Signal Denoising Research Articles

Application of translation wavelet transform with new threshold function in pulse wave signal denoising.

The wrist pulse wave under the optimal pulse pressure plays an important role in detecting human body's physiological and pathological information. Wavelet threshold filtering is a common method for pulse wave de-noising. However, traditional filtering methods cannot smoothen the whole pulse wave well and highlight the details. In view of this, an attempt is made in this paper to propose the pulse wave denoising algorithm for pulse wave under optimal pulse pressure according to the translation invariant wavelet transform (TIWT) and the new threshold function. Firstly, by using hyperbolic tangent curve and combining the advantages of soft threshold function and hard threshold function, the new threshold function is derived. Secondly, based on the TIWT, pseudo-Gibbs phenomenon gets suppressed. The experiments show that in comparison to the traditional wavelet filtering algorithm, the novel algorithm can better maintain the pulse wave geometric characteristics and has a higher signal to noise ratio (SNR). The TIWT with improved new threshold compensates the shortcomings of the traditional wavelet threshold denoising methods in a better way. It lays a foundation for extracting time-domain characteristics of pulse wave.

Deep learning seismic damage assessment with embedded signal denoising considering three-dimensional time–frequency feature correlation

Fast and accurate seismic damage assessment is crucial for timely post-earthquake evaluation and rescue. In seismic damage assessment, the correlation between ground motions in three directions during the time–frequency transform and the appropriate denoising thresholds during signal data preprocessing pose challenges for traditional methods. We propose a novel deep learning framework, DRSNet (deep residual shrinkage network), which incorporates the CNN structure of ResNet and a soft-threshold denoising module for simultaneous seismic signal denoising and damage assessment. To consider the feature correlation in time–frequency transform of seismic signals, they are first decomposed synchronously with noise-assisted multivariate empirical mode decomposition (NAMEMD) into multi-dimensional intrinsic mode functions (MIMF), and MIMFs are then transformed into seismic time–frequency maps using a non-parametric time–frequency analysis with scalable time windows and the Duhamel integral form. The subsidence and the subsidence rate of the dam are computed with finite element analysis and considered to assess seismic damage. The time–frequency maps and the finite element analysis results are used as input and output data to train DRSNet with no need for preprocessing seismic signal noise. The proposed model has been applied to a large-scale hydropower dam and achieved an average precision of 94.52% for predicting the seismic damage levels, which outperforms ResNet and ResNeSt by 3.09% and 2.62%, respectively. Thorough comparison and analysis of the model demonstrate its potential for accurate and efficient seismic damage assessment.

Parallel learning attention-guided CNN for signal denoising and mechanical fault diagnosis

Parallel learning attention-guided CNN for signal denoising and mechanical fault diagnosis

3-D-Curved Iontronic Tactile Sensor and Denoising Method for Physical Human–Robot Interactions

Tactile information is essential for safe physical interactions between humans and robots. However, for all kinds of tactile sensing principles, it is still challenging to monitor contact status during physical human–robot interactions (pHRIs) on 3-D irregular surfaces due to complex tactile sensor design and signal denoising. This study developed a robotic tactile sensing system by introducing the iontronic electric double-layer capacitor (EDLC) supercapacitive principle, covering a large area ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$191\times191$ </tex-math></inline-formula> mm), and ensuring a dense spatial resolution by using 1024 sensing units. A special grounding strategy and a spatio-temporal (S-T) digital filter significantly reduced the crosstalk interference resulting from low ionic mobility and lateral migration. Additionally, based on surface flattening technology, a 3-D-curved tactile sensor is presented for tactile sensing of a humanoid lower limb’s foot. Finally, response tests based on human actions were performed by the two kinds of robots. Results showed that the system could rapidly capture the entire dynamic process of pHRI actions and distinguish actions in real-time. This study enables the possibility of tactile sensing with whole-body coverage, rapid responses, and tactile-based robotic intelligence.

