Complete Ensemble Empirical Mode Decomposition With Adaptive Noise Algorithm Research Articles

Seismic exploration desert noise suppression based on complete ensemble empirical mode decomposition with adaptive noise

A foundation for the imaging and interpretation of stratigraphic structures is the high quality seismic data. The desert seismic events are contaminated by strong random noise. The random noise in desert seismic records has complex features, including nonlinear, non-Gaussian and low frequency, which is different from the random noise in people's previous cognition. In addition, the effective signal of desert seismic record and noise has the same frequency band. These situations have brought great difficulties to the denoising of conventional methods. While the conventional denoising algorithm for dealing with seismic signals is mainly for the suppression of random Gaussian noise. So the suppression result of random desert noise is not ideal. Based on these problems, we introduce the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm into the noise reduction process of desert seismic records. Compared with other time-frequency analysis methods, CEEMDAN algorithm has significant feature recognition effect, and remains the characteristics of adaptability. At the same time, it overcomes the problems of modal aliasing and false components. The experimental results show that denoising effect is obviously better than those of conventional denoising methods, and the suppression of the surface wave in the real seismic record is relatively thorough.

Adaptive Ultrasound Tissue Harmonic Imaging Based on an Improved Ensemble Empirical Mode Decomposition Algorithm

Complete and accurate separation of harmonic components from the ultrasonic radio frequency (RF) echo signals is essential to improve the quality of harmonic imaging. There are limitations in the existing two commonly used separation methods, that is, the subjectivity for the high-pass filtering (S_HPF) method and motion artifacts for the pulse inversion (S_PI) method. A novel separation method called S_CEEMDAN, based on the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm, is proposed to adaptively separate the second harmonic components for ultrasound tissue harmonic imaging. First, the ensemble size of the CEEMDAN algorithm is calculated adaptively according to the standard deviation of the added white noise. A set of intrinsic mode functions (IMFs) is then obtained by the CEEMDAN algorithm from the ultrasonic RF echo signals. According to the IMF spectra, the IMFs that contain both fundamental and harmonic components are further decomposed. The separation process is performed until all the obtained IMFs have been divided into either fundamental or harmonic categories. Finally, the fundamental and harmonic RF echo signals are obtained from the accumulations of signals from these two categories, respectively. In simulation experiments based on CREANUIS, the S_CEEMDAN-based results are similar to the S_HPF-based results, but better than the S_PI-based results. For the dynamic carotid artery measurements, the contrasts, contrast-to-noise ratios (CNRs), and tissue-to-clutter ratios (TCRs) of the harmonic images based on the S_CEEMDAN are averagely increased by 31.43% and 50.82%, 18.96% and 10.83%, as well as 34.23% and 44.18%, respectively, compared with those based on the S_HPF and S_PI methods. In conclusion, the S_CEEMDAN method provides improved harmonic images owing to its good adaptivity and lower motion artifacts, and is thus a potential alternative to the current methods for ultrasonic harmonic imaging.

Self-Adaptive Fault Feature Extraction of Rolling Bearings Based on Enhancing Mode Characteristic of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise

Originally, a rolling bearing, as a key part in rotating machinery, is a cyclic symmetric structure. When a fault occurs, it disrupts the symmetry and influences the normal operation of the rolling bearing. To accurately identify faults of rolling bearing, a novel method is proposed, which is based enhancing the mode characteristics of complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). It includes two parts: the first is the enhancing decomposition of CEEMDAN algorithm, and the second is the identified method of intrinsic information mode (IIM) of vibration signal. For the first part, the new mode functions (CIMFs) are obtained by combing the adjacent intrinsic mode functions (IMFs) and performing the corresponding Fast Fourier Transform (FFT) to strengthen difference feature among IMFs. Then, probability density function (PDF) is used to estimate FFT of each CIMF to obtain overall information of frequency component. Finally, the final intrinsic mode functions (FIMFs) are obtained by proposing identified method of adjacent PDF based on geometrical similarity (modified Hausdorff distance (MHD)). FIMFs indicate the minimum amount of mode information with physical meanings and avoid interference of spurious mode in original CEEMDAN decomposing. Subsequently, comprehensive evaluate index (Kurtosis and de-trended fluctuation analysis (DFA)) is proposed to identify IIM in FIMFs. Experiment results indicate that the proposed method demonstrates superior performance and can accurately extract characteristic frequencies of rolling bearing.

