Search

Original lidar return signals are covered by high levels of noise that seriously affect the accuracy of subsequent data processing and inversion. Therefore, it is important to separate the effective signal from the returned signal with noise interference. In this paper, an efficient denoising method based on the variational mode decomposition (VMD) algorithm optimized using the global search strategy-based whale algorithm and the total variational stationary wavelet transform (GSWOA-VMD-SWTTV) is proposed, and this method is applied to denoising of lidar return signals. First, the global search strategy-based whale optimization algorithm (GSWOA) is used to acquire the optimal parameters of the VMD algorithm adaptively, and the lidar return signal is then decomposed by global search strategy-based whale optimization algorithm (GSWOA)-VMD. The effective modal components are then determined using the cross-correlation coefficient method from the decomposed modal components, and total variation stationary wavelet denoising is performed on each effective mode. Finally, the effective modes are reconstructed to obtain a clean lidar return signal. Moreover, to provide further verification of the effectiveness of the proposed method, it is compared with the ensemble empirical mode decomposition (EEMD) method, the complete EEMD with adaptive noise (CEEMDAN) method, the singular value decomposition (SVD) method, and the wavelet threshold method under sunny, cloudy, and dusty weather conditions. The experimental results demonstrate the superior noise reduction performance of the proposed algorithm, which can filter out strong noise from the signal while retaining the complete signal details without distortion; additionally, the proposed method has the highest signal-to-noise ratio and lowest mean square error. [ABSTRACT FROM AUTHOR]

In order to improve the energy efficiency of wearable devices, it is necessary to compress and reconstruct the collected electrocardiogram data. The compressed data may be mixed with noise during the transmission process. The denoising-based approximate message passing (AMP) algorithm performs well in reconstructing noisy signals, so the denoising-based AMP algorithm is introduced into electrocardiogram signal reconstruction. The weighted nuclear norm minimization algorithm (WNNM) uses the low-rank characteristics of similar signal blocks for denoising, and averages the signal blocks after lowrank decomposition to obtain the final denoised signal. However, under the influence of noise, there may be errors in searching for similar blocks, resulting in dissimilar signal blocks being grouped together, affecting the denoising effect. Based on this, this paper improves the WNNM algorithm and proposes to use weighted averaging instead of direct averaging for the signal blocks after low-rank decomposition in the denoising process, and validating its effectiveness on electrocardiogram signals. Experimental results demonstrate that the IWNNM-AMP algorithm achieves the best reconstruction performance under different compression ratios and noise conditions, obtaining the lowest PRD and RMSE values. Compared with the WNNM-AMP algorithm, the PRD value is reduced by 0.17~4.56, the P-SNR value is improved by 0.12~2.70. [ABSTRACT FROM AUTHOR]

Diffusion-weighted imaging (DWI) is a magnetic resonance imaging (MRI) technique that provides information about the Brownian motion of water molecules within biological tissues. DWI plays a crucial role in stroke imaging and oncology, but its diagnostic value can be compromised by the inherently low signal-to-noise ratio (SNR). Conventional supervised deep learning-based denoising techniques encounter challenges in this domain as they necessitate noise-free target images for training. This work presents a novel approach for denoising and evaluating DWI scans in a self-supervised manner, eliminating the need for ground-truth data. By leveraging an adapted version of Stein's unbiased risk estimator (SURE) and exploiting a phase-corrected combination of repeated acquisitions, we outperform both state-of-the-art self-supervised denoising methods and conventional non-learning-based approaches. Additionally, we demonstrate the applicability of our proposed approach in accelerating DWI scans by acquiring fewer image repetitions. To evaluate denoising performance, we introduce a self-supervised methodology that relies on analyzing the characteristics of the residual signal removed by the denoising approaches. [ABSTRACT FROM AUTHOR]

The tensor singular value decomposition‐based model has garnered increasing attention in addressing tensor recovery challenges. However, existing tensor recovery methods exhibit certain inherent limitations. Some ignore the simultaneous effects of noise and missing values, while most can't handle higher‐order tensors, which are not reflective of real‐world scenarios. The information redundancy within tensor data often leads to a prevailing low‐rank structure, making low‐rankness a vital prior in the tensor recovery process. To tackle this pressing issue, a robust low‐rank tensor recovery framework is proposed to rehabilitate higher‐order tensors corrupted by sparse noise and missing entries. In the model, the tensor nuclear norm derived for order‐d tensors (d≥$\ge$ 4) are employed as a representation of the low‐rank prior, while utilizing the L1$\mathtt {L}_1$‐norm to model the sparse noise. To solve the proposed model, an efficient Alternating direction method of multipliers algorithm is developed. A series of experiments are performed on synthetic and real‐world datasets. The results show that the superior performance of the method compared with other algorithms dedicated to addressing order‐d tensor recovery challenges. Notably, in scenarios where the data is severely compromised (noise ratio 40%, sample ratio 70%), the algorithm consistently outperforms its competitors, achieving significantly improved results. [ABSTRACT FROM AUTHOR]

Learning-based denoising techniques have become superior to the traditional assumption-based denoising methods in this modern era. Also, with the advancement of wearable technologies and remote electrocardiogram (ECG) monitoring systems, the requirement for optimal storage has increased due to the limited availability of hardware resources. Therefore, denoising and compression both are essential at the preprocessing stage of the ECG signal. Deep learning-based denoising auto encoder-decoder (DAED) models guarantee cutting-edge performance for these tasks. This article presents a lightweight, adaptive, hybrid Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) based DAED model that achieves a signal compression ratio of 64 with high signal-to-noise ratio improvement for the elimination of ECG noises. The novelty of this work lies in the customization of the CNN layers and utilization of the advantages of the GRU layer in a proper channel for compression and denoising ECG signals. The comparative study with other complex deep learning-based DAED arrangements and state-of-the-art denoising techniques shows the proposed model has simplicity in construction and an improved signal-to-noise ratio with minimum mean square error. [ABSTRACT FROM AUTHOR]

Objectives: In order to effectively filter out complex noise components in GNSS coordinate time series and extract effective signals, we construct a denoising method based on parameter-optimized variational modal decomposition (VMD). Methods: First, the combination of permutation entropy and mutual information is used as fitness function, and the optimal parameter combination of the mode decomposition number K and the quadratic penalty factor α of VMD is obtained by using grey wolf optimization algorithm (GWO). Then the GNSS coordinate time series is decomposed into K eigen mode function components by VMD. Finally, the sample entropy is used to determine the effective modal component, which is reconstructed as an effective signal, so as to realize the effective separation of signal and noise.The GWO-VMD method is compared and analyzed with the empirical mode decomposition (EMD), wavelet denoising (WD) and IVMD methods by using the simulated signal and the measured data from 20 reference stations of the crustal movement observation network of China for experiments. Results: The simulated signal experiments show that the three denoising evaluation indexes of root mean square error,correlation coefficient and signal-to-noise ratio of GWO-VMD denoising signal are better than EMD, WD and IVMD methods. The experiments on the measured data show that the GWO-VMD method can reduce the amplitude of noise significantly. In terms of the velocity uncertainty of the reference station, the overall GWO-VMD method reduces the velocity uncertainty better than the EMD, WD and IVMD methods. Conclusions: The GWOVMD method can more effectively remove the noise from GNSS coordinate time series and better preserve the original characteristics of the signal, which can provide reliable data for subsequent analysis and processing. [ABSTRACT FROM AUTHOR]

