Dictionary learning and shift-invariant sparse coding denoising for CSEM data combined with CEEMD

Geophysics ◽  
2021 ◽  
pp. 1-52
Author(s):  
Guang Li ◽  
Zhushi He ◽  
Jing Tian Tang ◽  
Juzhi Deng ◽  
Xiaoqiong Liu ◽  
...  
Keyword(s):  
Dictionary Learning ◽  
Sparse Coding ◽  
Learning Algorithm ◽  
Signal To Noise Ratio ◽  
Estimation Method ◽  
Real Data ◽  
Ensemble Empirical Mode Decomposition ◽  
Baseline Drift ◽  
Mode Decomposition ◽  
Useful Signal

Controlled-source electromagnetic (CSEM) data recorded in industrialized areas are inevitably contaminated by strong cultural noise. Traditional noise attenuation methods are often ineffective for intricate aperiodic noise. To address the problem mentioned above, we propose a novel noise isolation method based on fast Fourier transform (FFT), complementary ensemble empirical mode decomposition (CEEMD) and shift-invariant sparse coding (SISC, an unsupervised machine learning algorithm under a data-driven framework). First, large powerline noise is accurately subtracted in the frequency domain. Then, the CEEMD based algorithm is used to correct the large baseline drift. Finally, taking advantage of the sparsity of periodic signals, SISC is applied to autonomously learn a feature atom (the useful signal with a length of one period) from the detrended signal and recover CSEM signal with high accuracy. We demonstrate the performance of the SISC by comparing with other three promising signal processing methods, including the mathematic morphology filtering (MMF), soft-threshold wavelet filtering, and K-SVD (another dictionary learning method) sparse decomposition. Experimental results illustrate that SISC provides the best performance. Robustness test results show that SISC can increase the signal-to-noise ratio (SNR) of noisy signal from 0 dB to more than 15 dB. Case studies of synthetic and real data collected in the Chinese Provinces Sichuan and Yunnan show that the proposed method is capable of effectively recovering the useful signal from the observed data contaminated with different kinds of strong ambient noise. The curves of U/I and apparent resistivity after applying the proposed method improved greatly. Moreover, the proposed method performs better than the robust estimation method based on correlation analysis.

scholarly journals A Denoising Method of Ship Radiated Noise Signal Based on Modified CEEMDAN, Dispersion Entropy, and Interval Thresholding

Electronics ◽  
2019 ◽  
Vol 8 (6) ◽  
pp. 597 ◽  
Author(s):  
Guohui Li ◽  
Zhichao Yang ◽  
Hong Yang
Keyword(s):  
Signal To Noise Ratio ◽  
Noise Signal ◽  
Ensemble Empirical Mode Decomposition ◽  
Measurement Technology ◽  
Signal Denoising ◽  
Frequency Noise ◽  
Denoising Method ◽  
Radiated Noise ◽  
Mode Decomposition ◽  
Adaptive Noise

Due to the non-linear and non-stationary characteristics of ship radiated noise (SR-N) signal, the traditional linear and frequency-domain denoising methods cannot be used for such signals. In this paper, an SR-N signal denoising method based on modified complete ensemble empirical mode decomposition (EMD) with adaptive noise (CEEMDAN), dispersion entropy (DE), and interval thresholding is proposed. The proposed denoising method has the following advantages: (1) as an improved version of CEEMDAN, modified CEEMDAN (MCEEMDAN) combines the advantages of EMD and CEEMDAN, and it is more reliable than CEEMDAN and has less consuming time; (2) as a fast complexity measurement technology, DE can effectively identify the type of intrinsic mode function (IMF); and (3) interval thresholding is used for SR-N signal denoising, which avoids loss of amplitude information compared with traditional denoising methods. Firstly, the original signal is decomposed into a series of IMFs using MCEEMDAN. According to the DE value of IMF, the modes are divided into three types: noise IMF, noise-dominated IMF and pure IMF. After noise IMFs are removed, the noise-dominated IMFs are denoised using interval thresholding. Finally, the pure IMF and the processed noise-dominated IMFs are reconstructed to obtain the final denoised signal. The denoising experiments with the Chen’s chaotic system show that the proposed method has a higher signal-to-noise ratio (SNR) than the other three methods. Applying the proposed method to denoise the real SR-N signal, the topological structure of chaotic attractor can be recovered clearly. It is proved that the proposed method can effectively suppress the high-frequency noise of SR-N signal.

