

  46. Haykin S (2008) Neural networks and learning machines, 3rd edn. Prentice Hall, Englewood Cliffs, NJ

    Google Scholar 

  47. Spall JC, Criston JA (1994) Nonlinear adaptive control using neural networks: estimation with a smoothed form of simultaneous perturbation gradient approximation. Stat Sin 4:1–27

    MathSciNet  MATH  Google Scholar 

  48. Spall JC (2003) Introduction to stochastic search and optimization: estimation, simulation, and control. Wiley, New York

    Book  MATH  Google Scholar 

  49. Spall JC (2000) Adaptive stochastic approximation by the simultaneous perturbation method. IEEE Trans Autom Control 45(10):1839–1853

    Article  MathSciNet  MATH  Google Scholar 

  50. Maeda Y, Hirano H, Kanata Y (1995) A learning rule of neural networks via simultaneous perturbation and its hardware implementation. Neural Netw 8(2):251–259

    Article  Google Scholar 

  51. Maeda Y, De Figueiredo RJP (1997) Learning rules for neuro-controller via simultaneous perturbation. IEEE Trans Neural Netw 8(6):1119–1130

    Article  Google Scholar 

  52. Maeda Y, Wakamura M (2005) Simultaneous perturbation learning rule for recurrent neural networks and its FPGA implementation. IEEE Trans Neural Netw 16(6):1664–1672

    Article  Google Scholar 

  53. Haykin S (1999) Neural networks: a comprehensive approach, 2nd edn. Prentice-Hall, Upper Saddle River, NJ

    MATH  Google Scholar 

  54. Haykin S (1996) Neural networks expand SP’s horizons. IEEE Signal Process Mag 13(2):24–49

    Article  Google Scholar 

  55. Eom K, Kang S (2005) Learning method of the adaline using the fuzzy logic system. Neural Comput Appl 14(3):235–242

    Article  Google Scholar 

  56. Spall JC (2009) Feedback and weighting mechanisms for improving Jacobian estimates in the adaptive simultaneous perturbation algorithm. IEEE Trans Autom Control 54(6):1216–1229

    Article  MathSciNet  Google Scholar 

  57. Steenis R, Rivera DE (2011) Plant-friendly signal generation for system identification using a modified simultaneous perturbation stochastic approximation (SPSA) methodology. IEEE Trans Control Syst Technol 19(6):1604–1612

    Article  Google Scholar 

  58. Xu Z, Song Q, Wang D (2014) A robust recurrent simultaneous perturbation stochastic approximation training algorithm for recurrent neural networks. Neural Comput Appl 24(7–8):1851–1866

    Article  Google Scholar 

  59. Song Q, Spall JC, Soh YC, Ni J (2008) Robust neural network tracking controller using simultaneous perturbation stochastic approximation. IEEE Trans Neural Netw 19(5):817–835

    Article  Google Scholar 

  60. Hong YY, Christian CY, Chiu CS (2008) Passive filter planning using simultaneous perturbation stochastic approximation. IEEE Trans Power Deliv 25(2):939–946

    Article  Google Scholar 

  61. Halunga SV, Vizireanu DN (2010) Performance evaluation for conventional and MMSE multiuser detection algorithms in imperfect reception conditions. Digital Signal Process 20(1):166–178

    Article  Google Scholar 

  62. Halunga SV, Vizireanu DN, Fratu O (2010) Imperfect cross-correlation and amplitude balance effects on conventional multiuser decoder with turbo encoding. Digital Signal Process 20(1):191–200

    Article  Google Scholar 

  63. Rahman M Zia Ur, Shaik R Ahamed, Rama Koti Reddy DV (2012) Efficient and simplified adaptive noise cancelers for ECG sensor based remote health monitoring. IEEE Sensors J 12(3):566–573

    Article  Google Scholar 

  64. Pascual-Marqui RD, Esslen M, Kochi K, Lehmann D (2002) Functional imaging with low resolution brain electromagnetic tomography (LORETA): a review. Methods Find Exp Clin Pharmacol 24C:91–95

    Google Scholar 

Download references

Acknowledgments

This work was sponsored by University of Castilla-La Mancha, the Project PI10/01215 from Instituto de Salud Carlos III and Virgen de la Luz Hospital of Cuenca (Spain).

Author information

Authors and Affiliations

  1. Innovation in Bioengineering Research Group, University of Castilla-La Mancha, Cuenca, Spain

    J. Mateo & A. M. Torres

  2. Department of Neurophysiology, Hospital Virgen de la Luz, Cuenca, Spain

    M. A. García

  3. Department of Psychiatry, Hospital Virgen de la Luz, Cuenca, Spain

    J. L. Santos

Authors
  1. J. Mateo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. M. Torres
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. A. García
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. J. L. Santos
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to J. Mateo.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mateo, J., Torres, A.M., García, M.A. et al. Noise removal in electroencephalogram signals using an artificial neural network based on the simultaneous perturbation method. Neural Comput & Applic 27, 1941–1957 (2016). https://doi.org/10.1007/s00521-015-1988-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-015-1988-7

Keywords

Search

Navigation