Deep-learning robust feature learning ability makes it a valuable tool for automatic fault detection of rolling bearings in Industry 4.0. This work presents a novel approach for classifying faults in rolling bearings under highly noisy conditions using a deep learning algorithm. The proposed methodology utilizes a double modes decomposition method, specifically the complete ensemble empirical mode decomposition (CEEMD) and variational mode decomposition (VMD) techniques for signal denoising. The novelty of this study lies in its utilization of a double decomposition method, coupled with the selection of dominant intrinsic mode functions (IMFs), followed by continuous wavelet analysis (CWT) to generate magnitude scalogram images for input into a VGG16 deep learning architecture. First, bearing vibration signals are mixed with white Gaussian noise to simulate noisy real-world conditions. The noisy signal is then decomposed into intrinsic mode functions (IMFs) using the CEEMD technique, and a dominant IMF is selected based on its permutation entropy and correlation coefficient values. This dominant IMF is further decomposed into another set of IMFs using the VMD technique to obtain a final dominant IMF based on its CC value. After that, continuous wavelet analysis (CWT) is performed on selected IMF to obtain magnitude scalogram images, and these images are fed into VGG16 deep learning architecture for bearing fault classifications. The results obtained after applying the proposed methodology to the standard bearing dataset suggest that CEEMD-VMD-IMF with magnitude scalogram images perform well with deep learning technique and achieve a bearing fault classification accuracy above 99 % in extremely noisy conditions. [ABSTRACT FROM AUTHOR]

Performing reliable calculations of power system dynamics requires accurate models of generating units. To be able to determine the parameters of the models with the required precision, a well-defined testing procedure is used to record various unit transient signals. Unfortunately, the recorded signals usually contain discontinuities, which complicates the removal of the existing harmonic interferences and noise. A set of four transient signals recorded during typical disturbance tests of a 200 MW power-generating unit was used as both training and research material for the signal denoising/interference removal methods compared in the paper. A systematic analysis of the measured transient signals was conducted, leading to the creation of a coherent mathematical model of the signals. Next, a method for denoising power-generating unit transient signals is proposed. The method is based on Sparsity-Assisted Signal Smoothing (SASS) combined with optimization algorithms (simulated annealing and Nelder-Mead simplex) and is called an optimal SASS method. The proposed optimal SASS method is compared to its direct Linear Time-Invariant (LTI) competitors, such as low-pass and notch filters. The LTI methods are based on the same filter types (Butterworth filters) and zero-phase filtering principle as the SASS method. A set of specially generated test signals (based on a developed mathematical model of the signals) is used for the performance evaluation of all presented filtering methods. Finally, it is concluded that—for the considered class of signals—the optimal SASS method might be a valuable noise removal technique. [ABSTRACT FROM AUTHOR]

Fetal heart monitoring, as a crucial part of fetal monitoring, can accurately reflect the fetus's health status in a timely manner. To address the issues of high computational cost, inability to observe fetal heart morphology, and insufficient accuracy associated with the traditional method of calculating the fetal heart rate using a four-channel maternal electrocardiogram (ECG), a method for extracting fetal QRS complexes from a single-channel non-invasive fetal ECG based on a multi-feature fusion neural network is proposed. Firstly, a signal entropy data quality detection algorithm based on the blind source separation method is designed to select maternal ECG signals that meet the quality requirements from all channel ECG data, followed by data preprocessing operations such as denoising and normalization on the signals. After being segmented by the sliding window method, the maternal ECG signals are calculated as data in four modes: time domain, frequency domain, time–frequency domain, and data eigenvalues. Finally, the deep neural network using three multi-feature fusion strategies—feature-level fusion, decision-level fusion, and model-level fusion—achieves the effect of quickly identifying fetal QRS complexes. Among the proposed networks, the one with the best performance has an accuracy of 95.85% and sensitivity of 97%. [ABSTRACT FROM AUTHOR]

Advances in AI techniques have fueled research on using EEG data for psychiatric disorder diagnosis. Despite EEG's cost-effectiveness and high temporal resolution, low Signal-to-Noise Ratio (SNR) hampers critical marker extraction and model improvement, while denoising techniques will lead to a loss of effective information in EEG. The aim of this study is to employ AI methods for the processing of raw EEG data. The primary objectives of the processing are twofold: first, to acquire more reliable markers for schizophrenia, and second, to construct a superior automatic classification for schizophrenia. To remove the noises and retain task-related (classification tasks) effective information mostly, we introduce an Effective Information Estimation Framework (EIEF) based on three key principles: the task-centered approach, leveraging 1D-CNNs' test metrics to gauge effective information proportion, and feedback. We address a theoretical foundation by integrating these principles into mathematical derivations to propose the mathematical model of EIEF. In experiments, we established a paradigm pool of 66 denoising paradigms, with EIEF successfully identifying the optimal paradigms (on two datasets) for restoring effective information. Utilizing the processed dataset, we trained a 3D-CNN for automatic schizophrenia diagnosis, achieving outstanding test accuracies of 99.94 % on dataset 1 and 98.02 % on dataset 2 in subject-dependent evaluations, and accuracies of 89.85 % on dataset 1 and 98.02 % on dataset 2 in subject-independent evaluations. Additionally, we extracted 38 features from each channel of both processed and raw datasets, revealing that 20.86 % (dataset 1) of feature distribution differences between the patients and the healthy exhibited significant changes after implementing the optimal paradigm. We enhance model performance and extract more reliable electrobiological markers. These findings have promising implications for advancing the field of the clinical diagnosis and pathological analysis of Schizophrenia. [ABSTRACT FROM AUTHOR]

The denoising of microseismic signals is a prerequisite for subsequent analysis and research. In this research, a new microseismic signal denoising algorithm called the Black Widow Optimization Algorithm (BWOA) optimized Variational Mode Decomposition (VMD) joint Wavelet Threshold Denoising (WTD) algorithm (BVW) is proposed. The BVW algorithm integrates VMD and WTD, both of which are optimized by BWOA. Specifically, this algorithm utilizes VMD to decompose the microseismic signal to be denoised into several Band-Limited Intrinsic Mode Functions (BLIMFs). Subsequently, these BLIMFs whose correlation coefficients with the microseismic signal to be denoised are higher than a threshold are selected as the effective mode functions, and the effective mode functions are denoised using WTD to filter out the residual low- and intermediate-frequency noise. Finally, the denoised microseismic signal is obtained through reconstruction. The ideal values of VMD parameters and WTD parameters are acquired by searching with BWOA to achieve the best VMD decomposition performance and solve the problem of relying on experience and requiring a large workload in the application of the WTD algorithm. The outcomes of simulated experiments indicate that this algorithm is capable of achieving good denoising performance under noise of different intensities, and the denoising performance is significantly better than the commonly used VMD and Empirical Mode Decomposition (EMD) algorithms. The BVW algorithm is more efficient in filtering noise, the waveform after denoising is smoother, the amplitude of the waveform is the closest to the original signal, and the signal-to-noise ratio (SNR) and the root mean square error after denoising are more satisfying. The case based on Fankou Lead-Zinc Mine shows that for microseismic signals with different intensities of noise monitored on-site, compared with VMD and EMD, the BVW algorithm is more efficient in filtering noise, and the SNR after denoising is higher. [ABSTRACT FROM AUTHOR]

