a r t i c l e i n f o a b s t r a c t
Article history: Electrocardiogram (ECG) is a widely used non-invasive method to study the rhythmic activity of the
Received 24 July 2015 heart. These signals, however, are often obscured by artifacts/noises from various sources and mini-
Received in revised form mization of these artifacts is of paramount importance for detecting anomalies. This paper presents a
19 November 2015
thorough analysis of the performance of two hybrid signal processing schemes ((i) Ensemble Empirical
Accepted 30 November 2015
Mode Decomposition (EEMD) based method in conjunction with the Block Least Mean Square (BLMS)
Available online 22 December 2015
adaptive algorithm (EEMD-BLMS), and (ii) Discrete Wavelet Transform (DWT) combined with the Neu-
ral Network (NN), named the Wavelet NN (WNN)) for denoising the ECG signals. These methods are
Keywords:
Electrocardiogram (ECG)
compared to the conventional EMD (C-EMD), C-EEMD, EEMD-LMS as well as the DWT thresholding
Denoising (DWT-Th) based methods through extensive simulation studies on real as well as noise corrupted ECG
Ensemble empirical mode decomposition signals. Results clearly show the superiority of the proposed methods.
(EEMD) 2015 Elsevier Ltd. All rights reserved.
Block least mean square (BLMS)
Discrete Wavelet Transform (DWT)
Neural Networks (NN)
http://dx.doi.org/10.1016/j.bspc.2015.11.012
1746-8094/ 2015 Elsevier Ltd. All rights reserved.
K. Krgaard et al. / Biomedical Signal Processing and Control 25 (2016) 178187 179
xv (n) = x(n) + wv (n), (4) where i s are the eigenvalues of the input covariance matrix. If the
lter length P is chosen to be equal to L, the update rule can be
where controls the amplitude of the added white noise. An aver-
written as,
age of these 3001000 sets of IMFs of xv (n)s produce the nal
IMFs. In both the C-EMD and C-EEMD approaches, the denoised
L1
ECG signals are obtained by subtracting the IMFs corresponding to wk (m + 1) = wk (m) + blms
k
uk (mL + i)ek (mL + i). (9)
the noise components from the observed ECG signals [2931]. i=0
180 K. Krgaard et al. / Biomedical Signal Processing and Control 25 (2016) 178187
Tj = Qj Cj , j = 0, 1, . . ., 11, (16)
where Cj is the power of the detail coefcient at the jth scale level.
The threshold is then applied to all ECG signals as per Eq. (15) and
subsequently the inverse DWT (IDWT) is performed to reconstruct
the denoised ECG signal [42].
In the WNN approach, wavelet decomposition is performed on
x(n), and the resulting coefcients (detail and approximation) are
fed to the NN for the estimation of d(n). The signal x(n), n = 0, 1,
. . ., N 1, of length N samples is rst zero padded (256 zeros in
the beginning and in the end) to generate a new signal (x (n))
of length N + 512. To mitigate the varying effect of zero-padding,
Fig. 2. Flowchart of the EEMD-BLMS algorithm. a sliding window approach for extracting wavelet coefcients is
adopted. From x (n), using a sliding window (with an overlap of
The conventional LMS lter can be seen as a special case of the 512 samples), N smaller data segments of length 513 samples are
BLMS lter with a block length L = 1. Hence, the block index m can extracted. Each of these smaller segments are subjected to DWT
be replaced by the sample index n and thereby the update rule for which results in 513 sets of 14 wavelet coefcients (13 detail
the kth LMS lter is given by Eq. (10): (W ) and 1 approximation(W )) which are arranged in a matrix
of dimension 14 513. From these wavelet coefcients matrices,
wk (n + 1) = wk (n) + lms uk (n)ek (n). (10)
k the 14 coefcients corresponding to specic smaller data seg-
The step-size lms for the LMS lters are chosen as, ments (for example, x(n)) is extracted as the 257th column of the
k
respective matrices. The corresponding input vector xDWT (n) (of
2 length 154 = 14 11) to the NN is obtained by concatenating 11
0 < lms
k
, (11)
max columns (252:262) of the respective wavelet coefcient matrix.
where max is the maximum eigenvalue of the input covariance The incorporation of wavelet coefcients of the ten neighbor-
matrix. A owchart of the EEMD-BLMS algorithm can be seen in ing samples of x(n) into xDWT (n) provides the NN with temporal
Fig. 2. information and thereby improves its performance. A multilayer
perceptron (MLP(154:38:38:1)), trained using the Bayesian regu-
2.3. DWT-Th and WNN larization backpropagation (BRBP) algorithm, is used in this study
[52,53]. A owchart describing the steps in the DWT-NN algorithm
DWT is used to obtain the frequency information over time for can be seen in Fig. 3.
