Search

In this paper, we propose a novel method for 3D data cube denoising, where the 3D data cube is corrupted by noise with spatially varying noise levels. We perform 3D dual tree complex wavelet transform (DTCWT) to the 3D data cube, and then conduct wavelet-based thresholding based on three scales of dependency in wavelet coefficients. Instead of using the global noise level, we estimate the noise levels locally, which improve the denoising results substantially. We conduct inverse DTCWT to obtain the noise reduced data cubes. Experiments demonstrate that our proposed method outperforms block matching and 3D filtering, video block matching and 3D filtering, 2D bivariate shrinkage, and 3D bivariate shrinkage significantly for noise reduction of 3D data cubes. [ABSTRACT FROM AUTHOR]

The ability to predict and preempt insulator failures holds the potential to enhance the reliability of electrical power grids. The increase in insulator leakage current is an indication that failures may occur. By harnessing historical data and employing time series forecasting models, it is possible to identify potential faults before they escalate into disruptive failures. In this paper, a hybrid model for time series prediction is proposed by combining the Christiano–Fitzgerald random walk filter for signal denoising with an ensemble bootstrap aggregation model for leakage current forecasting. A comparison between bootstrap aggregation, boosting, random subspace, and stacked generalization ensemble learning models is presented. With a root mean square error of 7.62 × 10 - 4 (in a statistical evaluation), the ensemble bootstrap aggregation model with Christiano–Fitzgerald random walk filter proved to be a promising approach to be applied for time series fault forecasting. The proposed method was shown to be more promising than the original ensemble bootstrap aggregation model and the long short-term memory. [ABSTRACT FROM AUTHOR]

We consider an abstract concept of perimeter measure space as a very general framework in which one can properly consider two of the most well-studied variational models in image processing: the Rudin–Osher–Fatemi model for image denoising (ROF) and the Mumford–Shah model for image segmentation (MS). We show the linkage between the ROF model and the two phases piecewise constant case of MS in perimeter measure spaces. We show applications of our results to nonlocal image segmentation, via discrete weighted graphs, and to multiclass classification on high dimensional spaces. [ABSTRACT FROM AUTHOR]

Human motion capture technology, which leverages sensors to track the movement trajectories of key skeleton points, has been progressively transitioning from industrial applications to broader civilian applications in recent years. It finds extensive use in fields such as game development, digital human modeling, and sport science. However, the affordability of these sensors often compromises the accuracy of motion data. Low-cost motion capture methods often lead to errors in the captured motion data. We introduce a novel approach for human motion reconstruction and enhancement using spatio-temporal attention-based graph convolutional networks (ST-ATGCNs), which efficiently learn the human skeleton structure and the motion logic without requiring prior human kinematic knowledge. This method enables unsupervised motion data restoration and significantly reduces the costs associated with obtaining precise motion capture data. Our experiments, conducted on two extensive motion datasets and with real motion capture sensors such as the SONY (Tokyo, Japan) mocopi, demonstrate the method's effectiveness in enhancing the quality of low-precision motion capture data. The experiments indicate the ST-ATGCN's potential to improve both the accessibility and accuracy of motion capture technology. [ABSTRACT FROM AUTHOR]

Diffusion MRI with free gradient waveforms, combined with simultaneous relaxation encoding, referred to as multidimensional MRI (MD‐MRI), offers microstructural specificity in complex biological tissue. This approach delivers intravoxel information about the microstructure, local chemical composition, and importantly, how these properties are coupled within heterogeneous tissue containing multiple microenvironments. Recent theoretical advances incorporated diffusion time dependency and integrated MD‐MRI with concepts from oscillating gradients. This framework probes the diffusion frequency, ω$$ \omega $$, in addition to the diffusion tensor, D$$ \mathbf{D} $$, and relaxation, R1$$ {R}_1 $$, R2$$ {R}_2 $$, correlations. A Dω−R1−R2$$ \mathbf{D}\left(\omega \right)-{R}_1-{R}_2 $$ clinical imaging protocol was then introduced, with limited brain coverage and 3 mm3 voxel size, which hinder brain segmentation and future cohort studies. In this study, we introduce an efficient, sparse in vivo MD‐MRI acquisition protocol providing whole brain coverage at 2 mm3 voxel size. We demonstrate its feasibility and robustness using a well‐defined phantom and repeated scans of five healthy individuals. Additionally, we test different denoising strategies to address the sparse nature of this protocol, and show that efficient MD‐MRI encoding design demands a nuanced denoising approach. The MD‐MRI framework provides rich information that allows resolving the diffusion frequency dependence into intravoxel components based on their Dω−R1−R2$$ \mathbf{D}\left(\omega \right)-{R}_1-{R}_2 $$ distribution, enabling the creation of microstructure‐specific maps in the human brain. Our results encourage the broader adoption and use of this new imaging approach for characterizing healthy and pathological tissues. [ABSTRACT FROM AUTHOR]