An Ice-Penetrating Signal Denoising Method Based on WOA-VMD-BD

Chang’E-7 will be launched around 2026 to explore resources at the lunar south pole. Glaciers are suitable scenes on the earth for lunar penetrating radar verification. In the verification experiment, ice-penetrating signals are inevitably polluted by noise, affecting the accuracy and reliability of glacier detection. This paper proposes a denoising method for ice-penetrating signals based on the combination of whale optimization algorithm (WOA), variational mode decomposition (VMD), and the improved Bhattacharyya distance (BD). Firstly, a fitness function for WOA is established based on permutation entropy (PE), and the number of decomposition modes K and the quadratic penalty factor α in the VMD are optimized using WOA. Then, VMD is performed on the signal to obtain multiple intrinsic mode functions (IMFs). Finally, according to the BD, the relevant IMFs are selected for signal reconstruction and denoising. The simulation results indicate the strengths of this method in enhancing the signal-to-noise ratio (SNR), and its performance is better than empirical mode decomposition (EMD). Experiments on the detected signals of the Mengke Glacier No. 29 indicate that the WOA-VMD-BD method can efficiently eliminate noise from the data and procure well-defined layered profiles of the glacier. The research in this paper helps observe the layered details of the lunar regolith profile and interpret the data in subsequent space exploration missions.

Application Research of Negative Pressure Wave Signal Denoising Method Based on VMD

The quality of pipeline leakage fault feature extractions deteriorates due to the influence of fluid pipeline running state and signal acquisition equipment. The pressure signal is characterized by high complexity, nonlinear and strong correlation. Therefore, traditional denoising methods have difficulty dealing with this kind of signal. In order to realize accurate leakage fault alarm and leak location, a denoising method based on variational mode decomposition (VMD) technology is proposed in this paper. Firstly, the intrinsic mode functions are screened out using the correlation coefficient. Secondly, information entropy is used to optimize the VMD decomposition layers k. Finally, based on the denoising signal, the inflection point of the negative pressure wave is extracted, and the position of the leakage point is calculated according to the time difference between the two inflection points. To verify the effectiveness of the algorithm, both laboratory experiments and real pipeline tests are conducted. Experimental results show that the method proposed by this paper can be used to effectively denoise the pressure signal. Furthermore, from the perspective of positioning accuracy, compared other methods, the proposed method can achieve a better positioning effect, as the positioning accuracy of the laboratory experiment reaches up to 0.9%, and that of the real pipeline test leakage point reaches up to 0.41%.

Cycle kurtosis entropy guided symplectic geometry mode decomposition for detecting faults in rotating machinery

Strong noise interference or compound fault coupling phenomenon may lead to the failure of fault diagnosis technology. This paper focuses on weak feature extraction and compound faults detection for rotating machinery fault diagnosis and proposes adaptive symplectic geometric mode decomposition (SGMD) using cycle kurtosis entropy. Firstly, an index named cycle kurtosis entropy (CKE) is presented to measure the strength of periodic impulses in a signal. The CKE uses the entropy value of calculating all delay cycle kurtosis (CK) to overcome the shortcomings of the CK in adaptive ability and obtain more stable values. Thirdly, CKE is applied to construct an adaptive slip window with optimal length. This process is called the adaptive window segmentation method, which is mainly used to dig out weak fault features in signals. Finally, CKE is used as the component selection criterion to select the components decomposed by SGMD. The selected components are reconstructed to obtain a de-noised signal. Hilbert envelope analysis is applied to the denoised signal to demodulate the fault characteristic frequency. Numerical simulations and experimental investigations using bearings and gears are performed to testify the property of the presented method. The results indicate that the adaptive slip window can enhance the decomposing ability of SGMD under strong noise condition. Moreover, for the strong periodic impulse identification ability, the cycle kurtosis entropy is suitable to determine the optimal components of SGMD. It is expected that the presented method will be effectively used for fault feature extractions in rotating machinery under stationary running conditions.

Behavior and Task Classification Using Wearable Sensor Data: A Study across Different Ages.

