EMD-BASED ECG DENOISING USING SOURCE SEPARATION

We consider the problem of speech denoising using source separation. In this study we have proposed a hybrid technique that consists in applying in the first step, the Bionic Wavelet Transform (BWT) to two different mixtures of the same speech signal with noise. This speech signal is corrupted by a Gaussian white noise with two different values of the Signal to Noise Ratio (SNR) in order to obtain those two mixtures. The second step consists in computing the entropy of each bionic wavelet coefficient and finds the two subbands having the minimal entropy. Those two subbands are used to estimate the separation matrix of the speech signal from noise by using the source separation. Our proposed technique is evaluated by comparing it to the denoising technique based on source separation in time domain.

Electrocardiogram (ECG) signal recording is a challenging task in the field of biomedical engineering. ECG is the cardiac recording of systematic electrical activity arising from the electro-physiological rhythm of the heart muscle. But, during processing, the ECG signal is contaminated with different types of noise in the medical environment. An immense task is the separation of the preferred signal from noises caused by artifacts like muscle noise, power line interference (PLI), baseline wandering (BW), and motion artifacts (MA). Hence, our paper focuses on 50 Hz PLI which is a major artifact/noise affecting the recorded ECG signal. This paper comprehensively reviews fundamental concepts of different denoising techniques. Some of the pioneers’ works are also concisely explained in the paper. Further, in this work, comparative analysis is carried out using notch filter, adaptive filter, discrete wavelet transform (DWT) and empirical mode decomposition (EMD) for filtering 50 Hz PLI noise. A considerable improvement in signal-to-noise ratio (SNR) can be observed from the results when compared with SNR input and SNR output values. Performance comparisons of all the four techniques are also analyzed based on variations in noise frequency. The simulations were carried out in the environment of MATLAB 2019b®. This work epitomizes the significance of our quantitative evaluation, in which adaptive filters are found to perform better with respect to the SNR, whereas DWT performs better with assessment of mean square error (MSE).

A filtering method based on empirical mode decomposition (EMD) for coulostatically-induced transients (CITs) was presented. The effect of EMD filtering was evaluated from different simulation systems. To boost the applicable solution for EMD filtering and reduce the subjectivity of filtering, discussions of the simulating noises were mainly focused on white noise, high frequency noise, 50 Hz noise from commercial power and blend of above-mentioned noises. To illustrate the most importance of EMD filtering for the goodness of fit of CIS, one real corrosion system involving multi-time constant was simultaneously investigated by electrochemical impedance spectrum (EIS) and coulostatically-induced spectrum (CIS). The results reported here demonstrate that EMD de-noising is applicable for CITs. The proposed method shows good performance of de-noising and is an alternative de-noising method for the CITs analysis. CIS with EMD filtering are in good agreement with EIS. For practical application of EMD, removal of the first two items of intrinsic mode function (IMF) and 50 Hz element in forth IMF will be generally satisfactory for CIS analysis.

A new method was proposed to identify speech-segment endpoints based on the empirical mode decomposition (EMD) and a new wavelet entropy ratio with improving the accuracy of voice activity detection. With the EMD, the noise signals can be decomposed into several intrinsic mode functions (IMFs). Then the proposed wavelet energy entropy ratio can be used to extract the desired feature for each IMFs component. In view of the question that the method of voice endpoint detection based on the original wavelet entropy ratio cannot adapt to the low signal-to-noise ratio (SNR) condition, an appropriate positive constant was introduced to the basic wavelet energy entropy ratio with effectively improved discriminability between the speech and noise. After comparing the traditional wavelet energy entropy ratio with the proposed wavelet energy entropy ratio, the experiment results show that the proposed method is simple and fast. The speech endpoints can be accurately detected in low SNR environments.

Near-infrared spectroscopy (NIRS) can be used as the basis of non-invasive neuroimaging that may allow the measurement of haemodynamic changes in the human brain evoked by applied stimuli. Since this technique is very sensitive, physiological interference arising from the cardiac cycle and breathing can significantly affect the signal quality. Such interference is difficult to remove by conventional techniques because it occurs not only in the extracerebral layer but also in the brain tissue itself. Previous work on this problem employing temporal filtering, spatial filtering, and adaptive filtering have exhibited good performance for recovering brain activity data in evoked response studies. However, in this study, we present a time-frequency adaptive method for physiological interference reduction based on the combination of empirical mode decomposition (EMD) and Hilbert spectral analysis (HSA). Monte Carlo simulations based on a five-layered slab model of a human adult head were implemented to evaluate our methodology. We applied an EMD algorithm to decompose the NIRS time series derived from Monte Carlo simulations into a series of intrinsic mode functions (IMFs). In order to identify the IMFs associated with symmetric interference, the extracted components were then Hilbert transformed from which the instantaneous frequencies could be acquired. By reconstructing the NIRS signal by properly selecting IMFs, we determined that the evoked brain response is effectively filtered out with even higher signal-to-noise ratio (SNR). The results obtained demonstrated that EMD, combined with HSA, can effectively separate, identify and remove the contamination from the evoked brain response obtained with NIRS using a simple single source–detector pair.