the given signal x(n). It has the inherent property of increasing the
temporal resolution for high frequencies, and increasing frequency 3. Results and discussion
resolution for low frequencies making it a suitable tool for analyzing
biological signals. Given x(n), its DWT can be derived as follows: The proposed methods are tested on simulated (noise cor-
Let = [ (0), (1), . . ., (N 1)]T and = [(0), (1), . . ., rupted ECG) as well as on real ECG signals and the performances
(N 1)] be two orthogonal basis functions and let j0 = 0, N = 2j ,
T
are compared quantitatively by the signal-to-noise ratio (SNR)
j = 0, 1, . . ., J 1 and q = 0, 1, . . ., 2j 1. Here, j represents different improvement.
scale levels, and q represents the translation in each scale level. The N1
Fig. 4. Power spectrum of desired (blue) and 0dB (red) Type-I ECG. (For interpreta-
tion of the references to color in this gure legend, the reader is referred to the web
version of this article.)
Table 2
Comparison of output SNRs on Type-II signals.
C-EMD
10 11.56 10.66 11.84 11.39 -11.93 11.48
5 6.54 5.70 5.70 5.25 6.74 5.99
0 1.08 1.52 1.64 1.14 0.72 1.22
5 2.28 2.14 0.98 1.11 2.62 1.83
10 3.83 4.62 3.31 4.86 5.37 4.40
C-EEMD
10 0.05 0.37 0.06 0.42 0.035 0.17
5 4.56 2.57 2.57 3.08 3.86 3.33
0 6.52 6.25 6.17 4.77 3.36 5.41
5 8.86 8.64 8.47 7.33 7.25 8.11
10 10.01 9.30 9.82 8.03 10.44 9.52 Fig. 7. SNR values for various lter lengths of the low frequency (blue) and high
frequency lter (red). (For interpretation of the references to color in this gure
Note: Bold values indicate the average output SNRs. legend, the reader is referred to the web version of this article.)
Table 3
Comparison of output SNRs on Type-I signals.
EEMD-LMS
10 17.64 18.71 16.55 18.25 20.81 18.39
5 19.00 21.79 20.98 21.72 20.69 20.84
0 19.88 23.21 21.77 23.06 22.50 22.08
5 20.53 22.63 22.24 21.87 22.03 21.86
10 20.42 21.78 19.68 20.65 25.12 21.53
EEMD-BLMS
10 17.76 18.75 16.59 18.29 20.85 18.45
5 19.07 21.76 21.04 21.85 20.83 20.91
Fig. 6. Time plots of the original and denoised Type-I 0dB signal (ECG1) using C- 0 20.00 23.27 21.85 23.18 22.56 22.17
EMD and C-EEMD. (a) Desired (red) and noisy signal (blue); (b) Desired (red) and 5 20.51 22.71 22.30 21.95 22.10 21.91
results obtained from C-EEMD (green) and C-EMD (black). (For interpretation of the 10 20.48 21.88 19.85 20.89 25.45 21.71
references to color in this gure legend, the reader is referred to the web version of
this article.) Note: Bold values indicate the average output SNRs.
K. Krgaard et al. / Biomedical Signal Processing and Control 25 (2016) 178187 183
Table 4
Comparison of output SNRs on Type-II signals.
EEMD-LMS
10 4.55 4.05 3.91 3.25 5.74 4.30
5 5.65 3.63 3.42 3.59 6.46 4.55
0 5.73 4.97 4.21 4.19 6.60 5.14
5 6.31 6.39 6.48 5.13 6.73 6.21
10 6.85 6.68 6.51 5.59 7.23 6.57
EEMD-BLMS
10 4.72 4.27 4.04 3.48 6.34 4.57
5 5.71 3.76 3.61 3.77 6.61 4.69 Fig. 9. Learning curves of the LMS (black) and BLMS (red) adaptive lters. (For inter-
0 5.87 5.03 4.29 4.20 6.68 5.21 pretation of the references to color in this gure legend, the reader is referred to the
5 6.49 6.51 6.70 5.21 6.81 6.34 web version of this article.)
10 7.08 6.88 6.84 5.66 7.45 6.78
Note: Bold values indicate the average output SNRs. Monte-Carlo simulations. The analysis is performed on a 0dB Type-
I signal (ECG1) with lter lengths 10 and 100. The corresponding
it is interesting to note that there is only a marginal difference step sizes are, for LMS: 5 104 lms 4 lms
max and 8.5 10 max , respec-
between the LMS and BLMS based schemes, as the average output tively and for BLMS, they are 5 103 blms
max and 8.5 103 blms
max ,
blms lms
respectively. Here, max and max are found from Eqs. (8) and (11),
SNR values and hence the SNR improvements (11.5328.39 dB for
LMS based scheme and 11.7128.45 dB for the BLMS based scheme) respectively. Both schemes can be seen to converge more or less
for all the cases are more or less even, though the BLMS based identically although the LMS based scheme converges a little faster.
scheme performs slightly better. For Type-II signals (Table 4), both Both schemes reach an MSE value <0.001 in about 2000 samples.
methods struggle to improve SNR values when the input SNR is The MSE values for the BLMS scheme are slightly lower compared
above 5 dB. The LMS still performs more or less similar to BLMS, to the LMS scheme (see the zoom in Fig. 9) explaining why the BLMS
however the BLMS (SNR improvement: 3.22 to 14.57dB) performs based scheme works slightly better than the LMS based scheme in
slightly better than the LMS scheme (SNR improvement: 3.43 to denoising the ECG signals.