scholarly journals The Application of Machine Learning ICA-VMD in an Intelligent Diagnosis System in a Low SNR Environment

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8344
Author(s):  
Shih-Lin Lin
Keyword(s):  
Machine Learning ◽  
Optimization Problem ◽  
Learning Algorithm ◽  
Signal To Noise Ratio ◽  
Sensory Cues ◽  
Original Source ◽  
Noise Interference ◽  
Low Snr ◽  
First Case ◽  
Mode Decomposition

This paper proposes a new method called independent component analysis–variational mode decomposition (ICA-VMD), which combines ICA and VMD. The purpose is to study the application of ICA-VMD in low signal-to-noise ratio (SNR) signal processing and data analysis. ICA is a very important method in the field of machine learning. It is an unsupervised learning algorithm that can dig out the independent factors hidden in the observation signal. The VMD method estimates each signal component by solving the frequency domain variational optimization problem, and it is very suitable for mechanical fault diagnosis. The advantage of ICA-VMD is that it requires two sensory cues to distinguish the original source from the unwanted noise. In the three cases studied here, the original source was first contaminated by white Gaussian noise. The three cases in this study are under different SNR conditions. The SNR in the first case is –6.46 dB, the SNR in the second case is –21.3728, and the SNR in the third case is –46.8177. The simulation results show that the ICA-VMD method can effectively recover the original source from the contaminated data. It is hoped that, in the future, there will be new discoveries and advances in science and technology to solve the noise interference problem through this method.

A method for remote sensing image denoising based on structured dictionary learning and cloud computing

2020 ◽  
pp. 002072092093107
Author(s):  
Ru Yang ◽  
Zhentao Qin ◽  
Xiangyu Zhao
Keyword(s):  
Remote Sensing ◽  
Cloud Computing ◽  
Image Denoising ◽  
Dictionary Learning ◽  
Learning Algorithm ◽  
Signal To Noise Ratio ◽  
Remote Sensing Data ◽  
Remote Sensing Image ◽  
Multispectral Image ◽  
Structured Dictionary

With the emerging technology of remote sensing, a huge amount of remote sensing data is collected and stored in the remote sensin02222g platform, and the transmission and processing of data on the platform is extremely wasteful. It is essential to incorporate the speedy remote sensing processing services in an integrated cloud computing architecture. In order to improve the denoising ability of remote sensing image, a new structured dictionary-based method for multispectral image denoising based on cluster is proposed. This method incorporates both the locality of spatial and the correlation across spectrum of multispectral image. Remote sensing image is divided into different groups by clustering, and sparse representation coefficients of spatial and spectral and dictionary is obtained according to the dictionary learning algorithm. After threshold processing, the similar blocks are averaged and realized with multispectral remote sensing image denoising. The algorithm is applied to denoise the noisy remote sensing image of Maoergai area in the upper Minjiang which contain typical vegetation and soil is chosen as study area, simulation results show that higher peak-signal to noise ratio can be obtained as compared to other recent image denoising methods.

scholarly journals Handling Data Heterogeneity in Electricity Load Disaggregation via Optimized Complete Ensemble Empirical Mode Decomposition and Wavelet Packet Transform

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3133
Author(s):  
Kwok Tai Chui ◽  
Brij B. Gupta ◽  
Ryan Wen Liu ◽  
Pandian Vasant
Keyword(s):  
Signal To Noise Ratio ◽  
Wavelet Packet ◽  
Ensemble Empirical Mode Decomposition ◽  
Wavelet Packet Transform ◽  
Smart Meters ◽  
Model Decomposition ◽  
Mode Decomposition ◽  
Data Heterogeneity ◽  
Electricity Load ◽  
Load Disaggregation