SCNN: Scalogram-based convolutional neural network to detect obstructive sleep apnea using single-lead electrocardiogram signals

Source signals often contain various hidden waveforms, which further provide precious information. Therefore, detecting and capturing these waveforms is very important. For signal decomposition (SD), discrete Fourier transform (DFT) and empirical mode decomposition (EMD) are two main tools. They both can easily decompose any source signal into different components. DFT is based on Cosine functions; EMD is based on a collection of intrinsic mode functions (IMFs). With the help of Cosine functions and IMFs respectively, DFT and EMD can extract additional information from sensed signals. However, due to a considerably finite frequency resolution, EMD easily causes frequency mixing. Although DFT has a larger frequency resolution than EMD, its resolution is also finite. To effectively detect and capture hidden waveforms, we use an optimization algorithm, differential evolution (DE), to decompose. The technique is called SD by DE (SDDE). In contrast, SDDE has an infinite frequency resolution, and hence it has the opportunity to exactly decompose. Our proposed SDDE approach is the first tool of directly applying an optimization algorithm to signal decomposition in which the main components of source signals can be determined. For source signals from four combinations of three periodic waves, our experimental results in the absence of noise show that the proposed SDDE approach can exactly or almost exactly determine their corresponding separate components. Even in the presence of white noise, our proposed SDDE approach is still able to determine the main components. However, DFT usually generates spurious main components; EMD cannot decompose well and is easily affected by white noise. According to the superior experimental performance, our proposed SDDE approach can be widely used in the future to explore various signals for more valuable information.

In ultrasonic testing of coarse-grained materials, signal to noise ratio (SNR) of testing signals is reduced seriously for the structure noise, and echoes from defects are difficult to be identified. In order to improve the SNR and the reliability of ultrasonic testing of coarse-grained materials, empirical mode decomposition (EMD) is introduced to process the testing signal here. Signal envelope can be formed by using cubic spline interpolation, and nonlinear and non-stationary signal can be decomposed self-adaptive into the sum of several intrinsic mode functions (IMF) by using characteristic time scale of the signals, and then higher order and tendency of the original signals can be obtained. The denoising experiment with low SNR simulated signal are achieved according to the feature of EMD, and SNR is enhanced more by comparison with the wavelet analysis method. And testing signal collected from coarse-grained materials is used to finish denoising experiment, and it is shown from the experiment result that the EMD has better adaptive ability in decomposing noise-polluted signals and less empirical information is required in the denoising process. DOI: http://dx.doi.org/10.11591/telkomnika.v11i9.3286

In this paper, we propose a novel ECG signal enhancement method based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Higher Order Statistics (HOS). In our scheme, the noisy ECG signal is first decomposed adaptively into oscillatory components called intrinsic mode functions (IMFs) by using Empirical Mode Decomposition (EMD) or its variants. Therefore, the obtained modes are separated into two groups of noisy signal modes and one group of useful signal modes, by using a novel criterion derived from the HOS namely the fourth order cumulant or kurtosis. After that, a modified shrinkage scheme based on Interval Thresholding technique is adaptively applied to each selected IMF from the noise-dominant groups in order to reduce the noise and to preserve the QRS complex. The overall filtered ECG signal is then reconstructed by combining the thresholded IMFs and the retained unprocessed lower frequency relevant IMFs. Various tests and simulations are investigated to evaluate the performance of our proposed approach in combination with the EMD, Ensemble EMD (EEMD) and CEEMDAN algorithms. The simulation results carried on MIT-BIH Arrhythmia database, show that CEEMDAN method gives better performance than the two other methods, and outperforms some state-of-the-art methods in terms of Signal to Noise Ratio (SNR) and Root Mean Square Error (RMSE).

Each year 400,000 North Americans die from sudden cardiac death (SCD). T- wave alternans (TWA) refers to an alternating pattern in the T-wave portion of the surface electrocardiogram (ECG) and has been shown as a risk stratifier for SCD. These subtle changes in the T-waves are in the micro-volt scale and ambulatory ECG recordings usually contain biological noise. Also, data non-stationarity owing to heart rate variability and the amplitude variability in TWA magnitude can limit the accuracy of the detection techniques. This necessitates the need for robust detection algorithms for processing such non-stationary data. In this thesis, we have proposed an Empirical Mode Decomposition (EMD) based scheme combined with the Instantaneous Frequency (IF). EMD decomposes the signal into several monocomponent signals called Intrinsic Mode Functions (IMFs). IF extracted from these IMFs provides an accurate estimate of time varying frequency components and hence can aid during characterization of TWAs. In order to validate the performance of the proposed detection technique, the feature vectors extracted from the IMFs were fed to a linear discriminant analysis (LDA) classifier. The performance assessment was carried out using two datasets: (a) Synthetic TWAs: 72 signals obtained from publicly accessible Physionet database and (b) TWAs from patients: 55 ambulatory ECG signals obtained from the Toronto General Hospital. Using an unbiased leave-one-out cross validation strategy, maximum overall classification accuracies of 86.1% and 81.8% were achieved for TWA detection from synthetic and ambulatory ECG recordings respectively. In addition, the usability of the proposed technique has been investigated to assess its suitability for addressing another cardiovascular problem stroke. Atrial Fibrillation (AF) has been identified as a risk factor to increase the chances of stroke. The most common method in studying the complex AF electrograms is to employ dominant frequency (DF) analysis; however, due to signal non-stationarity DF does not always provide the best estimate of the atrial activation rate. As a result, analyzing the electrograms via EMD and IF has been investigated as the second contribution of this work.