14.30dB). The poor performance of these methods at high input
SNRs may again be attributed to the fact that the 7 Hz noise ref- 3.2.3. DWT-Th and WNN
erence contain some real ECG information (Fig. 5). A comparison Here, the denoising performances of the DWT-Th and WNN
of the LMS and BLMS based schemes to the C-EMD and C-EEMD methods on simulated noise are compared. Both these methods are
schemes clearly show that the hybrid methods are signicantly set up as per the discussions in Section 2.3. In the WNN method,
better, be it for Type-I or Type-II signals. Paired t-test with a 5% the NN is trained on ECG6-ECG10 and tested on ECG1-ECG5
signicance level indicate a different performance for both meth- (details provided in Section 3.1). For the DWT-Th, the thresholds
ods on all SNR levels and signal types, except Type-I with 5dB SNR. described in Eq. (16) are obtained from the 0dB Type-I ECG1 signal.
Here the p-value (0.07) is just above the signicance level, support- These parameters are used for the rest of the simulation studies in
ing the statement that the two methods have different performance this section.
groups. In Tables 5 and 6, the output SNR values are listed for both
The time plots of the denoised ECG signals from the EEMD-LMS the DWT-Th and WNN methods when running the simulations on
and EEMD-BLMS ltering methods on 0 dB Type-I signal for ECG1 Type-I and Type-II signals for 5 different input SNR values. It can
is shown in Fig. 8. The initial transients before convergence can be be seen that for both types of noise, the WNN method provides
clearly seen in the gure due to the adaptive algorithms. Both meth- signicantly better performance (average SNR improvement for
ods give good estimates of the desired ECG signal (this is reected Type-I: 8.6624.69 dB and for Type-II: 3.4719.65 dB) compared
in the output SNRs as well: 19.88 dB (LMS) and 20.00 dB (BLMS)). to the DWT-Th method (Type-I: 4.2114.05 dB and for Type-II:
Analysis of the convergence of the algorithms is important when 2.204.70 dB). It is interesting to note that these methods unlike
we deal with adaptive algorithms. Fig. 9 shows the learning curves the other methods (C-EMD, C-EEMD, EEMD-LMS and EEMD-BLMS),
(samples versus the mean square error (MSE) curve) for both the do not produce a negative SNR improvement (average). Another
LMS and BLMS based schemes obtained as the average of 300 observation is that though the performance of these methods (on
Table 5
Comparison of output SNRs on Type-I signals.
DWT-Th
10 4.40 3.96 3.37 3.83 4.71 4.05
5 8.01 7.07 8.17 6.78 9.33 7.87
0 11.52 10.15 11.85 9.45 13.63 11.32
5 13.80 12.27 14.28 11.08 15.86 13.46
10 14.69 13.33 15.21 11.77 16.11 14.21
WNN
10 11.32 19.41 11.24 16.34 15.13 14.69
5 12.22 19.58 12.11 17.60 17.38 15.78
Fig. 8. Time plots of the original and denoised Type-I 0dB signal (ECG1) using EEMD- 0 15.60 23.71 17.04 20.46 18.35 19.03
LMS and EEMD-BLMS. (a) Desired (red) and noisy signal (blue); (b) Desired (red), 5 15.73 23.03 17.11 20.21 18.03 18.82
results obtained from EEMD-BLMS ltering (black) and EEMD-LMS ltering (green). 10 16.00 22.56 17.39 19.36 17.98 18.66
(For interpretation of the references to color in this gure legend, the reader is
referred to the web version of this article.) Note: Bold values indicate the average output SNRs.
184 K. Krgaard et al. / Biomedical Signal Processing and Control 25 (2016) 178187
Table 6
Comparison of output SNRs on Type-II signals.
DWT-Th
10 5.08 5.26 5.13 5.57 5.42 5.30
5 0.15 0.40 0.28 0.79 0.41 0.40
0 4.69 4.26 4.53 3.74 4.38 4.32
5 8.89 8.52 8.87 7.51 9.15 8.59
10 12.88 11.86 12.74 10.30 13.21 12.20
WNN
10 9.17 11.12 8.26 12.49 7.19 9.65
5 9.92 12.54 9.93 11.14 8.76 10.46 Fig. 11. Training curve for 0dB type I signals.