In this paper, we face the problem of task classification starting from physiological signals acquired using wearable sensors with experiments in a controlled environment, designed to consider two different age populations: young adults and older adults. Two different scenarios are considered. In the first one, subjects are involved in different cognitive load tasks, while in the second one, space varying conditions are considered, and subjects interact with the environment, changing the walking conditions and avoiding collision with obstacles. Here, we demonstrate that it is possible not only to define classifiers that rely on physiological signals to predict tasks that imply different cognitive loads, but it is also possible to classify both the population group age and the performed task. The whole workflow of data collection and analysis, starting from the experimental protocol, data acquisition, signal denoising, normalization with respect to subject variability, feature extraction and classification is described here. The dataset collected with the experiments together with the codes to extract the features of the physiological signals are made available for the research community.

Denoising ECG Signal Using DWT with EAVO

Cardiovascular diseases are the leading cause of death across the world, and traditional methods for determining cardiac health are highly invasive and expensive. Detecting CVDs early is critical for effective treatment, yet traditional detection methods lack accessibility, accuracy, and cost-effectiveness – leaving patients with little hope of taking control of their own cardiac health. Noisy ECG signals make it difficult for health practitioners to accurately read and determine heart health. Unreliable readings can lead to misdiagnosis and needless expense. Despite the importance of ECG analysis, traditional methods of signal denoising are inefficient and can produce inaccurate results. This means that medical practitioners are struggling to obtain reliable readings, leaving them unable to accurately treat their patients and leading to a lack of confidence in the medical field. The Enhanced African Vulture Optimization (AVO) algorithm with Discrete Wavelet Transform (DWT) optimized by adaptive switching mean filtration (SMF) is proven to provide accurate denoising of the ECG signal. With this reliable method, medical professionals can quickly and accurately diagnose patients. Obtaining accurate ECG signals and interpreting them quickly is a challenge for healthcare professionals. Not only it takes a lot of time and skill but also requires specialized software to interpret the signals accurately. Healthcare professionals are facing a serious challenge when it comes to obtaining accurate ECG signals and interpreting them quickly. It requires them to spend extra time and effort, as well as specialize in the field with expensive software. Time is of the essence in healthcare and ECG readings can mean the difference between life and death. Specialized software can be expensive and time-consuming for those who don't have the resources or expertise. Our easy-to-use platform allows healthcare professionals to quickly interpret ECG signals, saving time, money, and lives! Get accurate readings. The EAVO algorithm and MIT-BIH dataset provide an effective solution to this problem. With the proposed filter built using EAVO, businesses can attain significant enhancements in reliable parameters and obtain accurate testing results in terms of SNR, MD, MSE and NRMSE.

Artificial Intelligence Applications for MEMS-Based Sensors and Manufacturing Process Optimization

Micro-electromechanical systems (MEMS) technology-based sensors have found diverse fields of application due to the advancement in semiconductor manufacturing technology, which produces sensitive, low-cost, and powerful sensors. Due to the fabrication of different electrical and mechanical components on a single chip and complex process steps, MEMS sensors are prone to deterministic and random errors. Thus, testing, calibration, and quality control have become obligatory to maintain the quality and reliability of the sensors. This is where Artificial Intelligence (AI) can provide significant benefits, such as handling complex data, performing root cause analysis, efficient feature estimation, process optimization, product improvement, time-saving, automation, fault diagnosis and detection, drift compensation, signal de-noising, etc. Despite several benefits, the embodiment of AI poses multiple challenges. This review paper provides a systematic, in-depth analysis of AI applications in the MEMS-based sensors field for both the product and the system level adaptability by analyzing more than 100 articles. This paper summarizes the state-of-the-art, current trends of AI applications in MEMS sensors and outlines the challenges of AI incorporation in an industrial setting to improve manufacturing processes. Finally, we reflect upon all the findings based on the three proposed research questions to discover the future research scope.