Two-phase extreme learning machines integrated with the complete ensemble empirical mode decomposition with adaptive noise algorithm for multi-scale runoff prediction problems

Expert systems adopted in real-time multi-scale runoff prediction are useful decision-making tools for hydrologists but the stochastic nature of any hydrological variable can pose significant challenges in attaining a reliable predictive model. This paper advocates a data-driven approach used to design two-phase hybrid model (i.e., CVEE-ELM). The model utilizes complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) coupled with the variational mode decomposition (VMD) algorithms for better frequency resolution of the input datasets and the extreme learning machine (ELM) algorithm as the objective predictive model. In the first stage of the presented model design, notable frequencies in the predictor-target data series are uncovered, utilizing the CEEMDAN algorithm where the model’s inputs are decomposed into their respective Intrinsic Mode Functions (IMFs) and the Residual (Res) series. The second stage entails a VMD approach, used to decompose the yet-unresolved high frequencies (i.e., IMF1) into their variational modes, further discerning and establishing the data attributes to be incorporated into the ELM model to simulate the respective IMFs, Res and VM data series, aggregated as an integrative tool for multiscale runoff prediction. In the model evaluative phase, the hybrid CVEE-ELM is cross-validated with a single-phase hybrid ELM and an autoregressive integrated moving average (ARIMA) model to benchmark its accuracy for predicting 1-, 3- and 6-month ahead runoff in Yingluoxia watershed, Northwestern China. Two-phase hybrid model exhibits superior accuracy at all lead times, to accord with high degree of correlations between the observed and the forecasted runoff, a relatively large Nash-Sutcliffe and the Legate-McCabe Index. Taylor diagrams depict the two-phase hybrid CVEE-ELM model generated forecasts located close to a reference (i.e., a perfect) model, with a lower root-mean square centered difference, and a correspondingly large correlation for all forecast horizons, although the model’s accuracy for shorter lead times (1-month), as expected, are better than the 3- and 6-month horizon. The study shows that the two-phase hybrid CVEE-ELM model where an integration of two frequency resolution algorithms are made, is a preferred data-driven tool that can be explored for real-life decision-system design, particularly for hydrological forecasting problems that have significantly stochastic data features, and thus, will require reliable forecasts to be generated at multi-step horizons.

Fault Diagnosis of Gas Pressure Regulators Based on CEEMDAN and Feature Clustering

Gas pressure regulators are widely applied in natural gas pipeline networks, correspondingly, establishing an efficient fault diagnosis approach of regulators plays a critical role in optimizing the safety and reliability of pipeline network systems. In our paper, considering that the outlet pressure signals of gas regulators are nonstationary and nonlinear, we propose a fault diagnosis approach combining a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and fuzzy c-means (FCM) clustering to classify three typical faults of gas regulators. First, we propose to apply the CEEMDAN approach for decomposing intrinsic mode functions (IMFs). Then feature vectors of the typical faults are established by Hilbert marginal spectrum (HMS) of IMFs. Finally, we adopt cluster centers and feature clustering algorithm to distinguish the types of faults. The experimental results indicate the high performance of the present fault diagnosis approach. The membership degrees of test samples obtained from the CEEMDAN algorithm are optimized to be within 0.9 to 1.

Smoothing Photovoltaic Power Fluctuations for Cascade Hydro-PV-Pumped Storage Generation System Based on a Fuzzy CEEMDAN

Due to strong volatility and intermittent characteristics, the fluctuations of the photovoltaic (PV) output is inevitable which cause negative impacts on power system operation. However, such an issue can be resolved in a combined cascade hydro-PV-pumped storage (CH-PV-PS) generation system through an appropriate control. Based on the optimal base power of variable-speed pumped storage station (VSPSS), a smoothing method of fuzzy complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is proposed in this paper. To prevent smoothing insufficient and excessive, the fuzzy CEEMDAN algorithm is used to obtain the target power of the photovoltaic-pumped storage (PV-PS) generation system and the control signal of cascade hydro stations (CHSs) for eliminating large amplitude fluctuations of the PV output. Furthermore, in order to overcome the drawback that too frequent conversion of unit operating mode would reduce the service life and smoothing effect of the VSPSS unit, the optimization model of the base power of the VSPSS is established and solved by the grid adaptive direct search method (MADS) to obtain the control signal of the VSPSS for suppressing the short-term fluctuations of the PV output. Finally, the performance of the method is evaluated through using the PV station data in Xiaojin County, Sichuan province, China. The simulation results reveal that compared with the fixed base power smoothing method, this method can effectively suppress the PV power fluctuations and improve the smoothing effect and energy efficiency.