This paper presents a novel ultrasonic signal denoising method that integrates adaptive variational mode decomposition (AVMD) with convolutional neural networks (CNNs). Initially, the whale optimisation algorithm (WOA) is employed to optimise key parameters of variational mode decomposition, specifically the decomposition modes K and the penalty factor α. The ultrasonic signals are then decomposed into intrinsic mode functions (IMFs) and various statistical feature parameters, such as energy entropy, sample entropy, kurtosis and correlation factors, are calculated for each IMF. The signal-to-noise ratio (SNR) of the reconstructed signal from the IMFs is used to assign label values, forming a feature dataset. Subsequently, a CNN is utilised to train and recognise this dataset, achieving an accuracy rate of 93.94% on the test set. The results demonstrate that the CNN effectively distinguishes between various IMF combinations based on the reconstructed SNR and can proficiently identify IMF combinations with higher SNR. Finally, denoising experiments on actual ultrasonic echo signals validate the feasibility of this method for noise reduction applications. [ABSTRACT FROM AUTHOR]

Estimating the line spectra of ship-radiated noise is a crucial remote sensing technique for detecting and recognizing underwater acoustic targets. Improving the signal-to-noise ratio (SNR) makes the low-frequency components of the target signal more prominent. This enhancement aids in the detection of underwater acoustic signals using sonar. Based on the characteristics of low-frequency narrow-band line spectra signals in underwater target radiated noise, we propose a dual-stream deep learning network with frequency characteristics transformation (DS_FCTNet) for line spectra estimation. The dual streams predict amplitude and phase masks separately and use an information exchange module to swap learn features between the amplitude and phase spectra, aiding in better phase information reconstruction and signal denoising. Additionally, a frequency characteristics transformation module is employed to extract convolutional features between channels, obtaining global correlations of the amplitude spectrum and enhancing the ability to learn target signal features. Through experimental analysis on ShipsEar, a dataset of underwater acoustic signals by hydrophones deployed in shallow water, the effectiveness and rationality of different modules within DS_FCTNet are verified.Under low SNR conditions and with unknown ship types, the proposed DS_FCTNet model exhibits the best line spectrum enhancement compared to methods such as SEGAN and DPT_FSNet. Specifically, SDR and SSNR are improved by 14.77 dB and 13.58 dB, respectively, enabling the detection of weaker target signals and laying the foundation for target localization and recognition applications. [ABSTRACT FROM AUTHOR]

Accurately classifying the intra-pulse modulations of radar emitter signals is important for radar systems and can provide necessary information for relevant military command strategy and decision making. As strong additional white Gaussian noise (AWGN) leads to a lower signal-to-noise ratio (SNR) of received signals, which results in a poor classification accuracy on the classification models based on deep neural networks (DNNs), in this paper, we propose an effective denoising method based on a denoising diffusion probabilistic model (DDPM) for increasing the quality of signals. Trained with denoised signals, classification models can classify samples denoised by our method with better accuracy. The experiments based on three DNN classification models using different modal input, with undenoised data, data denoised by the convolutional denoising auto-encoder (CDAE), and our method's denoised data, are conducted with three different conditions. The extensive experimental results indicate that our proposed method could denoise samples with lower values of the SNR, and that it is more effective for increasing the accuracy of DNN classification models for radar emitter signal intra-pulse modulations, where the average accuracy is increased from around 3 to 22 percentage points based on three different conditions. [ABSTRACT FROM AUTHOR]

Dropping the ambient noise from microseismic signals is very important for disaster monitoring such as a rockburst and early warning system using microseismic monitoring techniques in the mine and coal mines. Currently, it is still a challenge to remove high and low-frequency noise simultaneously without losing the useful information of microseismic signal. The aim of this paper is to remove the low-frequency noise contained in microseismic signal effectively, while preserving the useful signal information by using a stochastic approach. We first statistically model the wavelet coefficients in the approximation subband of noisy microseismic signal. In addition, we evaluate qualitatively and quantitatively the fitness of Gauss–Laplace mixture distribution and the statistical modeling of data. Then, we propose a novel denoising algorithm to remove the ambient noise effectively from the noisy microseismic signals in wavelet domain. This algorithm removes the low-frequency noise by using a stochastic approach and the high-frequency noise by using a traditional wavelet thresholding method. The low-frequency noise is removed by using a closed-form shrinkage function based on Gauss–Laplace mixture distribution, while the high-frequency noise is removed by using a threshold function combined with Garrote and hyperbolic threshold functions. Next, we evaluated the ambient denoising performance of our novel denoising algorithm by comparing it with various denoising methods with different test signals. Experimental results show that the ambient denoising performance of the proposed method is better than the other seven existing methods. [ABSTRACT FROM AUTHOR]

Underwater Acoustic signal denoising is encountering high demand due to the extensive use of acoustic in a lot of underwater applications. Underwater acoustic noise (UWAN) has a high effect on the quality of the acoustic signal therefore, it is always preferred to use a de-noising filter to remove it. In this paper, we propose a filter that utilizes a Complex wavelet transform (CWT) to remove UWAN and help improve the signal-to-noise ratio (SNR) of the detected acoustic signal. CWT is nearly shift-invariant and offers a good directionality in contrast to normal wavelet transform (DWT). The proposed method was tested using a real recorded UWAN for three depths from the Tigris River. The proposed method was compared with a more conveniently used discrete wavelet transform. The test included using Two signals: fixed frequency and linear modulation signal. De-noising was performed using a soft thresholding technique based on level-dependent threshold estimation. The proposed method showed supreme performance in terms of SNR and root mean square error (RMSE). When the input signal was 5.9 dB and -13.2 dB for SNR and RMSE respectively, the results were 10.9 dB for SNR and -15.7 dB for RMSE in the case of fixed frequency. [ABSTRACT FROM AUTHOR]

Wavelets transforms are effective mathematical tools useful in compression and denoising of n-D signals. Subjecting a signal to discrete wavelet transforms (DWT) generates approximation and detailed coefficients that are similar to the coefficients generated by passing the signal through lowpass and high pass filters respectively. Multilevel decomposition (filtering) can be carried out which can successively filter the signal at each bandpass. In this work, a normal sinus rhythm ECG signal noised with a sinewave was denoised by DWT using by members of mother wavelets like coiflet, symlet and biorthogonal families. The denoising performance of the wavelets were evaluated by comparing the signal characteristics of the original and the denoised signals. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Education & Science is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This work develops theories and algorithms for computing rank‐revealing QR factorizations (qRRQR) of quaternion matrices. First, by introducing a novel quaternion determinant, a quasi‐Cramer's rule is established to investigate the existence theory of the qRRQR factorization of an m×n$$ m\times n $$ quaternion matrix A$$ \boldsymbol{A} $$. The proposed theory provides a systematic approach for selecting k$$ k $$ linearly independent columns of A$$ \boldsymbol{A} $$ in order to ensure that the resulting diagonal blocks R11$$ {\boldsymbol{R}}_{11} $$, R22$$ {\boldsymbol{R}}_{22} $$ of the R‐factor possess rank revealing properties in both spectral and Frobenius norms. Secondly, by increasing the quaternion determinants of R11$$ {\boldsymbol{R}}_{11} $$ in each iteration by a factor of at least f−1$$ {f}^{-1} $$(0