Low-dose computed tomography (LDCT) technology has attracted more and more attention in the field of medical imaging because of the reduction of radiation damage to the human body. However, the large amount of quantum noise contained in LDCT images can affect physicians' judgment. To solve the problem of large amounts of quantum noise and artifacts in LDCT images, a convolutional neural network denoising model based on cartoon texture decomposition of images (CATCNN) is developed in this study based on deep learning. The model first uses a U-Net-based image decomposition sub-network to decompose LDCT images into cartoon images and texture images. The texture images are then denoised using a texture denoising sub-network based on edge protection and Efficient Channel Attention, finally, cartoon images are summed with the denoised texture images to obtain images with improved quality. Our experimental results demonstrate that the proposed model outperforms existing technologies, achieving a peak signal-to-noise ratio value of 33.4666 dB and a structural similarity value of 0.9193. The visual and quantitative evaluation results suggest that the CATCNN model effectively improves the quality of LDCT images. [ABSTRACT FROM AUTHOR]

This paper introduces an innovative electrocardiogram (ECG ) denoising technique based on stationary wavelet transform ( S W T) and wavelet/total variation (WATV). In this technique, we also use two different artificial neural networks ( ANNs ) to determine two ideal thresholds, t h r 1 and t h r 2 . The latter is used for the soft thresholding of a noisy details coefficient, c d b 2 , to obtain a denoised coefficient, c d d 2 . The threshold t h r 1 is used for the soft thresholding of a noisy details coefficient, c d b 1 , yielding a denoised coefficient, c d d 1. The coefficient c d b 1 and a noisy approximation coefficient, c a b 1 , are obtained by applying SWT to the noisy ECG signal. The coefficient c d b 2 and another noisy approximation coefficient, c a b 2 , are obtained by applying SWT to c a b 1 . In this proposed ECG denoising system, we also apply a WATV-based denoising technique to c a b 2 to obtain a denoised approximation coefficient, c a d 2 . This WATV-based denoising technique requires the estimation of the level of the noise corrupting the clean ECG signal. This noise is additive Gaussian white noise (AGWN) and its level is denoted as σ , which is estimated from c d b 1 . After that, the inverse of SWT ( S W T - 1 ) is applied to c d d 2 and c a d 2 to obtain a denoised approximation coefficient, c a d 1 . Subsequently, we apply S W T - 1 to c d d 1 and c a d 1 to finally obtain the denoised ECG signal. The performance of this proposed ECG denoising technique is proven by the results obtained after computing the signal-to-noise ratio ( SNR ), the peak SNR ( PSNR ), the mean square error ( MSE ), the mean absolute error ( MAE ) and the cross-correlation ( CC ). [ABSTRACT FROM AUTHOR]

Image denoising is an important pre-processing process in the fields of computer vision and image processing. Traditional denoising techniques blur edges excessively and degrade image quality by removing noise components but failing to maintain clarity. To overcome these problems, this paper proposes a multispectral image denoising strategy combining non-local rank tensor decomposition (NLRTD) and bilateral filtering. To extract patches from noisy images, single-level discrete wavelet transform (DWT) is utilized. Then, similar patches from the extracted images are grouped using spectral clustering. After that, mixed noise is reduced by separating clean images from each clustered group using NLRTD. An optimized bilateral filter using Sunflower optimization (SFO) is used for denoising by preserving edge details and is reconstructed using its constituent parts. The effectiveness of the proposed denoising method is assessed using performance matrices, such as BER, PSNR, MSE, RMSE, SNR and SSIM were 0.8544%, 53.21%, 2.41%, 2.41%, 25.06% and 0.90%, respectively. [ABSTRACT FROM AUTHOR]