Global warming is a leading world issue driving the common social objective of reducing carbon emissions. People have witnessed the melting of ice and abrupt changes in climate. Reducing electricity usage is one possible method of slowing these changes. In recent decades, there have been massive worldwide rollouts of smart meters that automatically capture the total electricity usage of houses and buildings. Electricity load disaggregation (ELD) helps to break down total electricity usage into that of individual appliances. Studies have implemented ELD models based on various artificial intelligence techniques using a single ELD dataset. In this paper, a powerline noise transformation approach based on optimized complete ensemble empirical model decomposition and wavelet packet transform (OCEEMD–WPT) is proposed to merge the ELD datasets. The practical implications are that the method increases the size of training datasets and provides mutual benefits when utilizing datasets collected from other sources (especially from different countries). To reveal the effectiveness of the proposed method, it was compared with CEEMD–WPT (fixed controlled coefficients), standalone CEEMD, standalone WPT, and other existing works. The results show that the proposed approach improves the signal-to-noise ratio (SNR) significantly.

scholarly journals Online dictionary learning method for extracting GPR diffractions

2019 ◽  
Vol 16 (6) ◽  
pp. 1116-1123
Author(s):  
Jingtao Zhao ◽  
Caixia Yu ◽  
Suping Peng ◽  
Zongnan Chen
Keyword(s):  
Plane Wave ◽  
Dictionary Learning ◽  
Sparse Coding ◽  
Learning Algorithm ◽  
Scale Up ◽  
Shielding Effect ◽  
Small Scale ◽  
Near Surface ◽  
Online Dictionary Learning ◽  
Local Plane

Abstract Diffractions in a Ground-Penetrating Radar (GPR) data carry significant responses from near-surface small-scale fractures or karsts. However, this geological information is generally difficult to extract because of the shielding effect of strong reflections from subsurface layers. In order to solve this problem, a GPR diffraction extraction method is proposed for individually separating and imaging of GPR diffractions that incorporates a local plane-wave destruction filter with an online dictionary learning algorithm. The strong reflections are estimated and eliminated by the local plane-wave destruction method and the weak GPR diffractions are extracted by a sparse coding algorithm. In solving this model, a trust-region algorithm is used for accelerating the sparse coding procedures that can scale up gracefully to a large GPR data processing. A numerical experiment demonstrates the good performance of the proposed method in destroying strong reflections and enhancing weak diffractions from small-scale void holes. Real data application further verifies its potential value in resolving fine details of subsurface small-scale buried targets, such as pipes or void holes.

scholarly journals Multi-Fault Diagnosis of Gearbox Based on Improved Multipoint Optimal Minimum Entropy Deconvolution

Entropy ◽  
2018 ◽  
Vol 20 (8) ◽  
pp. 611 ◽  
Author(s):  
Fuhe Yang ◽  
Xingquan Shen ◽  
Zhijian Wang
Keyword(s):  
White Noise ◽  
Signal To Noise Ratio ◽  
Ensemble Empirical Mode Decomposition ◽  
Original Signal ◽  
Intrinsic Mode Functions ◽  
Minimum Entropy ◽  
Feature Extraction Method ◽  
Mode Decomposition ◽  
Fault Features ◽  
Selection Of

Under complicated conditions, the extraction of a multi-fault in gearboxes is difficult to achieve. Due to improper selection of methods, leakage diagnosis or misdiagnosis will usually occur. Ensemble Empirical Mode Decomposition (EEMD) often causes energy leakage due to improper selection of white noise during signal decomposition. Considering that only a single fault cycle can be extracted when MOMED (Multipoint Optimal Minimum Entropy Deconvolution) is used, it is necessary to perform the sub-band processing of the compound fault signal. This paper presents an adaptive gearbox multi-fault-feature extraction method based on Improved MOMED (IMOMED). Firstly, EEMD decomposes the signal adaptively and selects the intrinsic mode functions with strong correlation with the original signal to perform FFT (Fast Fourier transform); considering the mode-mixing phenomenon of EEMD, reconstruct the intrinsic mode functions with the same timescale, and obtain several intrinsic mode functions of the same scale to improve the entropy of fault features. There is a lot of white noise in the original signal, and EEMD can improve the signal-to-noise ratio of the original signal. Finally, through the setting of different noise-reduction intervals to extract fault features through MOMED. The proposed method is compared with EEMD and VMD (Variational Mode Decomposition) to verify its feasibility.

scholarly journals Extraction method of weak underwater acoustic signal based on the combination of wavelet transform and empirical mode decomposition