0 11.15 13.29 11.19 12.68 10.11 11.68
5 12.25 13.84 12.94 12.76 10.60 12.48 of the proposed denoising schemes, they have been extended to
10 13.28 14.14 13.54 13.46 12.93 13.47 ve sets of real, noise contaminated ECG signals (ECG1 to ECG5),
Note: Bold values indicate the average output SNRs. which are downloaded from the MIT/BIH ECG-ID database [54].
The database also contains the desired (noise minimized) ECG sig-
Type-I signals) is signicantly lower than the LMS and BLMS based nals which we use to compare the performance of the proposed
schemes (Table 3), they are are much better than the C-EMD and algorithms for denoising the signals.
C-EEMD based methods. Paired t-test with a 5% signicance level The parameter settings for different methods used for the sim-
also indicate a different performance for these methods except for ulation studies have been used in the real data analysis as well.
10 dB Type-I and Type-II with p-values of 0.055 and 0.11, respec- Since the desired ECG signals corresponding to ECG1 to ECG5 are
tively. This can be seen from Tables 5 and 6 where the difference in available, the output SNR values for the denoised signals using the
mean performance becomes less compared to variation within the proposed methods are calculated (using Eq. (17)) and tabulated in
10 dB signals. Table 7. Since we observe a degradation in performance when using
The time plots for the denoised ECG signals corresponding to IMFs inside the bandwidth of the ECG signals in the simulation stud-
the DWT-Th and WNN methods when run on 0 dB Type-I signal ies, only IMFs outside the ECG bandwidth are considered for the
(ECG1) are shown in Fig. 10. Both methods provide good denois- EMD and EEMD based methods.
ing performances however the DWTTh is shown to cause minor From Table 7, it can be seen that the C-EEMD is once again
issues at the QRS complexes. The WNN method on the other hand, shown to perform signicantly better than the C-EMD method
is shown to retain some low-frequency component in the denoised for all ECG signals considered. The use of adaptive lters (LMS
ECG signal. and BLMS) further improves the performance signicantly. Surpris-
It is important to study the learning efciency (training curve) ingly, the EEMD-LMS based method provides an SNR improvement
of the MLP network. For this, the MLP is trained on 5 ECG data sets of 1.05 dB more than EEMD-BLMS. When it comes to the wavelet
(ECG6-ECG10) of 5000 samples. For each sample (x(n)), the 154 based methods, the WNN method is once again shown to be supe-
DWT coefcients are determined and used as the inputs to the MLP. rior to the DWT-Th and is comparable to both the LMS and BLMS
The corresponding desired signals (d(n)s) are used as the target. based methods. However, the DWT-Th performs the worst among
This huge set of (5 5000) input-target pairs form one epoch. The all the methods with an output (average) SNR of 1.61 dB.
MLP is trained up to 10 epochs, the mean square error (MSE) is The time plots and the corresponding noise spectra for all six
determined and the learning curve is plotted in Fig. 11. It can be proposed approaches in denoising ECG5 are discussed in detail
observed that the MSE decreased with an increase in the number here. As can be seen from Table 7, the inherent SNR of real ECG5
of epochs, until achieving the lowest value at about 7 epochs and is estimated to be 16.01 dB. The noisy ECG signal (green) and the
remained more or less unchanged with further training. corresponding desired signal (orange) are shown in Fig. 12(a). It is
clear that the real ECG5 has a signicant amount of low frequency
3.3. Results on real data as well as high frequency noise components. Subtracting the
desired signal from the original signal provides the noise that
After the extensive studies on ECG signals contaminated with is present in the real signal and the corresponding noise power
simulated noises (Type-I and Type-II) to assess the performance spectrum (black) is plotted in Fig. 12(c) along with the noise
power spectrum after EMD subtraction (red). Here, the presence
of low frequency noise is still evident in the signal after the C-EMD
processing. This can be attributed to mode mixing in the IMFs
containing the lowest frequencies.
For all EEMD based methods, the same IMFs are identied as
noise components. This is done to alleviate the inherent problem
Table 7
Input and output SNRs for the real ECG data.
Fig. 14. Time plots of the desired and denoised ECG5, as well as the power spectrum
of the original and residual noise. (a) Desired (orange) and ECG5 obtained through
EEMD-LMS (blue); (b) noise frequencies before (black) and after EEMD-LMS (red).
(For interpretation of the references to color in this gure legend, the reader is
referred to the web version of this article.)