In the acquisition process of 3D cultural relics, it is common to encounter noise. To facilitate the generation of high-quality 3D models, we propose an approach based on graph signal processing that combines color and geometric features to denoise the point cloud. We divide the 3D point cloud into patches based on self-similarity theory and create an appropriate underlying graph with a Markov property. The features of the vertices in the graph are represented using 3D coordinates, normal vectors, and color. We formulate the point cloud denoising problem as a maximum a posteriori (MAP) estimation problem and use a graph Laplacian regularization (GLR) prior to identifying the most probable noise-free point cloud. In the denoising process, we moderately simplify the 3D point to reduce the running time of the denoising algorithm. The experimental results demonstrate that our proposed approach outperforms five competing methods in both subjective and objective assessments. It requires fewer iterations and exhibits strong robustness, effectively removing noise from the surface of cultural relic point clouds while preserving fine-scale 3D features such as texture and ornamentation. This results in more realistic 3D representations of cultural relics. [ABSTRACT FROM AUTHOR]

In this article, the topic of time series modelling is discussed. It highlights the criticality of analysing and forecasting time series data across various sectors, identifying five primary application areas: denoising, forecasting, nonlinear transient modelling, anomaly detection, and degradation modelling. It further outlines the mathematical frameworks employed in a time series modelling task, categorizing them into statistical, linear algebra, and machine- or deep-learning-based approaches, with each category serving distinct dimensions and complexities of time series problems. Additionally, the article reviews the extensive literature on time series modelling, covering statistical processes, state space representations, and machine and deep learning applications in various fields. The unique contribution of this work lies in its presentation of a Python-based toolkit for time series modelling (PyDTS) that integrates popular methodologies and offers practical examples and benchmarking across diverse datasets. [ABSTRACT FROM AUTHOR]

Raman spectroscopy can be effectively used for detection and analysis of chemical agents that are serious threats in modern warfare, but the detection and analysis performance is prone to deterioration due to noise. The existing denoising technique has limitations that there is no criterion for selecting the window length and that the filtering distorts the peaks, key features for Raman spectral data analysis. To overcome such limitations, in this paper, we propose the peak‐aware adaptive denoising for Raman spectroscopy based on machine learning approach. The proposed technique utilizes the information of detected peaks to eliminate noise effectively using different window values optimal for each region in the Raman spectrum while preserving the shape of peaks. We conducted the various analyses and experiments, and the proposed technique showed a 28% lower Euclidean distance and a 48% lower Fréchet inception distance compared to the existing technique, meaning the proposed technique outperformed the existing one. [ABSTRACT FROM AUTHOR]

Measurement of lightning current plays a critical role in the field of atmospheric electricity. Traditionally, Rogowski coils or low-resistance shunts were employed for measuring lightning currents in the range from several amperes up to several hundreds of kilo-amperes, and high-value resistors were utilized for measuring corona discharge currents at sub-ampere levels. However, these approaches were not suitable for continuously recording the vast range of lightning currents. For this sake, we have developed a lightning current measurement system equipped with a shock-tolerant low-noise amplifier module. With the system installed on a tall tower, sub-ampere level currents just before the lightning initiation were observed for the first time. To confirm the authenticity of the recorded currents, the background noise of the measurement system and surrounding environment were identified, and a digital multi-frequency notch filter was proposed for de-noising. Results show that the system can achieve a current identification level of 50 mA even in complex electromagnetic environments, while having a measurement capability of 220 kA. [ABSTRACT FROM AUTHOR]

