Journal of Scientific and Industrial Research

Open Access Open Access  Restricted Access Subscription Access

Combining CEEMDAN with PCA for Effective Cardiac Artefact Suppression from Single-Channel EEG


Affiliations
1 SDTD, Materials Science Group, Indira Gandhi Centre for Atomic Research, HBNI, Kalpakkam 603 102, India
 

The large signal due to cardiac activity can easily distort the signals originating from the relatively weak electrical activity of the brain, commonly measured as an Electroencephalogram (EEG). The artifact due to cardiac activity in EEG is called cardiac artifact, which contaminates the EEG data and makes interpretation of the EEG difficult for clinicians. Hence it is crucial to remove the cardiac artifact from EEG data. To suppress the cardiac artifact, we propose a novel approach to effectively extract cardiac artifacts from single-channel contaminated EEG data without using reference Electrocardiogram (EKG) data. The proposed methodology uses Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to decompose EEG data contaminated by cardiac activity into the Intrinsic Mode Functions (IMFs). Principal Component Analysis (PCA) is performed on these IMFs to obtain the principal components arranged in the order of decreasing variance. Effective cardiac artifact extraction is achieved by optimizing the signal reconstruction process so that only those principal components that capture the cardiac activity are retained with the constraint that distortion introduced in EEG data should be minimum. The comparison clearly shows that the proposed method outperforms conventionally employed methods like wavelet-based approach.

Keywords

CEEMDAN, ECG, EEG, PCA, Wavelet.
User
Notifications
Font Size

  • Mannan M N, Kamran M A & Jeong M Y, Identification and removal of physiological artifacts from electroencephalogram signals: A review, IEEE Access, 6 (2018) 30630–30652.

  • Klados M A, Papadelis Christos, Braun Christoph & Bamidis P D, REG-ICA: A hybrid methodology combining blind source separation and regression techniques for the rejection of ocular artifacts, Biomed Signal Process Control, 6(3) (2011) 291–300.

  • Selvan S & Srinivasan R, Recurrent neural network based efficient adaptive filtering technique for the removal of ocular artefacts from EEG, IETE Tech Rev, 17 (2000) 73–78.

  • Kandaswamy A, Krishnaveni V, Jayaraman S, Malmurugan N & K Ramadoss, Removal of ocular artifacts from EEG-a survey, IETE J Res, 51(2) (2005)121–130.

  • Romero S, Mananas M A & Barbanoj M J, Ocular reduction in EEG signals based on adaptive filtering, regression and blind source separation, Ann Biomed Eng, 37(1) (2009) 176–191.

  • Muhammad Tahir Akhtar, Wataru Mitsuhashi & Christopher J James, Employing spatially constrained ICA and wavelet denoising, for automatic removal of artifacts from multichannel EEG data, Signal Processing, 92(2) (2012) 401–416.

  • Bono V, Das S, Jamal W & Maharatna K, Hybrid wavelet and EMD/ICA approach for artifact suppression in pervasive EEG, J Neurosci Methods, 267 (2016) 89–107.

  • Patel R, Sengottuvel S, Gireesan K, Janawadkar M P, Radhakrishnan T S & Mariyappa N, Ocular artifact suppression from EEG using ensemble empirical mode decomposition with principal component analysis, Comput Electr Eng, 54 (2016) 78–86.

  • Hamaneh M B, Chitravas N, Kaiboriboon K, Lhatoo S D & Loparo K A, Automated removal of EKG artifact from EEG data using independent component analysis and continuous wavelet transformation, IEEE Trans Biomed Eng, 61(6) (2016) 1634–1641.

  • Patel R, Gireesan K, Sengottuvel S, Janawadkar M P & Radhakrishnan T S, Common methodology for cardiac and ocular artifact suppression from EEG recordings by combining ensemble empirical mode decomposition with regression approach, J Med Biol Eng, 37(2) (2017) 201–208.

  • Dora C & Biswal P K, Correlation-based ECG artifact correction from single channel EEG using modified variational mode decomposition, Comput Methods Programs Biomed, 183 (2020) 105092,

  • Wu Z & Huang N E, Ensemble empirical mode decomposition: A noise-assisted data analysis method, AADA, 01(01) (2009) 1–41.

  • Bouny L El, Khalil M & Abdellah A, ECG signal filtering based on CEEMDAN with hybrid interval thresholding and higher order statistics to select relevant modes, Multimed Tools Appl, 78(10) (2019) 13067–13089.

  • Jun W, Yuyan L, Lingyu T & Ge P, A new weighted CEEMDAN-based prediction model: An experimental investigation of decomposition and non-decomposition approaches, Knowl Based Systems, 160 (2018) 188–199.

  • Escudero Javier, Hornero Roberto, Abasolo Daniel, Fernandez Alberto & Lopez Coronado Miguel, Artifact removal in magneto encephalogram background activity with independent component analysis, IEEE Trans Biomed Eng, 54(11) (2007) 1965–1973.

  • Books C. Orphanidou, Quality assessment for the electrocardiogram (ECG), Signal Quality Assessment in Physiological Monitoring, 1 (2018) 15–40.

  • Perez F & Granger B E, Ipython: A system for interactive scientific computing, Comput Sci Eng, 9(3) (2007) 21–29.

  • Luukko P J J, Helske J & Rasanen E, Introducing libeemd: a program package for performing the ensemble empirical mode decomposition, Comput Stat, 31(2) (2016) 545–557.

  • Chouakri S A, Bereksi Reguig F, Ahmaidi S & Fokapu O, Wavelet denoising of the electrocardiogram signal based on the corrupted noise estimation, Comput Cardiol 4(8) (2005) 1021–1024.


Abstract Views: 69

PDF Views: 52




  • Combining CEEMDAN with PCA for Effective Cardiac Artefact Suppression from Single-Channel EEG

Abstract Views: 69  |  PDF Views: 52

Authors

Rajesh Patel
SDTD, Materials Science Group, Indira Gandhi Centre for Atomic Research, HBNI, Kalpakkam 603 102, India
K Gireesan
SDTD, Materials Science Group, Indira Gandhi Centre for Atomic Research, HBNI, Kalpakkam 603 102, India
R Baskaran
SDTD, Materials Science Group, Indira Gandhi Centre for Atomic Research, HBNI, Kalpakkam 603 102, India

Abstract


The large signal due to cardiac activity can easily distort the signals originating from the relatively weak electrical activity of the brain, commonly measured as an Electroencephalogram (EEG). The artifact due to cardiac activity in EEG is called cardiac artifact, which contaminates the EEG data and makes interpretation of the EEG difficult for clinicians. Hence it is crucial to remove the cardiac artifact from EEG data. To suppress the cardiac artifact, we propose a novel approach to effectively extract cardiac artifacts from single-channel contaminated EEG data without using reference Electrocardiogram (EKG) data. The proposed methodology uses Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) to decompose EEG data contaminated by cardiac activity into the Intrinsic Mode Functions (IMFs). Principal Component Analysis (PCA) is performed on these IMFs to obtain the principal components arranged in the order of decreasing variance. Effective cardiac artifact extraction is achieved by optimizing the signal reconstruction process so that only those principal components that capture the cardiac activity are retained with the constraint that distortion introduced in EEG data should be minimum. The comparison clearly shows that the proposed method outperforms conventionally employed methods like wavelet-based approach.

Keywords


CEEMDAN, ECG, EEG, PCA, Wavelet.

References