This paper presents a new denoising method called EMD-ITF that was based on Empirical Mode Decomposition (EMD) and the Improved Thresholding Function (ITF) algorithms. EMD was applied to decompose adaptively a noisy signal into intrinsic mode functions (IMFs). Then, all the noisy IMFs were thresholded by applying the improved thresholding function to suppress noise and improve the signal to noise ratio (SNR). The method was tested on simulated and real data and the results were compared to the EMD-Based signal denoising methods using the soft thresholding. The results showed the superior performance of the new EMD-ITF denoising over the traditional approach. The performance were evaluated in terms of SNR in dB, and Mean Square Error (MSE).

Sleep disorders has a vital effect on mental depression and many other diseases of human body. Diagnosing the sleep disorder in an early curable stage may help to provide better treatment and save the life. The EEG (Electroencephalogram) signal is one of the most uses bio signal for capturing brain activities to detect and diagnosis the sleep disorders. Empirical mode decomposition (EMD) is an efficient time-frequency data analysis technique for diagnosing disease by analyzing EEG signal. However, it is a challenging issue to select the optimal intrinsic mode functions (IMFs) of Empirical mode decomposition (EMD) for extracting discriminant properties of EEG signals to diagnosis the sleep disorder. From this point of view, this paper presents a model to select optimal IMF of EMD for diagnosing the sleep disorder using EEG brain signal. In this proposed model, EMD is applied to decompose and analyze EEG signal for extracting biomarker/feature of sleep disorders. During the EMD decomposition process, different levels of IMF are extracted and features, i.e., Shannon Entropy, Spectral Entropy, Standard deviation, Skewness and Kurtosis are calculated from those IMFs for detecting the sleep disorders. In identification process, the multiclass support vector machine (MC-SVM) classification algorithm is used and sleep disorders are classified based on trained knowledge. Finally, the performance of proposed model is evaluated for different IMFs of EMD and find the optimal IMF for sleep disorder diagnosis. For evaluating the proposed model, a benchmark dataset including 4 types of data such as Apnea, REM, PLM and healthy subjects are used in experiment. According to the experimental result, the proposed model achieves the optimal classification performance for IMF 8, i.e., 93.24% average classification accuracy.

Primal sketch performs an important role in early vision. In this paper, we propose a novel method to obtain the primal sketch of natural images by integrating empirical mode decomposition (EMD) techniques and image gradient. 2D EMD approach can decompose the image into a finite number of intrinsic mode functions (IMF), and each one represents the original image in a different scale, with the 1st IMF representing the finest scale. To enhance the information represented by the IMF, we multiply the 1st IMF by the image gradient. This enhanced IMF highlights intensity changes in the image. By linking all the maximal points in the enhanced IMF, we obtain a primal sketch of the original image. Compared with the existed primal sketch extraction methods, our method is fully driven by the image data, and it needs neither to choose filters nor to learn the image bases. The experiment results show that our method is fast and effective.

Using filter bank property to simplify the calculations of Empirical Mode Decomposition

In this paper, an aliasing noise restraint technique and a system identification-based surface electromyography (sEMG)-force prediction model are proposed to realize a type of robust sEMG and muscle force prediction. For signal denoising, a novel non-negative matrix factorization screening empirical mode decomposition (NMFSEMD) and a fast orthogonal search (FOS)-based muscle force prediction model are developed. First, the NMFSEMD model is used to screen the empirical mode decomposition (EMD) results into the noisy intrinsic mode functions (IMF). Then, the noise matrix is computed using IMF translation and superposition, and the matrix is used as the input of NMF to obtain the denoised IMF. Furthermore, the reconstruction outcome of the NMFSEMD method can be used to estimate the denoised sEMG. Finally, a new sEMG muscle force prediction model, which considers a kind of candidate function in derivative form, is constructed, and a data-training-based linear weighted model is obtained. Extensive experimental results validate the suggested method’s correction: after the NMFSEMD denoising of raw sEMG signal, the signal-noise ratio (SNR) can be improved by about 15.0 dB, and the energy percentage (EP) can be greater than 90.0%. Comparing with the muscle force prediction models using the traditional pretreatment and LSSVM, and the NMFSEMD plus LSSVM-based method, the mean square error (MSE) of our approach can be reduced by at least 1.2%.