Summary In wireless communication, impulsive noise often degrades channel quality, which poses challenges for equalizers. Although robust equalization methods offer some effectiveness, the occurrence of impulsive noise after training significantly impacts the symbol error rate (SER). To mitigate this issue, we propose a method that involves denoising the received signal using robust wavelet decomposition before equalization. This approach combines the discrete wavelet transform with median and morphological filters to reduce impulsive noise. A pre‐impulsive noise detection mechanism triggers denoising only when impulsive noise is detected. We evaluate the SER performance of the proposed technique using simulations of a 16‐QAM orthogonal frequency division multiplexing (OFDM) system with kernel interpolation‐based frequency domain equalization (FDE) in a Rayleigh fading channel with impulsive noise. Results show that our approach achieves SER levels comparable to conventional methods in Gaussian noise scenarios, demonstrating its effectiveness in challenging wireless communication environments. The simulation results demonstrate that the proposed technique in non‐Gaussian noise gives the SER on par with the FDE in a Gaussian noise environment. [ABSTRACT FROM AUTHOR]

The phonocardiogram (PCG) is a crucial tool for the early detection, continuous monitoring, accurate diagnosis, and efficient management of cardiovascular diseases. It has the potential to revolutionize cardiovascular care and improve patient outcomes. The PhysioNet/CinC Challenge 2016 database, a large and influential resource, encourages contributions to accurate heart sound state classification (normal versus abnormal), achieving promising benchmark performance (accuracy: 99.80%; sensitivity: 99.70%; specificity: 99.10%; and score: 99.40%). This study reviews recent advances in analytical techniques applied to this database, and 104 publications on PCG signal analysis are retrieved. These techniques encompass heart sound preprocessing, signal segmentation, feature extraction, and heart sound state classification. Specifically, this study summarizes methods such as signal filtering and denoising; heart sound segmentation using hidden Markov models and machine learning; feature extraction in the time, frequency, and time-frequency domains; and state-of-the-art heart sound state recognition techniques. Additionally, it discusses electrocardiogram (ECG) feature extraction and joint PCG and ECG heart sound state recognition. Despite significant technical progress, challenges remain in large-scale high-quality data collection, model interpretability, and generalizability. Future directions include multi-modal signal fusion, standardization and validation, automated interpretation for decision support, real-time monitoring, and longitudinal data analysis. Continued exploration and innovation in heart sound signal analysis are essential for advancing cardiac care, improving patient outcomes, and enhancing user trust and acceptance. [ABSTRACT FROM AUTHOR]

Seismic data acquired in seismic exploration is often contaminated by random noise, and it is necessary to develop effective seismic data denoising methods in seismic signal processing. The current seismic data denoising solutions mainly include traditional model-based methods and supervised deep learning methods. However, the traditional model-based methods cannot achieve satisfactory denoising accuracy, while the supervised deep learning methods have a demand for labeled data, which is difficult to collect in field seismic exploration. To address these difficulties in seismic signal denoising, we proposed an unsupervised deep learning method USDDM (Unsupervised Seismic Denoising Diffusion Model) based on diffusion model. USDDM utilizes the forward process of a diffusion model to assimilate the noise in seismic data, and then the backward process of the diffusion model is used to gradually remove the assimilated noise. Experiments on synthetic and field data are carried out to evaluate the denoising performance of USDDM, model-based methods f-x deconvolution and curvelet, and supervised deep learning methods CAE and DnCNN are used as comparison models. The results of the simulated experiments suggest that the proposed USDDM can effectively reduce the random noise in contaminated seismic data. USDDM can achieve better denoising accuracy compared to f-x deconvolution and curvelet, and the performance between USDDM and supervised deep learning methods is very close. The effectiveness and practicality of USDDM are demonstrated. [ABSTRACT FROM AUTHOR]

The threshing cylinder will wear and deform during the threshing process, causing dynamic balance problems. The combine harvester has multiple vibration excitation sources and a complex vibration environment, making it challenging to extract weak unbalanced signals from strong background noise. A novel three-step filtering framework is proposed in this paper. A zero phase filter was used as the pre-processing layer to filter out the high frequency components in the original signal and reduce the number of parameter-adaptive variational mode decompositions (PAVMD) needed. The PAVMD was used to decompose the non-stationary vibration signal before Adaptive Neuron Linear (Adaline) function was used to fit sinusoidal signal parameters. A measurement index, termed the correlation amplitude (CA) index, is constructed. The parameterisation of PAVMD was guided by the CA index, and the modal component of the unbalanced fault features were located. The simulation and real cylinder signals proved that the proposed method could effectively extract unbalanced signals under noise interference, and the unbalance was identified accurately by the influence coefficient method. Experiments on a threshing cylinder showed that the amplitude identification error was <24 g in single-sided unbalance identification, and the amplitude identification error was <27 g in double-sided unbalance identification. The proposed method had high robustness and small identification error, especially under short-time working conditions, compared with other similar approaches. • Unbalance signal extraction method based on parameter-adaptive VMD was proposed. • It uses a novel three-step filtering framework for signal extraction. • Experiments on threshing cylinder demonstrated the effectiveness and advantages. [ABSTRACT FROM AUTHOR]

Interrupted sampling repeater jamming (ISRJ) with flexible modulation parameters and coherent processing gain seriously threatens the radar detection system. The jamming suppression and target detection performance of existing anti‐jamming methods are limited by strong noise and jamming signals. An ISRJ suppression method combining multiple extended complex‐valued convolutional auto‐encoders (CVCAEs) and compressed sensing (CS) reconstruction is proposed. For the different tasks of parameter estimation and signal denoising, the extended CVCAEs including a complex‐valued convolutional shrinkage network (CVCSNet) and a complex‐valued UNet (CVUNet) are developed. Based on the time‐domain discontinuity of ISRJ signals, the CVCSNet is first used to directly estimate the parameters representing signal components and extract jamming‐free signals from received signals. Then, the extracted signals are denoised using the CVUNet. After that, relying on the denoised signals and the frequency sparsity of de‐chirped target signals, a CS model is established and solved to recover complete target signals for jamming suppression. Utilising the advantages of deep neural networks in weak feature extraction and signal representation, the CVCSNet and CVUNet can effectively improve the signal extraction accuracy and alleviate the limitation of noise on target signal reconstruction. Experimental results verify that the proposed method has superior ISRJ suppression performance and is robust to varying signal‐to‐noise ratios, jamming‐to‐signal ratios and jamming parameters. [ABSTRACT FROM AUTHOR]