Fig. 12. Time plots of the original (noisy), desired and denoised ECG5, as well as the the rst 4 s of the noise data have been excluded. Fig. 14(b)
power spectrum of the original and residual noise. (a) Desired (orange) and original however, reveals the presence of a very small amount of low
signal (green);(b) desired (orange) result obtained through C-EMD (blue); (c) noise frequencies, which can be neglected. The output SNR performance
spectrum before (black) and after C-EMD (red). (For interpretation of the references
(29.92 dB improvement (Table 7)) of this method is superior to all
to color in this gure legend, the reader is referred to the web version of this article.)
other methods.
Fig. 15 illustrates the corresponding plots of the denoised ECG
in EEMD where the same number of IMFs is not produced for dif- with the EEMD-BLMS approach. Like in the LMS approach, the
ferent trials. In Fig. 13, results from the C-EEMD denoising on ECG5 BLMS scheme also needs about 4 s to converge to the optimum
is shown. Here, EEMD produced 12 IMFs and from these, IMFs 1 lter coefcients. As can be seen in Fig. 15(a), the denoised ECG
and 2 have been identied as the power-line reference, and the is able to follow the desired ECG quite closely after 4 s. The noise
three lowest IMFs (10, 11, and 12) are identied for the baseline ref- power spectra shown in Fig. 15(b) also shows a more or less simi-
erence. The corresponding noise power spectra have been shown lar performance, as with the EEMD-LMS approach. The output SNR
in Fig. 13(b); the red curve here shows the residual noise power performance is very impressive here, although slightly inferior to
spectrum. In Fig. 13(a), the denoised ECG signal (blue) still contains the EEMD-LMS approach. This shows the superiority of these meth-
some high frequency components even after ltering. This is visi- ods in minimizing noise components from the ECG signal. Although
ble in the residual noise power spectrum (Fig. 13(b)) where a peak according to the convergence analysis (Fig. 9), the BLMS method is
at 50 Hz is seen. In this case, the 50 Hz noise appeared between supposed to provide a better performance compared to the LMS,
the lter banks of the rst and second IMF, dividing the noise the SNR values (Table 7) show little inferior performance here in
power between them. However, including the second IMF in the the real data case. This discrepancy of the BLMS method in the sim-
high frequency noise component would result in subtraction of ulated and the real data case could be caused by the addition of
ECG components and thereby further attenuation of the desired white noise, which the BLMS struggles to remove. This is in line with
ECG signal. [17] which reports that BLMS lters are not optimal for minimiz-
Results from the EEMD-LMS method when applied to ECG5 are ing the white noise. Fig. 15(b) shows a power spectrum similar to
shown in Fig. 14. The desired signal (orange) and the corresponding the one obtained from EEMD-LMS. Here one can see that the back-
denoised signal (blue) are shown in Fig. 14(a). It can be clearly seen ground noise level is slightly higher than in the LMS case (Fig. 14),
that after about 4 s, the denoised ECG signal closely follows the supporting its little inferior performance.
desired ECG signal, showing the effectiveness of the EEMD-LMS Time and power spectrum plots of the signal using the DWT-Th
method in denoising. The initial transients can be attributed to the method are shown in Fig. 16. As can be seen from the time-plots, the
convergence time of the adaptive algorithm, which is about 4 s, denoised ECG signal (blue) still contains a large amount of baseline
according to the learning curve shown in Fig. 9. Accordingly, in the wander (in the range of 0.10.3 Hz), which can be seen in the noise
noise power spectrum estimates as well as the SNR calculations, power spectrum as well (Fig. 16(b)). Fig. 16(b) also shows some
Fig. 13. Time plots of the desired and denoised ECG5, as well as the power spectrum Fig. 15. Time plots of the desired and denoised ECG5, as well as the power spectrum
of the original and residual noise. (a) Desired (orange) and ECG5 obtained through of the original and residual noise. (a) Desired (orange) and ECG5 obtained through
C-EEMD (blue); (b) noise frequencies before (black) and after C-EEMD (red). (For EEMD-BLMS (blue); (b) noise frequencies before (black) and after EEMD-BLMS (red).
interpretation of the references to color in this gure legend, the reader is referred (For interpretation of the references to color in this gure legend, the reader is
to the web version of this article.) referred to the web version of this article.)
186 K. Krgaard et al. / Biomedical Signal Processing and Control 25 (2016) 178187
estimating the noises present in the ECG but inferior to the hybrid
schemes in terms of denoising the ECG signals.
References
[1] J.A. Van Alste, T.S. Schilder, Removal of base-line wander and power line inter-
ference from the ECG by an efcient FIR lter with a reduced number of
taps, in: Proceedings of the 2nd International Conference on vol. 32, 1985, pp.
10521060.
[2] T. Slonim, M.A. Slonim, E. Ovsyscher, The use of simple FIR lters for ltering
of ECG signals and a new method for post-lter signal reconstruction, in: Pro-
ceedings of Computers in Cardiology Conference, London, 1993, pp. 871873.