A Hybrid De-Noising Algorithm for the Gear Transmission System Based on CEEMDAN-PE-TFPF

In order to remove noise and preserve the important features of a signal, a hybrid de-noising algorithm based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Permutation Entropy (PE), and Time-Frequency Peak Filtering (TFPF) is proposed. In view of the limitations of the conventional TFPF method regarding the fixed window length problem, CEEMDAN and PE are applied to compensate for this, so that the signal is balanced with respect to both noise suppression and signal fidelity. First, the Intrinsic Mode Functions (IMFs) of the original spectra are obtained using the CEEMDAN algorithm, and the PE value of each IMF is calculated to classify whether the IMF requires filtering, then, for different IMFs, we select different window lengths to filter them using TFPF; finally, the signal is reconstructed as the sum of the filtered and residual IMFs. The filtering results of a simulated and an actual gearbox vibration signal verify that the de-noising results of CEEMDAN-PE-TFPF outperforms other signal de-noising methods, and the proposed method can reveal fault characteristic information effectively.

Quantification of Feto-Maternal Heart Rate from Abdominal ECG Signal Using Empirical Mode Decomposition for Heart Rate Variability Analysis

In this paper, a robust method of feto-maternal heart rate extraction from the non-invasive composite abdominal Electrocardiogram (aECG) signal is presented. The proposed method is based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method, in which a composite aECG signal is decomposed into its constituent frequency components called Intrinsic Mode Functions (IMFs) or simply “modes”, with better spectral separation. Decomposed IMFs are then selected manually according to probable maternal and fetal heart rate information and are processed further for quantification of maternal and fetal heart rate and variability analysis. The proposed method was applied to aECG recordings collected from three different sources: (i) the PhysioNet (adfecgdb) database; (ii) the PhysioNet (nifecgdb) database; and (iii) synthetic aECG signal generated from mathematical modeling in the LabVIEW software environment. An overall sensitivity of 98.83%, positive diagnostic value of 97.97%, accuracy of 96.93% and performance index of 96.75% were obtained in the case of Maternal Heart Rate (MHR) quantification, and an overall sensitivity of 98.13%, positive diagnostic value of 97.62%, accuracy of 95.91% and performance index of 95.69% were obtained in case of Fetal Heart Rate (FHR) quantification. The obtained results confirm that CEEMDAN is a very robust and accurate method for extraction of feto-maternal heart rate components from aECG signals. We also conclude that non-invasive aECG is an effective and reliable method for long-term FHR and MHR monitoring during pregnancy and labor. The requirement of manual intervention while selecting the probable maternal and fetal components from “n” number of decomposed modes limits the real-time application of the proposed methodology. This is due to the fact that the number of modes “n” produced by the CEEMDAN decomposition is unpredictable. However, the proposed methodology is well suited for applications where a small time-delay or offset in feto-maternal monitoring can be acceptable. In future, application-specific modification of the CEEMDAN algorithm can be implemented to eliminate manual intervention completely and will be suitable for long-term feto-maternal monitoring.

Pretreatment and Wavelength Selection Method for Near-Infrared Spectra Signal Based on Improved CEEMDAN Energy Entropy and Permutation Entropy

The noise of near-infrared spectra and spectral information redundancy can affect the accuracy of calibration and prediction models in near-infrared analytical technology. To address this problem, the improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and permutation entropy (PE) were used to propose a new method for pretreatment and wavelength selection of near-infrared spectra signal. The near-infrared spectra of glucose solution was used as the research object, the improved CEEMDAN energy entropy was then used to reconstruct spectral data for removing noise, and the useful wavelengths are selected based on PE after spectra segmentation. Firstly, the intrinsic mode functions of original spectra are obtained by improved CEEMDAN algorithm. The useful signal modes and noisy signal modes were then identified by the energy entropy, and the reconstructed spectral signal is the sum of useful signal modes. Finally, the reconstructed spectra were segmented and the wavelengths with abundant glucose information were selected based on PE. To evaluate the performance of the proposed method, support vector regression and partial least square regression were used to build the calibration model using the wavelengths selected by the new method, mutual information, successive projection algorithm, principal component analysis, and full spectra data. The results of the model were evaluated by the correlation coefficient and root mean square error of prediction. The experimental results showed that the improved CEEMDAN energy entropy can effectively reconstruct near-infrared spectra signal and that the PE can effectively solve the wavelength selection. Therefore, the proposed method can improve the precision of spectral analysis and the stability of the model for near-infrared spectra analysis.

Quantitative metric for MR brain tumour grade classification using sample space density measure of analytic intrinsic mode function representation

In the present study, a new feature named as density measure is proposed for classification of the glioma brain tumour magnetic resonance (MR) image into low and high-grade categories. The proposed feature is derived using improved complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and Hilbert transformation technique. The proposed feature uses the difference signal created by mapping of the fluid attenuation inversion recovery segmented region onto T1 and T1-contrast-enhanced MR images. This difference signal is decomposed into various intrinsic mode functions (IMFs) using improved CEEMDAN algorithm that effectively captures the texture variations existing in both tumour groups. Then, the Hilbert transformation of resulting IMF is computed that provides the analytic signal representation, thereby giving a better visualisation of the texture difference. The proposed feature is calculated from this analytic signal representation at 97% confidence level. Subsequently, this feature is utilised to calculate a quantitative metric for tumour classification. The proposed metric has been validated on 120 tumorous images taken from brain tumour image segmentation benchmark (BRATS) 2012 dataset and the images taken from Harvard Medical School repository. The results illustrate that proposed metric yields an overall classification accuracy of 100% which is better than existing state-of-art works.