Radar High‐Resolution Range Profile (HRRP) has great potential for target recognition because it can provide target structural information. Existing work commonly applies deep learning to extract deep features from HRRPs and achieve impressive recognition performance. However, most approaches are unable to distinguish between the target and non‐target regions in the feature extraction process and do not fully consider the impact of background noise, which is harmful to recognition, especially at low signal‐to‐noise ratios (SNR). To tackle these problems, the authors propose a radar HRRP target recognition framework termed Adaptive Soft Threshold Transformer (ASTT), which is composed of a patch embedding (PE) layer, ASTT blocks, and Discrete Wavelet Patch Merging (DWPM) layers. Given the limited semantic information of individual range cells, the PE layer integrates nearby isolated range cells into semantically explicit target structure patches. Thanks to its convolutional layer and attention mechanism, the ASTT blocks assign a weight to each patch to locate the target areas in the HRRP while capturing local features and constructing sequence correlations. Moreover, the ASTT block efficiently filters noise features in combination with a soft threshold function to further enhance the recognition performance at low SNR, where the threshold is adaptively determined. Utilising the reversibility of the discrete wavelet transform, the DWPM layer efficiently eliminates the loss of valuable information during the pooling process. Experiments based on simulated and measured datasets show that the proposed method has excellent target recognition performance, noise robustness, and small‐scale range shift robustness. [ABSTRACT FROM AUTHOR]

To ensure the reliable operation of high voltage cables, it is crucial to routinely inspect the lead sealing using pulsed eddy current. But nevertheless, the signals can be impacted by noise in actual engineering. While retaining the useful high-frequency information in the original signal, wavelet denoising can filter the clutter efficiently. However, previous research on wavelet denoising has only used it as a straightforward filtering tool, ignoring the impact of changing the parameters on the actual denoising effect. In this study, a more accurate evaluation index called PNCC is constructed for pulsed eddy current testing signals with a focus on maintaining the peak information. This index is then adopted as a fitness function for the particle swarm optimisation algorithm to determine the befitting wavelet denoising parameters and denoised signals. The results show that the signal-to-noise ratio of the signals after denoising is approximately 25 dB, and the distortion at the peak position is stable at about 1%. It demonstrates that the comprehensive index PNCC is a reliable metric for assessing the quality of pulsed eddy current signals. The optimal wavelet denoising parameters for pulsed eddy current signals are found to be the Sym 4 wavelet, 10-layer decomposition and Median threshold function. [ABSTRACT FROM AUTHOR]

In acoustic signal–based natural gas pipeline leak detection, it is a technical difficulty to effectively remove the strong background noise hidden in the acoustic signal. Unfortunately, existing techniques usually study denoising in isolation from the model, and do not consider the synergistic effect of integrating denoising with the model to update filtering parameters adaptively, which limits the performance development of the diagnostic model. To solve this problem, this paper proposes a fault diagnosis method that incorporates acoustic signal hybrid filtering and a one-dimensional convolutional neural network (1D-CNN) to jointly update the denoising parameters. Firstly, the acoustic signal is sampled at a fixed frequency by the sensor unit. Secondly, a hybrid filtering method with low-frequency characteristics is designed, which integrates low-pass filtering and median filtering to eliminate background noise. Finally, an adaptive fault diagnosis network that fuses acoustic signal denoising with 1D-CNN feature extraction is developed. The network updates the filtering parameters during training based on the model recognition accuracy, so that the denoising parameters and model weights change dynamically. The experimental results show that the method is capable of performing adaptive parameter search with 97.07% identification accuracy of fault type. [ABSTRACT FROM AUTHOR]

Esophageal speech (ES) is a pathological voice that is often difficult to understand. Moreover, acquiring recordings of a patient's voice before a laryngectomy proves challenging, thereby complicating enhancing this kind of voice. That is why most supervised methods used to enhance ES are based on voice conversion, which uses healthy speaker targets, things that may not preserve the speaker's identity. Otherwise, unsupervised methods for ES are mostly based on traditional filters, which cannot alone beat this kind of noise, making the denoising process difficult. Also, these methods are known for producing musical artifacts. To address these issues, a self-supervised method based on the Only-Noisy-Training (ONT) model was applied, consisting of denoising a signal without needing a clean target. Four experiments were conducted using Deep Complex UNET (DCUNET) and Deep Complex UNET with Complex Two-Stage Transformer Module (DCUNET-cTSTM) for assessment. Both of these models are based on the ONT approach. Also, for comparison purposes and to calculate the evaluation metrics, the pre-trained VoiceFixer model was used to restore the clean wave files of esophageal speech. Even with the fact that ONT-based methods work better with noisy wave files, the results have proven that ES can be denoised without the need for clean targets, and hence, the speaker's identity is retained. [ABSTRACT FROM AUTHOR]

Abstract The tensor singular value decomposition‐based model has garnered increasing attention in addressing tensor recovery challenges. However, existing tensor recovery methods exhibit certain inherent limitations. Some ignore the simultaneous effects of noise and missing values, while most can't handle higher‐order tensors, which are not reflective of real‐world scenarios. The information redundancy within tensor data often leads to a prevailing low‐rank structure, making low‐rankness a vital prior in the tensor recovery process. To tackle this pressing issue, a robust low‐rank tensor recovery framework is proposed to rehabilitate higher‐order tensors corrupted by sparse noise and missing entries. In the model, the tensor nuclear norm derived for order‐d tensors (d ≥ 4) are employed as a representation of the low‐rank prior, while utilizing the L1‐norm to model the sparse noise. To solve the proposed model, an efficient Alternating direction method of multipliers algorithm is developed. A series of experiments are performed on synthetic and real‐world datasets. The results show that the superior performance of the method compared with other algorithms dedicated to addressing order‐d tensor recovery challenges. Notably, in scenarios where the data is severely compromised (noise ratio 40%, sample ratio 70%), the algorithm consistently outperforms its competitors, achieving significantly improved results.

Abstract Interrupted sampling repeater jamming (ISRJ) with flexible modulation parameters and coherent processing gain seriously threatens the radar detection system. The jamming suppression and target detection performance of existing anti‐jamming methods are limited by strong noise and jamming signals. An ISRJ suppression method combining multiple extended complex‐valued convolutional auto‐encoders (CVCAEs) and compressed sensing (CS) reconstruction is proposed. For the different tasks of parameter estimation and signal denoising, the extended CVCAEs including a complex‐valued convolutional shrinkage network (CVCSNet) and a complex‐valued UNet (CVUNet) are developed. Based on the time‐domain discontinuity of ISRJ signals, the CVCSNet is first used to directly estimate the parameters representing signal components and extract jamming‐free signals from received signals. Then, the extracted signals are denoised using the CVUNet. After that, relying on the denoised signals and the frequency sparsity of de‐chirped target signals, a CS model is established and solved to recover complete target signals for jamming suppression. Utilising the advantages of deep neural networks in weak feature extraction and signal representation, the CVCSNet and CVUNet can effectively improve the signal extraction accuracy and alleviate the limitation of noise on target signal reconstruction. Experimental results verify that the proposed method has superior ISRJ suppression performance and is robust to varying signal‐to‐noise ratios, jamming‐to‐signal ratios and jamming parameters.