[3] M.S. Chavan, R.A. Agarwala, M.D. Uplane, Suppression of baseline wander and
power line interference in ECG using digital IIR lter, Int. J. Circuit Syst. Signal
Fig. 16. Time plots of the desired and denoised ECG5, as well as the power spectrum
Process. 2 (2) (2008) 132142.
of the original and residual noise. (a) Desired (orange) and ECG5 obtained through
[4] S. Cuomo, G. De Pietro, R. Farina, A. Galletti, G. Sannino, A novel O(n) numerical
DWT-Th (blue); (b) noise frequencies before (black) and after DWT-Th (red). (For scheme for ECG signal denoising, Proc. Comput. Sci. 51 (2015) 775784.
interpretation of the references to color in this gure legend, the reader is referred [5] V. Alfonso, W. Thomkins, T. Nguyen, S. Trautmann, S. Luo, Filter bank-based
to the web version of this article.) processing of the stress ECG, in: Proceedings of the 17th IEEE Engineering in
Medicine and Biology Society Conference vol. 2, 1995, pp. 887888.
[6] S. Hargittai, Savitzky-Golay least-squares polynomial lters in ECG signal
processing, in: Proceedings of the Computers in Cardiology, Lyon, 2005, pp.
763766.
[7] K.M. Chang, S.H. Liu, Gaussian noise ltering from ECG by wiener lter
and ensemble empirical mode decompostion, J. Siganl Proc. Syst. 64 (2011)
249264.
[8] N.V. Thakor, Y.-S. Zhu, Applications of adaptive ltering to ECG analysis: noise
cancellation and arrhythmia detection, IEEE Trans. Biomed. Eng. 38 (8) (1991
Aug) 785794.
[9] J. Jenitta, A. Rajeswari Dr., Denoising of ECG signal based on improved adaptive
lter with EMD and EEMD, in: Conference on Information and Communication
Technology, 2013, pp. 957962.
[10] G.M.S. Sajjad, H. Rahman, A.K. Dey, A.M. Biswas, Z. Islam, A.K.M.J. Hoque, Per-
formance comparison of modied LMS and RLS algorithms in denoising of ECG
signals, Int. J. Eng. Technol. 2 (3) (2012) 466468.
[11] C. Chandrakar, M.K. Kowar, Denoising ECG signals using adaptive lter algo-
rithm, Int. J. Soft Comput. Eng. 2 (1) (2012) 120123.
Fig. 17. Time plots of the desired and denoised ECG5, as well as the power spectrum [12] M. Rahman, R. Shaik, D. Reddy, Adaptive noise removal in the ECG using the
of the original and residual noise. (a) Desired (orange) and ECG5 obtained through Block LMS algorithm, in: Proceedings of the 2nd International Conference on
WNN (blue); (b) noise frequencies before (black) and after WNN (red). (For inter- Adaptive Science and Technology (ICAST), 2009, pp. 380383.
pretation of the references to color in this gure legend, the reader is referred to the [13] Y. Weiting, Z. Runjing, An improved self-adaptive lter based on LMS algorithm
web version of this article.) for ltering 50 Hz interference in ECG signals, in: Proceedings of the 8th Interna-
tional Conference on Electronic Measurement and Instruments ICEMI07, 2007,
pp. 3-8743-878.
[14] M. Rahman, R. Shaik, D. Reddy, Noise cancellation in ECG signals using nor-
residual high frequency components (around 50 Hz), although not
malized sign-sign LMS algorithm, in: Proceedings of the IEEE International
as prominent as the baseline wander. Due to the presence of these Symposium on Signal Processing and Information Technology, (ISSPIT), 2009,
residual noise components, the SNR improvement is not signicant pp. 288292.
[15] S. Olmos, L. Srnmo, P. Laguna, Block adaptive lters with deterministic ref-
as seen in Table 7, where the output SNR after denoising is 4.70 dB,
erence inputs for event-related signals: BLMS and BRLS, IEEE Trans. Signal
giving an SNR improvement of 11.11 dB. Process. 50 (5) (2002) 11021112.
In Fig. 17, the results of the WNN denoising method is illustrated. [16] S.A. Rehman, R.R. Kumar, Performance comparison of adaptive lter algorithms
Although Table 7 shows that the SNR improvement of WNN is about for ECG signal enhancement, Int. J. Adv. Res. Comput. Commun. Eng. 1 (2)
(2012).
2 dB lower than the EEMD-LMS (27.92 dB), Fig. 17(b) reveals high [17] S. Malik, N.A. Saqib, Adaptive ltering for noisy and mismatched conditions
attenuation of both low and high frequency noises. The time-plots in speaker recognition, in: Proceedings of the IEE International Conference on
(Fig. 17(a)) also clearly show clear matching of the denoised signal Signal and Image Processing Applications, 2011, pp. 162167.