Light Sheet Fluorescence Microscopy (LSFM) has emerged as a valuable tool for neurobiologists, enabling the rapid and high-quality volumetric imaging of mice brains. However, inherent artifacts and distortions introduced during the imaging process necessitate careful enhancement of LSFM images for optimal 3D reconstructions. This work aims to correct images slice by slice before reconstructing 3D volumes. Our approach involves a three-step process: firstly, the implementation of a deblurring algorithm using the work of K. Becker; secondly, an automatic contrast enhancement; and thirdly, the development of a convolutional denoising auto-encoder featuring skip connections to effectively address noise introduced by contrast enhancement, particularly excelling in handling mixed Poisson–Gaussian noise. Additionally, we tackle the challenge of axial distortion in LSFM by introducing an approach based on an auto-encoder trained on bead calibration images. The proposed pipeline demonstrates a complete solution, presenting promising results that surpass existing methods in denoising LSFM images. These advancements hold potential to significantly improve the interpretation of biological data. [ABSTRACT FROM AUTHOR]

Denoising electrocardiogram (ECG) signals is a challenge because of the unavoidable artifacts. In this paper, an adaptive and effective signed error normalized least mean square algorithm (SE-NLMS) is proposed to improve denoising and reduce the mean square error (MSE). The performance of the SE-NLMS algorithm with unfolding technique (SE-UNLMS) has been compared with that of the normalized least mean square algorithm with unfolding structure (UNLMS) as well as the least mean square algorithm with unfolding structure (ULMS). SE-NLMS has the advantage of NLMS, namely an adaptive convergence rate and reduced computational complexity. We have implemented all three algorithms, namely LMS, NLMS and SE-NLMS, using an unfolding architecture that offers minimum delay and is suitable for real-time applications. Performance metrics such as an MSE of 0.0062 and a signal-to-noise ratio (SNR) improvement of about 10.2% are achieved through the proposed method of SE-UNLMS compared to other denoising methods. Additionally, exploration has been carried out for the application of denoised ECG signals under various arrhythmia conditions. The time-domain features were extracted from various denoised ECG signals and classified with support vector machines (SVM) to yield a good classification accuracy of 96.5%. The SE-UNLMS denoising method is demonstrated to be a valuable implementation for the detection and diagnosis of arrhythmias in real-world medical situations via this classification process. For real-time validation, the proposed method SE-UNLMS was implemented on a field-programmable gate array (FPGA) using Spartan 6 VPTB-20. The FPGA implementation highlights the feasibility of the proposed SE-UNLMS for real-time ECG monitoring applications. [ABSTRACT FROM AUTHOR]

Image processing is an important area to bring out the best in an image for human interpretation. This process has been widely used in various fields such as machine vision, remote sensing image analysis, medical diagnosis, image restoration, image pattern recognition, and video processing. During the acquisition and transmission of digital images, several random signals, known as noise, can affect image quality. To reduce or to remove efficiently the noise in the acquired or transmitted images, various image denoising techniques can be applied. The performance of denoising methods increases progressively when the noise parameters are taken into account as input parameters. Traditional denoising approaches adopt some assumptions to model noise, such noise is known as purely additive or multiplicative, pixel-independent, and channel-invariant. Usually, these assumptions limit the denoising effect due to inaccurate estimation of noise parameters in these algorithm models. However, the real noise model is signal-dependent and even device-dependent. In this paper, a new denoising method called signal-dependant noise-reducing anisotropic diffusion is developed, which is a version of the speckle reducing anisotropic diffusion (SRAD) filter. It differs from the standard SRAD filter approach by the insertion of a suitable noise parameters estimation framework. The new filter is designed to handle a variety of images corrupted by several common types of signal-dependent noises that are produced by charge-coupled device sensors. As well as it offers great potential for denoising with preserving textures and fine details. Extensive experiments demonstrate a significant increase in the image denoising performance in terms of SNR and RMSE. Qualitative (visual) results underline the efficacy of the proposed algorithm for filtering mixed signal-dependent noise. [ABSTRACT FROM AUTHOR]