Copyright of International Journal of Engineering Transactions C: Aspects is the property of International Journal of Engineering (IJE) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The parameters estimation through bias-to-variance ratio optimization has been suggested for various applications in literature. The explicit values of bias or variance for a "near to optimal" solution are generally not needed. However, the additional noise components vary the bias or variance randomly. This work proposes an adaptive Intersection of Confidence Intervals (ICI)-based method for the mitigation of noise component by balancing bias to variance trade-off. The presented method is a non-linear and non-parametric method of local polynomial regression (LPR). Unlike curve fitting by shrinkage or adaptation to higher harmonics representation in the wavelet transform method, the proposed technique optimized the bias of variance by estimating the signals based on smoothing parameter. The optimization in the bias or variance of estimation has a direct impact on the removal of noise components. A well-denoised signal brings precision in the local fitting of the curve in a kernel regression problem that uses the parameter obtained from ICI method. The Nadaraya-Watson kernel is used in this approach where the values of point-wise smoothing parameter is kept constant throughout regressions. The comparisons of the results of proposed method are carried out with the latest wavelet denoising to ensure its superiority in performance. The implementation complexity and memory requirements are also discussed in detail. [ABSTRACT FROM AUTHOR]

Abstract Noise impairs the performance of inverse synthetic aperture radar (ISAR) motion compensation, which induces severe defocusing under low signal‐to‐noise ratio environments. To overcome this issue, a novel similarity‐oriented (SO) method with a two‐domain denoising strategy is proposed. A PIxEl similarity‐oriented (PIE‐SO) denoising method designed for range‐Doppler (RD) domain and a modified RAnge Profile Similarity‐Oriented (RAP‐SO) denoising method designed for high‐resolution range profile (HRRP) matrix are included in the presented framework. Firstly, the PIE‐SO method directly performs a two‐dimensional fast Fourier transform on dechirp processed echo data to form a coarsely focusing ISAR image in the RD domain. Then the focusing image is separated from the noise background by virtue of pixel similarity, after which the noise is preliminarily removed. Subsequently, the coarsely denoised image is transformed into the HRRP matrix. Considering the range profile similarity impaired by noise is restored by the PIE‐SO denoising, a Laplacian regularised‐weighted nuclear norm proximal (LR‐WNNP) operator is proposed. The proposed modified RAP‐SO method, that is, the LR‐WNNP operator, exploits the low‐rank property of the HRRP matrix and the local similarity of adjacent HRRPs to reduce the residual noise. As a result, ISAR imaging quality is significantly improved. Comprehensive experiments illustrate the effectiveness and superiority of the presented method.

Electrocardiogram is the most essential diagnostic test for heart disease detection in this era, where it has low frequency and small amplitude, making it vulnerable to a variety of stimuli, including high/low-frequency noises resulting in diagnostic quality suffers. Implementation of adaptive filter removes noise from the signal in a better way. Adaptive filters in signal processing plays a major role in biomedical applications for denoising different types of noises such as Power Line Interference noise which is generated by the power line electromagnetic field and it exhibits its peak from 50 to 60 Hz, Baseline Wander noise which occurs due to the variation of electrode skin impedance, Motion Artifacts which is generated by the electrode motions away from the contact zone on the skins and Muscle Noise, this is due to the Electromyographic signals, originating from the skeletal muscle contractions. In order to eliminate the above-mentioned noises, the most common adaptive filters such as Least Mean Square (LMS) and Recursive Least Squares (RLS) are used. In existing method, they used Cascaded Least Mean Square adaptive filters to reduce noises at a much higher rate than the Least Mean Square Adaptive filter and to achieve the higher Signal to Noise Ratio (SNR). The Cascaded RLS filter can be used to obtain faster range of convergence than the Cascaded LMS. The filter is designed with adaptive variable step size which calculates the step size according to the input signal of the filter, this is used to increase the stability of the filter. The systolic architecture and associativity of the VLLMS filter is implemented to reduce the number of adders and multipliers along the critical path of the filter. This work comprises of designing the 4 tap, 8 tap and 16 tap cascaded systolic associative variable leaky least mean square adaptive filters using Simulink and the SNR comparisons have been made between normal LMS cascaded filter and cascaded VLLMS filter. The area and delay between normal filter and systolic associative filter are compared by converting the Simulink design into Verilog and by implementing in Xilinx. [ABSTRACT FROM AUTHOR]

In this paper, denoising of seismic signals based on Maximal Overlap Discrete Wavelet Transform and Adaptive Filtering (MODWT-AF) is discussed. In this method, first the seismic signals are converted into a set of coefficients called approximation and detailed coefficients by applying MODWT-based Multi Resolution Analysis (MODWT-MRA) technique. Then, adaptive filtering is applied to these coefficients, which removes noise present in the frequency sub bands of the signals. Finally, the denoised signal is reconstructed by performing the inverse MODWT to the modified set of coefficients. As a statistical analysis, the performance measures such as input signal-to-noise $ (SN{R_{in}}) $ (SN R in ) , output signal-to-noise ratio $ (SN{R_{out}}) $ (SN R out ) , SNR improvement $ (\Delta SNR) $ (ΔSNR) , Normalized Correction Coefficient (NCC), Mean Square Error (MSE), and RMS error are evaluated for different real earthquake records and synthetic seismic signals. The performance results of the proposed methodology are compared with other conventional thresholding methods such as MODWT-based thresholding (MODWT-TH) and Discrete Wavelet Transform based thresholding techniques namely Heursure (DWT-HE), Sqtwolog (DWT-SG), Minimaxi (DWT-MI), and Rigrsure (DWT-RE). The experimental results effectively demonstrated that the proposed methodology produced better outcomes compared to the conventional methods. [ABSTRACT FROM AUTHOR]

The identification of slag inclusion defects in welds is of the utmost importance in guaranteeing the integrity, safety, and prolonged service life of welded structures. Most research focuses on different kinds of weld defects, but branch research on categories of slag inclusion material is limited and critical for safeguarding the quality of engineering and the well-being of personnel. To address this issue, we design a simulated method using ultrasonic testing to identify the inclusion of material categories in austenitic stainless steel. It is based on a simulated experiment in a water environment, and six categories of cubic specimens, including four metallic and two non-metallic materials, are selected to simulate the slag materials of the inclusion defects. Variational mode decomposition optimized by particle swarm optimization is employed for ultrasonic signals denoising. Moreover, the phase spectrum of the denoised signal is utilized to extract the phase characteristic of the echo signal from the water–slag specimen interface. The experimental results show that our method has the characteristics of appropriate decomposition and good denoising performance. Compared with famous signal denoising algorithms, the proposed method extracted the lowest number of intrinsic mode functions from the echo signal with the highest signal-to-noise ratio and lowest normalized cross-correlation among all of the comparative algorithms in signal denoising of weld slag inclusion defects. Finally, the phase spectrum can ascertain whether the slag inclusion is a thicker or thinner medium compared with the weld base material based on the half-wave loss existing or not in the echo signal phase. [ABSTRACT FROM AUTHOR]