[18] M.Z.U. Rahman, R.A. Shaik, D.V.R.K. Reddy, Adaptive noise removal in the ECG
to the desired ECG signal. The lower SNR performance of the WNN using the block LMS algorithm, in: Proceedings of the 2nd International Con-
method may be attributed to the fact that there is a small amount ference on Adaptive Science & Technology, 2009, pp. 380383.
of low frequency noise component still present in the denoised ECG [19] N.K. Muhsin, Noise removal of ECG signal using recursive least square algo-
rithms, Al-Khwarizmi Engg. Jl. 7 (1) (2011) 1321.
(according to residual noise power spectrum in Fig. 17(b)). [20] S. Olmos, L. Srnmo, P. Laguna, Block adaptive lters with deterministic ref-
erence inputs for event-related signals: BLMS and BRLS, IEEE Trans. Signal
Process. 50 (5) (2002).
4. Conclusion [21] M. Mneimneh, E. Yaz, M. Johnson, R. Povinelli, An adaptive Kalman lter for
removing baseline wandering in ECG signals, in: Proceedings of the 33rd Annual
International Conference Computers and Cardiology, 2006, pp. 253256.
ECG is one of the most widely used non-invasive method to
[22] R. Sameni, M.B. Shamsollahi, C. Jutten, Filtering electrocardiogram signals using
understand the rhythmic activities of the heart. These signals how- the extended Kalman lter, in: Proceedings of the 27th Annual International
ever are obscured by unwanted noises/artifacts which are to be Conference IEEE Engineering in Medicine and Biology Society (EMBS), 14
minimized before the clinicians could make a proper diagnosis. September, Shanghai, China, 2005, pp. 56395642.
[23] R. Sameni, M.B. Shamsollahi, C. Jutten, M. Babaie-Zadeh, Filtering noisy ECG
In this article, a comprehensive analysis of the performance of signals using the extended Kalman lter based on a modied dynamic ECG
six different ECG denoising algorithms based on both the EMD model, in: Proceedings of the 32nd Annual International Conference Computers
and wavelets is performed. They are the C-EMD, C-EEMD, EEMD- in Cardiology, 2528 September, Lyon, France, 2005, pp. 10171020.
[24] O. Sayadi, M.B. Shamsollahi, ECG denoising and compression using a modi-
LMS, EEMD-BLMS, DWT-Th and WNN methods. Results from the ed extended Kalman lter structure, IEEE Tans. Biomed. Eng. 55 (9) (2008)
simulated and real data show that the EEMD-LMS and EEMD- 22402248.
BLMS hybrid methods provide the best performances, followed by [25] R. Sameni, M.B. Shamsollahi, C. Jutten, G.D. Clifford, A nonlinear Bayesian l-
tering framework for ECG denoising, IEEE Trans. Biomed. Eng. 54 (12) (2007)
another hybrid scheme, the WNN method. This method however, 21722185.
produced signicantly better performance than the DWT-Th. The [26] T. Schreiber, D.T. Kaplan, Nonlinear noise reduction for electrocardiograms,
C-EEMD method is shown to outperform the C-EMD method in Chaos 6 (1) (1996) 8792.
K. Krgaard et al. / Biomedical Signal Processing and Control 25 (2016) 178187 187
[27] A.K. Barros, A. Mansour, N. Ohnishi, Removing artifacts from electrocardio- [42] M. Alfaouri, K. Daqrouq, ECG signal denoising by wavelet transform threshold-
graphic signals using independent components analysis, Neurocomputing 22 ing, Am. J. Appl. Sci. 5 (3) (2008) 276281.
(1-3) (1998) 173186. [43] G. Georgieva-Tsaneva, K. Tcheshmedjiev, Denoising of electrocardiogram data
[28] J.S. Paul, M.R.S. Reddy, J. Kumar, Data processing of stress ECG using discrete with methods of wavelet transform, in: Proceedings International Conference
cosine transform, Comput. Biol. Med. 28 (6) (1998) 639658. on Computer Systems and Technologies Compsystech13, 2013, pp. 916.
[29] W. Zhaohua, H. Norden E, Ensemble empirical mode decomposition: a noise [44] H.A. Kestler, M. Haschka, W. Kratz, et al., De-noising of high-resolution ECG
assisted data analysis method, in: Advances in Adaptive Data Analysis, 2009, signals by combining the discrete wavelet transform with the Wiener lter,
pp. 141. in: Proceedings Computers in Cardiology, September, Cleveland, OH, 1998, pp.
[30] N. Pan, V. Mang I, M. Peng Un Pun Sio Hang, Accurate removal of baseline 233236.
wander in ECG using empirical mode decomposition, in: Proceedings of the [45] Q. Zhang, A. Benveniste, Wavelet Networks, IEEE Trans. Neural Netw. 3 (6) (1992
Joint Meeting of the 6th International Symposium on Noninvasive Functional November) 889898.