High-Accuracy Spectral Measurement of Stimulated-Brillouin-Scattering Lidar Based on Hessian Matrix and Steger Algorithm

The measurement accuracy of Brillouin scattering spectra is crucial for ocean remote sensing by Brillouin scattering lidar. Due to the limited resolution of ICCD cameras, the traditional processing methods remain at the pixel or partial sub-pixel level, which cannot meet the requirements of high-performance lidar. In this paper, to extract the frequency shift with high precision from stimulated Brillouin scattering (SBS) lidar, a novel spectral processing method with sub-pixel recognition accuracy is proposed based on the Hessian matrix and Steger algorithm combined with the least square fitting method. Firstly, the Hessian matrix and Frangi filter are used for signal denoising. Then, the center points of SBS spectra at the sub-pixel level are extracted using the Steger algorithm and are connected and classified according to the signal type. On that basis, the frequency shifts of Brillouin scattering are calculated by using the center and radii of interference spectra after through fitting by the least squares method. Finally, the water temperatures are inverted by using the frequency shifts of Brillouin scattering. The results show that the processing method proposed in this paper can accurately calculate the frequency shift of Brillouin scattering. The measured errors of frequency shift are generally at an order of MHz, and the inversion accuracy of water temperature can be as low as 0.14 °C. This work is essential to the application for remote sensing the seawater parameters by using the Brillouin lidar technique.

A new rainfall prediction model based on ICEEMDAN-WSD-BiLSTM and ESN.

Precipitation, as an important indicator describing the evolution of the regional climate system, plays an important role in understanding the spatial and temporal distribution characteristics of regional precipitation. Scientific and accurate prediction of regional precipitation is helpful to provide theoretical basis for relevant departments to guide flood and drought control. To address the uncertainty and nonlinear characteristics of precipitation series, this paper uses the established improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN)-wavelet signal denoising (WSD)-bi-directional long short-term memory (BiLSTM), and echo state network (ESN) models to predict precipitation of four cities in southern Anhui Province. The BiLSTM is used to predict the high-frequency components and the ESN to predict the low-frequency components, thus avoiding the influence between the two neural network predictions. The results show that the ICEEMDAN-WSD-BiLSTM and ESN models are more accurate. The average relative error reached 2.64% and the NSE (Nash-Sutcliffe efficiency coefficient) was 0.91, which was significantly better than the other four models. The model reveals the temporal change pattern and evolution characteristics of future precipitation, guides flood prevention and mitigation, and has certain theoretical significance and application value for promoting regional sustainable development.

EEG-based driver states discrimination by noise fraction analysis and novel clustering algorithm.

Driver states are reported as one of the principal factors in driving safety. Distinguishing the driving driver state based on the artifact-free electroencephalogram (EEG) signal is an effective means, but redundant information and noise will inevitably reduce the signal-to-noise ratio of the EEG signal. This study proposes a method to automatically remove electrooculography (EOG) artifacts by noise fraction analysis. Specifically, multi-channel EEG recordings are collected after the driver experiences a long time driving and after a certain period of rest respectively. Noise fraction analysis is then applied to remove EOG artifacts by separating the multichannel EEG into components by optimizing the signal-to-noise quotient. The representation of data characteristics of the EEG after denoising is found in the Fisher ratio space. Additionally, a novel clustering algorithm is designed to identify denoising EEG by combining cluster ensemble and probability mixture model (CEPM). The EEG mapping plot is used to illustrate the effectiveness and efficiency of noise fraction analysis on the denoising of EEG signals. Adjusted rand index (ARI) and accuracy (ACC) are used to demonstrate clustering performance and precision. The results showed that the noise artifacts in the EEG were removed and the clustering accuracy of all participants was above 90%, resulting in a high driver fatigue recognition rate.