In speech coding, denoising of the speech signal is essential as well as crucial. The filters for minimizing errors through denoising employ the autoregressive moving average (ARMA) approach, introducing higher computational complexity in speech coder design. This research work presents the design and implementation of an effective perceptual weighting filter (PWF) for speech coding. The high-level synthesis of the fixed-point PWF filter is optimized by multiple optimization techniques along with detailed design space exploration using the weighted sum (WS) method. To enhance the performance, an FPGA-based hardware accelerator is proposed using hardware/software (HW/SW) co-design in an embedded environment. Simulative analysis in Vivado HLS and final accelerator design in the Vitis IDE tool validate the proposed architecture by using real-time speech samples, demonstrating a 50% reduction in area and a 99% execution improvement. This makes it well-suited for use in modern speech codecs, enhancing the efficiency. [ABSTRACT FROM AUTHOR]

Random noise attenuation is significant in seismic data processing. Supervised deep learning-based denoising methods have been widely developed and applied in recent years. In practice, it is often time-consuming and laborious to obtain noise-free data for supervised learning. Therefore, we propose a novel deep learning framework to denoise prestack seismic data without clean labels, which trains a high-resolution residual neural network (SRResnet) with noisy data for input and the same valid data with different noise for output. Since valid signals in noisy sample pairs are spatially correlated and random noise is spatially independent and unpredictable, the model can learn the features of valid data while suppressing random noise. Noisy data targets are generated by a simple conventional method without fine-tuning parameters. The initial estimates allow signal or noise leakage as the network does not require clean labels. The Monte Carlo strategy is applied to select training patches for increasing valid patches and expanding training datasets. Transfer learning is used to improve the generalization of real data processing. The synthetic and real data tests perform better than the commonly used state-of-theart denoising methods. [ABSTRACT FROM AUTHOR]

Noise impairs the performance of inverse synthetic aperture radar (ISAR) motion compensation, which induces severe defocusing under low signal‐to‐noise ratio environments. To overcome this issue, a novel similarity‐oriented (SO) method with a two‐domain denoising strategy is proposed. A PIxEl similarity‐oriented (PIE‐SO) denoising method designed for range‐Doppler (RD) domain and a modified RAnge Profile Similarity‐Oriented (RAP‐SO) denoising method designed for high‐resolution range profile (HRRP) matrix are included in the presented framework. Firstly, the PIE‐SO method directly performs a two‐dimensional fast Fourier transform on dechirp processed echo data to form a coarsely focusing ISAR image in the RD domain. Then the focusing image is separated from the noise background by virtue of pixel similarity, after which the noise is preliminarily removed. Subsequently, the coarsely denoised image is transformed into the HRRP matrix. Considering the range profile similarity impaired by noise is restored by the PIE‐SO denoising, a Laplacian regularised‐weighted nuclear norm proximal (LR‐WNNP) operator is proposed. The proposed modified RAP‐SO method, that is, the LR‐WNNP operator, exploits the low‐rank property of the HRRP matrix and the local similarity of adjacent HRRPs to reduce the residual noise. As a result, ISAR imaging quality is significantly improved. Comprehensive experiments illustrate the effectiveness and superiority of the presented method. [ABSTRACT FROM AUTHOR]

Lidar (Light Detection and Ranging), utilizes laser based remote sensing data to measure distances and properties of objects by analysing reflected light, serving diverse applications. Lidar signals in the middle atmosphere face challenges like noise and atmospheric uncertainties. Lidar signal denoising and temperature retrievals are crucial for accurate measurements, improving data reliability in atmospheric research. Lidar signal denoising is the process of reducing unwanted noise or interference from Lidar data, enhancing accuracy and reliability. To address the issues Shuffle Attention with Encoder and Decoder based Deep Convolutional Neural Network (SAED-DCNN) is proposed. The Lidar signal undergoes preprocessing, including normalization, followed by convolution and pooling encoding in the autoencoding layer of SAED-DCNN. Leveraging Deep Convolutional Neural Network (DCNN) and encoder-decoder Framework, with shuffle attention, enhances spatial interactions for reducing Lidar signal noise. the introduction of enhanced spider wasp optimization addresses computational complexity, optimizing SAED-DCNN parameters, presenting an innovative Lidar signal enhancement approach. The suggested framework exhibits outstanding performance, achieving signal-to-noise ratio and root mean squared error of 28.135 dB and 68.113, respectively. These metrics underscores the mode's efficacy in overcoming denoising challenges, establishing it as a robust denoising solution. [ABSTRACT FROM AUTHOR]

A multi-sensor information fusion algorithm based on fault-tolerant Kalman filter is proposed in phase-sensitive optical time-domain reflectometer (Φ-OTDR) system, for achieving fading-free distributed vibration sensing. Firstly, a fault-tolerant dual-core complementary array model is designed. The Rayleigh scattering signal denoising, and vibration existence judgment of localization points are carried out to obtain the differentiated frequency demodulation results of the sensing points of the dual-core fiber array. Then a fault-tolerant control strategy is used to determine the sensor weight coefficients and vibration judgment coefficients during data fusion processing, and array data fusion is carried out based on time series data using Kalman filter to realize error value identification and filling. The advantage of this method is the combination of redundant data in a complementary way to improve the system stability. The frequency response ranges from 10 Hz to 2400 Hz and the localization accuracy is 98.33%. The influence of key parameters on the frequency demodulation performance of fault-tolerant Kalman filter is discussed, and a standard deviation of 14.6 Hz and an average error of 7.6 Hz are obtained. The demodulation frequency data matrix obtained by the classical demodulation method has a demodulation error probability of 89.18%, which proves the widespread existence of demodulation errors in vibration signals. The fusion error of demodulation frequency is reduced to 0.25 Hz, the frequency demodulation accuracy reaches 100%, and the demodulation error caused by interference attenuation can be completely eliminated. This system based on fault-tolerant Kalman filter has the characteristics of simple multiplexing structure, interference fading resistance and stable demodulation performance. • A sensor information fusion algorithm based on fault-tolerant Kalman filter is proposed to achieve fading-free sensing. [ABSTRACT FROM AUTHOR]

Purpose: The working environment of the mine is complex, and there are many interference noises. Microseismic signals and noises are mixed together, which interferes with the analysis of microseismic signals and affects the subsequent work of phase arrival picking and source location. Therefore, it is necessary to study the noise reduction of microseismic signals. Method: In view of the randomness and non-stationarity of microseismic signals, a signal denoising method based on the multi-layer joint is proposed in this paper. SVD (singular value decomposition) is used as the first layer denoising method to remove the white noise in the signal. EMD( Empirical Mode Decomposition) is used as the second layer noise reduction method to deal with random and non-stationary microseismic signals. As the third layer noise reduction method, the wavelet threshold eliminates the modal aliasing phenomenon generated by EMD. Result: The experimental analysis shows that the proposed method has a good noise reduction effect on the simulation signal and the actual microseismic signal with different signal-to-noise ratios. Conclusion: It overcomes the disadvantage of the poor noise reduction effect of a single noise reduction method, can greatly improve the signal-to-noise ratio of the signal, and has a high similarity with the original signal, which provides a new idea for microseismic signal noise reduction. [ABSTRACT FROM AUTHOR]