Source Imaging of the Brain and Heart and the International Conference on [46] S. Poungponsri, X. Yu, Electrocardigram (ECG) signal modeling and noise reduc-
Functional Biomedical Imaging, 2007, pp. 177180. tion using wavelet neural networks, in: Proceedings of the IEEE International
[31] C. Kang-Ming, Arrhythmia ECG noise reduction by ensemble empirical mode Conference on Aut. and Logis, 2009, pp. 394398.
decomposition, Sensors 10 (6) (2010) 60636080. [47] S. Poungponsri, X. Yu, An adaptive ltering approach for electrocardiogram
[32] G. Singh, G. Kaur, V. Kumar, ECG denoising using adaptive selection of IMFs (ECG) signal noise reduction using neural networks, Neucomputing 117 (2013)
through EMD and EEMD, in: Proceedings of the International Conference on 206213.
Data Science & Engineering (ICDSE), 2014, pp. 228231. [48] N.E. Huang, Review of empirical mode decomposition, Proceedings of the SPIE
[33] V. Prasad, T.S. Latha, M. Suresh, Denoising of biological signals using wavelets, 4391 (2001) 7180.
Int. J. Curr. Eng. Technol. 3 (3) (2013) 863866. [49] S. Haykin, Adaptive Filter Theory, 3rd ed., Prentice-Hall, Inc. A S, New Jersey,
[34] R. Cohen, Signal Denoising Using Wavelets, 2012, Project Report 1996, pp. 449451, ch. 10, sec. 1.
(http://tx.technion.ac.il/rc). [50] S. Mallet, A Wavelet Tour of Signal Processing, 2nd ed., A Harcourt Sci. and
[35] K. Daqrouq, ECG baseline wander reduction using discrete wavelet transform, Technol. Comp, London, 2001, ch. 4 & 7, sec 3, pp. 8991 & 255259.
Asian J. Inf. Technol. 4 (11) (2005) 989995. [51] B.N. Singh, A.K. Tiwari, Optimal selection of wavelet basis function applied to
[36] B. Arvinti, M. Costache, D. Toader, M. Oltean, A. Isar, ECG statistical denoising in ECG signal denoising, Dig. Signal Process. 16 (3) (2006) 275287.
the wavelet domain, in: Proceedings of the 9th IEEE International Symposium [52] X. Pan, B. Lee, C. Zhang, A comparison of neural network backpropagation algo-
on Electronics and Telecommunications, 2010, pp. 307310. rithms for electricity load forecasting, in: Proceedings of the IEEE International
[37] K. Daqrouq, A.-R. Al-Qawasmi, ECG enhancement using wavelet transform, Workshop on Intelligent Energy Systems, 2013 November, pp. 2227.
WSEAS Trans. Biol. Biomed. 7 (2) (2010) 6272. [53] F.D. Foresee, M.T. Hagan, Gauss-Newton Approximation to Bayesian Regular-
[38] G. Georgieva-Tsaneva, K. Tcheshmedjiev, Denoising of electrocardiogram data ization, in: Proceedings of the 1997 International Joint Conference on Neural
with methods of wavelet transform, in: Proceedings of the International Con- Networks, 1997, pp. 19301935.
ference on Computer Systems and Technologies, 2013, pp. 916. [54] The MIT-BIH ECG-ID Database [Online]. Available at: http://www.physionet
[39] M.F.M. Kania, Wavelet denoising for multi-lead high resolution ECG signals, .org/cgi-bin/atm/ATM.
Meas. Sci. Rev. 7 (2) (2007). [55] Biometric Human Identication based on ECG [Online]. Available at:
[40] P.S. Gokhale, ECG signal de-noising using discrete wavelet transform for http://physionet.org/physiobank/database/ecgiddb/biometric.shtml.
removal of 50Hz PLI noise, Int. J. Emerg. Technol. Adv. Eng. 2 (5) (2012) [56] V.K. Murthy, T.M. Grove, G.A. Harvey, L.J. Haywood, Clicinal usefullness of ECG
8185. frequency spectrum analysis, in: Proceedings of Annual Symposium on Com-
[41] O. Sayadi, M.B. Shamsollahi, Multiadaptive bionic wavelet transform: applica- puter Applications in Medical Care, 1978, pp. 610612.
tion to ECG denoising and baseline wandering reduction, EURASIP J. Adv. Signal [57] J. Zhang, R. Yan, R.X. Gao a, Z. Feng, Performance enhancement of ensem-
Process. 2007 (2007), http://dx.doi.org/10.1155/2007/41274, Article ID 41274, ble empirical mode decomposition, Mech. Syst. Signal Process. 24 (7) (2010)
11 p. 21042123.