2021 ◽  
Vol 12 ◽  
pp. 7
Author(s):  
Junbing Shi ◽  
Yingmin Wang ◽  
Xiaoyong Zhang ◽  
Libo Yang
Keyword(s):  
Wavelet Transform ◽  
Empirical Mode Decomposition ◽  
Signal To Noise Ratio ◽  
Intrinsic Mode Functions ◽  
Threshold Method ◽  
Underwater Acoustic ◽  
Baseline Drift ◽  
Mode Decomposition ◽  
Empirical Mode Decomposition Method ◽  
Combined Algorithm

When studying underwater acoustic exploration, tracking and positioning, the target signals collected by hydrophones are often submerged in strong intermittent noise and environmental noise. In this paper, an algorithm that combines empirical mode decomposition and wavelet transform is proposed to achieve the efficient extraction of target signals in the environment with strong noise. First the calibration of baseline drift is performed on the algorithm, and then it is decomposed into different intrinsic mode functions via empirical mode. The wavelet threshold processing is conducted according to the correlation coefficient of each mode component and the original signal, and finally the signals are reconstructed. The simulation and experiment results show that compared with the conventional empirical mode decomposition method and wavelet threshold method, when the signal-to-noise ratio is low and there exist high-frequency intermittent jamming and baseline drift, the combined algorithm can better extract the target signal, laying the foundation for direction-of-arrival estimation and target positioning in the next step.

scholarly journals Removal of Baseline Wander from Electrocardiogram using Ensemble Empirical Mode Decomposition and Low Pass Filter

2019 ◽  
Vol 8 (4) ◽  
pp. 2771-2774
Keyword(s):  
Empirical Mode Decomposition ◽  
Human Heart ◽  
Signal To Noise Ratio ◽  
Normal Sinus Rhythm ◽  
Ensemble Empirical Mode Decomposition ◽  
Comparative Performance ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Mode Decomposition ◽  
Baseline Wander

Electrocardiogram (ECG) is a graphical visualization of the electrical activity of human heart. The biomedical signal, such as ECG, has a major issue of separating the pure signal from artifacts due to baseline wander (BW), electrode artifacts, muscle artifacts, and power-line interference. Reduction of these artifacts is vital for clinical purposes for diagnosis and interpretation of the human heart condition. This paper presents removal of BW from ECG using ensemble empirical mode decomposition (EMD) with multiband filtering approach. A comparative performance analysis of EMD and ensemble EMD for synthetic as well as real BW on normal sinus rhythm and arrhythmia ECG signal are presented. This method can remove the BW in different inherent signal to noise ratio (SNR) including negative and positive as well. This method shows that quantitative and qualitative results with miniscule signal distortion via experiments on several ECG records.

scholarly journals Short-Range Vital Signs Sensing Based on EEMD and CWT Using IR-UWB Radar

2016 ◽  
Author(s):  
Xikun Hu ◽  
Tian Jin
Keyword(s):  
Doppler Radar ◽  
Signal To Noise Ratio ◽  
Vital Signs ◽  
Ensemble Empirical Mode Decomposition ◽  
The Body ◽  
Ultra Wideband ◽  
Detection Range ◽  
Wall Movement ◽  
Uwb Radar ◽  
Mode Decomposition

The radar sensor described realizes healthcare monitoring capable of detecting subject chest-wall movement caused by cardiopulmonary activities, and wirelessly estimating the respiration and heartbeat rates of the subject without attaching any devices to the body. Conventional single-tone Doppler radar can only capture Doppler signatures because of a lack of bandwidth information with noncontact sensors. In contrast, we take full advantage of impulse radio ultra-wideband (IR-UWB) radar to achieve low power consumption and convenient portability, with a flexible detection range and desirable accuracy. A noise reduction method based on improved ensemble empirical mode decomposition (EEMD) and a vital sign separation method based on the continuous-wavelet transform (CWT) are proposed jointly to improve the signal-to-noise ratio (SNR) in order to acquire accurate respiration and heartbeat rates. Experimental results illustrate that respiration and heartbeat signals can be extracted accurately under different conditions. This noncontact healthcare sensor system proves the commercial feasibility and considerable accessibility of using compact IR-UWB radar for emerging biomedical applications.

Sign in / Sign up

Export Citation Format

Share Document