Assessment of vocal cord nodules: a case study in speech processing by using Hilbert-Huang Transform

Vocal cord nodules represent a pathological condition for which the growth of unnatural masses on vocal folds affects the patients. Among other effects, changes in the vocal cords’ overall mass and stiffness alter their vibratory behaviour, thus changing the vocal emission generated by them. This causes dysphonia, i.e. abnormalities in the patients’ voice, which can be analysed and inspected via audio signals. However, the evaluation of voice condition through speech processing is not a trivial task, as standard methods based on the Fourier Transform, fail to fit the non-stationary nature of vocal signals. In this study, four audio tracks, provided by a volunteer patient, whose vocal fold nodules have been surgically removed, were analysed using a relatively new technique: the Hilbert-Huang Transform (HHT) via Empirical Mode Decomposition (EMD); specifically, by using the CEEMDAN (Complete Ensemble EMD with Adaptive Noise) algorithm. This method has been applied here to speech signals, which were recorded before removal surgery and during convalescence, to investigate specific trends. Possibilities offered by the HHT are exposed, but also some limitations of decomposing the signals into so-called intrinsic mode functions (IMFs) are highlighted. The results of these preliminary studies are intended to be a basis for the development of new viable alternatives to the softwares currently used for the analysis and evaluation of pathological voice.

A Comparative Study of Empirical Mode Decomposition-Based Filtering for Impact Signal

The Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) has been used to propose a new method for filtering time series originating from nonlinear systems. The filtering method is based on fuzzy entropy and a new waveform. A new waveform is defined wherein Intrinsic Mode Functions (IMFs)—which are obtained by CEEMDAN algorithm—are firstly sorted in ascending order (the sorted IMFs is symmetric about center point, because at any point, the mean value of the envelope line defined by the local maxima and the local minima is zero), and the energy of the sorted IMFs are calculated, respectively. Finally, the new waveform with axial symmetry can be obtained. The complexity of the new waveform can be quantified by fuzzy entropy. The relevant modes (noisy signal modes and useful signal modes) can be identified by the difference between the fuzzy entropy of the new waveform and the next adjacent new waveform. To evaluate the filter performance, CEEMDAN and sample entropy, Ensemble Empirical Mode Decomposition (EEMD) and fuzzy entropy, and EEMD and sample entropy were used to filter the synthesizing signals with various levels of input signal-to-noise ratio (SNRin). In particular, this approach is successful in filtering impact signal. The results of the filtering are evaluated by a de-trended fluctuation analysis (DFA) algorithm, revised mean square error (RMSE), and revised signal-to-noise ratio (RSNR), respectively. The filtering results of simulated and impact signal show that the filtering method based on CEEMDAN and fuzzy entropy outperforms other signal filtering methods.

Analysis of laser speckle contrast images variability using a novel empirical mode decomposition: comparison of results with laser Doppler flowmetry signals variability.

Laser Doppler flowmetry (LDF) and laser speckle contrast imaging (LSCI) have emerged as noninvasive optical modalities to monitor microvascular blood flow. Many studies proposed to extract physiological information from LDF by analyzing signals variability. By opposition, such analyses for LSCI data have not been conducted yet. We propose to analyze LSCI variability using a novel data-driven method: the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). CEEMDAN is suitable for nonlinear and nonstationary data and leads to intrinsic mode functions (IMFs). It is based on the ensemble empirical mode decomposition (EEMD) which relies on empirical mode decomposition (EMD). In our work the average frequencies of LSCI IMFs given by CEEMDAN are compared with the ones given by EMD and EEMD. Moreover, LDF signals acquired simultaneously to LSCI data are also processed with CEEMDAN, EMD and EEMD. We show that the average frequencies of IMFs given by CEEMDAN depend on the signal-to-noise ratio (SNR) used in the computation but, for a given SNR, the average frequencies found for LSCI are close to the ones obtained for LDF. By opposition, EEMD leads to IMFs with frequencies that do not vary much when the SNR level is higher than a threshold. The new CEEMDAN algorithm has the advantage of achieving a complete decomposition with no error in the reconstruction but our study suggests that further work is needed to gain knowledge in the adjustment of the added noise level. CEEMDAN, EMD and EEMD are data-driven methods that can provide a better knowledge of LSCI.