The alarming mortality rates associated with cardiac abnormalities emphasize the critical need for early and accurate detection of heart disorders to mitigate severe health consequences for patients. Electrocardiograms (ECG) are commonly employed instruments for the examination of cardiac disorders, with a preference for noise-free ECG signals to ensure precise interpretation. However, ECG signal recordings are susceptible to environmental interferences, including patient movement and electrode positioning. This paper introduces a hardware implementation for denoising ECG signals, leveraging a novel method by integrating high-order Synchrosqueezing Transform, Detrended Fluctuation Analysis, and Non-Local-Mean filter optimized by Particle Swarm Optimization (HSST-DFA-PSO-NLM) techniques on Field-Programmable Gate Array (FPGA) platforms. FPGA-based processing units are chosen for their outstanding performance attributes, including high re-programmability, speed, architectural flexibility, and low power consumption, resulting in efficient signal processing. The effectiveness of the designed filtering algorithm is evaluated using key criteria, including Signal-to-Noise Ratio (SNR) and Root Mean Square Error (RMSE) for performance assessment. Additionally, resource utilization metrics such as Look-Up Tables (LUTs), Flip Flops, and DSP Blocks, as well as power consumption measures including dynamic power and static or leakage power, are analysed across various FPGA boards (Virtex and Zedboards) utilizing the VIVADO environment. Comparative analyses are conducted to identify the most suitable FPGA board for implementation, highlighting the superior performance of the proposed design. Remarkably, the proposed denoising solution gives excellent SNR of 29.56, 29.68, and 28.86 by denoising various ECG noises. The RMSE attained by the model is also less than 0.05. This research advances the field of cardiac disorder detection by providing a reliable and efficient FPGA-based solution for ECG signal denoising, thereby enhancing the accuracy of early diagnosis and treatment. [ABSTRACT FROM AUTHOR]

In this paper, we propose a Transformer-based encoder architecture integrated with an unsupervised denoising method to learn meaningful and sparse representations of vibration signals without the need for data transformation or pre-trained data. Existing Transformer models often require transformed data or extensive computational resources, limiting their practical adoption. We propose a simple yet competitive modification of the Transformer model, integrating a trainable noise reduction method specifically tailored for failure mode classification using vibration data directly in the time domain without converting them into other domains or images. Furthermore, we present the key architectural components and algorithms underlying our model, emphasizing interpretability and trustworthiness. Our model is trained and validated using two benchmark datasets: the IMS dataset (four failure modes) and the CWRU dataset (four and ten failure modes). Notably, our model performs competitively, especially when using an unbalanced test set and a lightweight architecture. [ABSTRACT FROM AUTHOR]

To accurately identify the deflection data collected by a traffic speed deflectometer (TSD) and eliminate the noise in the measured signals, a TSD signal denoising method based on the partial swarm optimization–variational mode decomposition (PSO–VMD) method is proposed. Initially, the VMD algorithm is used for modal decomposition, calculating the correlation coefficients between each decomposed mode and the original signal for modal selection and signal reconstruction; Then, the particle swarm optimization algorithm is utilized to optimize the number of modes K and the value α for the VMD algorithm, adopting fuzzy entropy as the affinity function to circumvent effects from sequence decomposition and forecasting accuracy, thus identifying the optimal combination of hyperparameters. Finally, the analysis on simulated signals indicates that the PSO–VMD method secures the best parameters, showing a clear advantage in denoising. Denoising real TSD data validates that the approach proposed herein achieves commendable outcomes in TSD deflection noise reduction, offering a feasible strategy for TSD signal denoising. [ABSTRACT FROM AUTHOR]

Acoustic signal processing technology is a new discipline developed in recent years, which has been widely applied in various fields such as communication, radar, sonar, and so on. Due to the wide variety of sound sources and the high susceptibility of signals to various interferences, it is necessary to perform noise reduction processing on them. Blind source separation technology is an emerging signal processing method that can simultaneously separate signals from multiple sources, thus having significant advantages in noise reduction. On the basis of summarizing traditional noise reduction algorithms, this article proposes an improved adaptive filtering algorithm combined with blind source separation technology, and conducts simulation experiments on both the traditional algorithm and the improved algorithm. [ABSTRACT FROM AUTHOR]

Vibration signal analysis is regarded as a fundamental approach in diagnosing faults in rolling bearings, and recent advancements have shown notable progress in this domain. However, the presence of substantial background noise often results in the masking of these fault signals, posing a significant challenge for researchers. In response, an adaptive denoising autoencoder (ADAE) approach is proposed in this paper. The data representations are learned by the encoder through convolutional layers, while the data reconstruction is performed by the decoder using deconvolutional layers. Both the encoder and decoder incorporate adaptive shrinkage units to simulate denoising functions, effectively removing interfering information while preserving sensitive fault features. Additionally, dropout regularization is applied to sparsify the network and prevent overfitting, thereby enhancing the overall expressive power of the model. To further enhance ADAE's noise resistance, shortcut connections are added. Evaluation using publicly available datasets under scenarios with known and unknown noise demonstrates that ADAE effectively enhances the signal-to-noise ratio in strongly noisy backgrounds, facilitating accurate diagnosis of faults in rolling bearings. [ABSTRACT FROM AUTHOR]

Neonatal electrocardiogram (ECG) monitoring is an important diagnostic tool for identifying cardiac issues in infants at birth. Long-term remote neonatal dryelectrode ECG monitoring solutions can be an additional step for preventive healthcare measures. In these solutions, power and computationally efficient embedded signal processing techniques for denoising newborn ECGs can assist in increasing neonatal medical wearable time. Wavelet denoising is an appropriate denoising mechanism with low computational complexity that can be implemented on embedded microcontrollers for long-term remote ECG monitoring. Discrete wavelet transform (DWT) denoising for neonatal dry-electrode ECG using different wavelet families is investigated. The wavelet families and mother wavelets used include Daubechies (db1, db2, db3, db4, and db6), symlets (sym5), and coiflets (coif5). Different levels of added white Gaussian noise (AWGN) were added to 19 newborn ECG signals, and denoising was performed to select the appropriate wavelets for neonatal dry-electrode ECG. The selected wavelets then undergo real noise additions of baseline wander and electrode motion to determine their robustness and accuracy. Signal-to-noise ratio (SNR), mean squared error (MSE), and power spectral density (PSD) are used to examine denoising performance. db1, db2, and db3 wavelets are eliminated from analysis where the 30 dB AWGN led to negative SNR improvement for at least one newborn ECG, removing important ECG information. db4 and sym5 are eliminated from selection due to their different waveform morphology compared to the dry-electrode newborn ECG's QRS complex. db6 and coif5 are selected due to their highest SNR improvement and lowest MSE of 6.26 × 10-6 and 1.65 × 10-7 compared to other wavelets, respectively. Their wavelet shapes are more like a newborn ECG's QRS morphology, validating their selection. db6 and coif5 showed similar denoising performance, decreasing electrode motion and baseline wander noisy ECG signals by 10 dB and 14 dB, respectively. Further denoising of inherent dry-electrode noise is observed. DWT with coif5 or db6 wavelets is appropriate for denoising newborn dry-electrode ECGs for long-term neonatal dry-electrode ECG monitoring solutions under different noise types. Their similarity to newborn dry-electrode ECGs yields accurate and robust reconstructed denoised newborn dry-electrode ECG signals. [ABSTRACT FROM AUTHOR]