An Improved Microseismic Signal Denoising Method of Rock Failure for Deeply Buried Energy Exploration

Microseismic monitoring has become a well-known technique for predicting the mechanisms of rock failure in deeply buried energy exploration, in which noise has a great influence on microseismic monitoring results. We proposed an improved microseismic denoising method based on different wavelet coefficients of useful signal and noise components. First, according to the selection of an appropriate wavelet threshold and threshold function, the useful signal part of original microseismic signal was decomposed many times and reconstructed to achieve denoising. Subsequently, synthetic signals of different types (microseismic noise, microseismic current, microseismic noise current) and with various signal-to-noise ratios (SNRs, −10~10) were used as test data. Evaluation indicators (mean absolute error μ and standard deviation error σ) were established to compare the denoising effect of different denoising methods and verify that the improved method is more effective than the traditional denoising methods (wavelet global threshold, empirical mode decomposition and wavelet transform–empirical mode decomposition). Finally, the proposed method was applied to actual field microseismic data. The results showed that the microseismic signal (with different types of noise) could be fully denoised (car honk, knock, current and construction noise, etc.) without losing useful signals (pure microseismic), suggesting that the proposed approach provides a good basis for the subsequent evaluation and classification of rock burst disasters.

Parallel Processing Method for Microseismic Signal Based on Deep Neural Network

The microseismic signals released by rock mass fracture can be captured via microseismic monitoring to evaluate the development of geological disasters. This is crucial for underground engineering construction, underground mining, and earthquake and geological disaster evaluation. However, extracting information effectively is difficult due to the low signal-to-noise ratio of microseismic signals caused by complex environmental factors. Therefore, denoising and detection (onset time picking) are essential to processing microseismic signals and extracting source information. To improve the efficiency and accuracy of microseismic signal processing, we propose a parallel dual-tasking network, which is an advanced deep learning model that can simultaneously perform microseismic denoising and detection tasks. The network, comprising one encoder and two parallel decoders, is customised to extract input data features, and two outputs can be simultaneously generated to denoise and detect microseismic signals. The model exhibits excellent denoising and detection performance for microseismic signals containing various types of noise. Compared with traditional methods, the signal-to-noise ratio of the denoised signal is greatly improved, and the waveform distortion of the denoised signal is small. Even when the signal-to-noise ratio is low, the proposed model can maintain good onset time pickup performance. This method obviates the need for different denoising methods for different types of noise and precludes setting thresholds artificially to improve the denoising effect and detection accuracy. Moreover, the dual processing characteristics of the model facilitate simultaneous denoising and detection, which improves the processing efficiency of microseismic data and meets the demand for automatically processing massive microseismic data. Therefore, this method has excellent data processing potential in exploration seismology, and earthquake and disaster assessment.

Motor imagery classification method based on relative wavelet packet entropy brain network and improved lasso.

Motor imagery (MI) electroencephalogram (EEG) signals have a low signal-to-noise ratio, which brings challenges in feature extraction and feature selection with high classification accuracy. In this study, we proposed an approach that combined an improved lasso with relief-f to extract the wavelet packet entropy features and the topological features of the brain function network. For signal denoising and channel filtering, raw MI EEG was filtered based on an R2 map, and then the wavelet soft threshold and one-to-one multi-class score common spatial pattern algorithms were used. Subsequently, the relative wavelet packet entropy and corresponding topological features of the brain network were extracted. After feature fusion, mutcorLasso and the relief-f method were applied for feature selection, followed by three classifiers and an ensemble classifier, respectively. The experiments were conducted on two public EEG datasets (BCI Competition III dataset IIIa and BCI Competition IV dataset IIa) to verify this proposed method. The results showed that the brain network topology features and feature selection methods can retain the information of EEG more effectively and reduce the computational complexity, and the average classification accuracy for both public datasets was above 90%; hence, this algorithms is suitable in MI-BCI and has potential applications in rehabilitation and other fields.

A Fault Feature Extraction Method Based on Improved VMD Multi-Scale Dispersion Entropy and TVD-CYCBD.

In modern industry, due to the poor working environment and the complex working conditions of mechanical equipment, the characteristics of the impact signals caused by faults are often submerged in strong background signals and noises. Therefore, it is difficult to effectivelyextract the fault features. In this paper, a fault feature extraction method based on improved VMD multi-scale dispersion entropy and TVD-CYCBD is proposed. First, the marine predator algorithm (MPA) is used to optimize the modal components and penalty factors in VMD. Second, the optimized VMD is used to model and decompose the fault signal, and then the optimal signal components are filtered according to the combined weight index criteria. Third, TVD is used to denoise the optimal signal components. Finally, CYCBD filters the de-noised signal and then envelope demodulation analysis is carried out. Through the simulation signal experiment and the actual fault signal experiment, the results verified that multiple frequency doubling peaks can be seen from the envelope spectrum, and there is little interference near the peak, which shows the good performance of the method.

Forward-Looking Super-Resolution Imaging Based on Echo Denoising and Noise Weighting at Low SNR

In forward-looking imaging radar sensors, the targets of our focus are typically sparse in comparison to the whole imaging scene, which provides the feasibility of applying compressed sensing (CS) to forward-looking super-resolution imaging. However, sparsity is not satisfied in radar imaging when there is strong noise. This will result in the emergence of false targets and affect imaging results when traditional CS-based approaches are employed directly. In this article, we propose a noise robust imaging method that combines echo denoising and noise weighting to solve this problem. First, the denoised radar echo is generated using a complex variational mode decomposition (CVMD) method. The CVMD method is an extension of variational mode decomposition (VMD), which has been used to the traditional real signal denoising. According to the signal spectrum characteristics, we successfully applied the proposed CVMD method to radar echo denoising. Second, a noise weighting method based on <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${l}_{1}$ </tex-math></inline-formula> -norm is performed to further overcome strong noise. The weight comes from the CVMD denoising process, and it can better distinguish targets from the support area of noise. Lastly, simulated and measured data are utilized to verify the proposed method’s performance.

Acoustic Emission Signal Denoising of Bridge Structures Using SOM Neural Network Machine Learning

Identification of noise signals is one of the most challenging problems in health monitoring of a bridge structure using acoustic emission (AE) monitoring and identification technology. Hardware filtering technology and spatial identification technologies are the most common methods used in identifying signals from the defects of the bridge, which have great limitations due to the presence of environmental noise. Therefore, this paper focuses on the AE noise signal from a bridge in an operation state and other specific loading states, which is diagnosed in the hardware filtering technology, spatial identification, and self-organizing map (SOM) neural network, to obtain the new noise recognition methods. It is found that the first two methods can indeed filter the noise signal, but the filtering rate can only reach about 50%, and can barely filter strong noise signals. The SOM neural network had strong self-recognition ability. The classification accuracy of simulated AE signals is 90% and 100%, respectively. The trained network was used to test 183 sample signals, and the defect signal detection accuracy reached 76% and 78.8%; therefore, the noise signal filtering effect is significantly improved.

Denoising method of machine tool vibration signal based on variational mode decomposition and Whale-Tabu optimization algorithm

The noise from other sources is inevitably mixed in the vibration information of CNC machine tools obtained using the sensors. In this work, a de-noising method based on joint analysis is proposed. The variational mode decomposition (VMD), correlation analysis (CA), and wavelet threshold (WT) denoising are used to denoise the original signal. First, VMD decomposes noisy signals into multiple intrinsic mode functions (IMFs). The penalty factor and decomposition level of VMD parameters are selected by the optimization algorithm by combining the whale optimization algorithm (WOA) and tabu search (TS). The minimum permutation entropy of IMF is used as the fitness function of the proposed fusion algorithm. Then, the IMF is divided into three categories by using the cross-correlation number. They include the pure components, signals containing noise, and complete noise components. Then, the WT method is used to further denoise the signals, and signal reconstruction is performed with the pure component to obtain the denoised signal. This joint analysis denoising method is named TS-WOA-VMD-CA-WT. The simulation results show that the fusion optimization algorithm proposed in this work has better performance as compared to the single optimization algorithm. It performs effectively when applied to the actual machine tool vibration signal denoising. Therefore, the proposed TS-WOA-VMD-CA-WT method is superior to other existing denoising techniques and has good generality, which is expected to be popularized and applied more widely.