23Na MRI can be used to quantify in-vivo tissue sodium concentration (TSC), but the inherently low 23Na signal leads to long scan times and/or noisy or low-resolution images. Reconstruction algorithms such as compressed sensing (CS) have been proposed to mitigate low signal-to-noise ratio (SNR); although, these can result in unnatural images, suboptimal denoising and long processing times. Recently, machine learning has been increasingly used to denoise 1H MRI acquisitions; however, this approach typically requires large volumes of high-quality training data, which is not readily available for 23Na MRI. Here, we propose using 1H data to train a denoising convolutional neural network (CNN), which we subsequently demonstrate on prospective 23Na images of the calf. 1893 1H fat-saturated transverse slices of the knee from the open-source fastMRI dataset were used to train denoising CNNs for different levels of noise. Synthetic low SNR images were generated by adding gaussian noise to the high-quality 1H k-space data before reconstruction to create paired training data. For prospective testing, 23Na images of the calf were acquired in 10 healthy volunteers with a total of 150 averages over ten minutes, which were used as a reference throughout the study. From this data, images with fewer averages were retrospectively reconstructed using a non-uniform fast Fourier transform (NUFFT) as well as CS, with the NUFFT images subsequently denoised using the trained CNN. CNNs were successfully applied to 23Na images reconstructed with 50, 40 and 30 averages. Muscle and skin apparent TSC quantification from CNN-denoised images were equivalent to those from CS images, with <0.9 mM bias compared to reference values. Estimated SNR was significantly higher in CNN-denoised images compared to NUFFT, CS and reference images. Quantitative edge sharpness was equivalent for all images. For subjective image quality ranking, CNN-denoised images ranked equally best with reference images and significantly better than NUFFT and CS images. Denoising CNNs trained on 1H data can be successfully applied to 23Na images of the calf; thus, allowing scan time to be reduced from ten minutes to two minutes with little impact on image quality or apparent TSC quantification accuracy. [ABSTRACT FROM AUTHOR]

To obtain accurate resonance peaks from surface plasmon resonance (SPR) spectra, a denoising approach based on generalized S-transform optimized by a new iterative algorithm of bald eagle search (BES) is reported and applied. First, a fiber SPR sensing system is used to collect the original noisy spectra, and the generalized S-transform is performed to obtain the corresponding S-domain spectrum. Next, the denoising threshold ( λ n ) is optimized by the BES algorithm to denoise and reconstruct the SPR reflection spectrum. Finally, the original SPR reflection and the denoised reflection spectra are used to evaluate the fitness function until the optimal denoising threshold ( λ n ) and denoising effect are obtained. The experimental results show that the developed method maintains a relatively stable denoising for SPR reflection spectra as the average values of root mean square error ( RMSE ) and signal to noise ratio ( SNR ) are 0.27 and 23.6, respectively. This method overcomes the problem of arbitrary selection of basic functions or thresholds in conventional denoising methods, improves the accuracy of SPR sensor, and provides a new approach for spectral denoising. [ABSTRACT FROM AUTHOR]

Noise removal is a critical stage in the preprocessing of point clouds, exerting a significant impact on subsequent processes such as point cloud classification, segmentation, feature extraction, and 3D reconstruction. The exploration of methods capable of adapting to and effectively handling the noise in point clouds from real-world outdoor scenes remains an open and practically significant issue. Addressing this issue, this study proposes an adaptive kernel approach based on local density and global statistics (AKA-LDGS). This method constructs the overall framework for point cloud denoising using Bayesian estimation theory. It dynamically sets the prior probabilities of real and noise points according to the spatial function relationship, which varies with the distance from the points to the center of the LiDAR. The probability density function (PDF) for real points is constructed using a multivariate Gaussian distribution, while the PDF for noise points is established using a data-driven, non-parametric adaptive kernel density estimation (KDE) approach. Experimental results demonstrate that this method can effectively remove noise from point clouds in real-world outdoor scenes while maintaining the overall structural features of the point cloud. [ABSTRACT FROM AUTHOR]

The acquisition and transmission of magnetic resonance (MR) images are frequently affected by random noise pollution, which hampers the diagnosis of diseases by doctors or automated systems. Hence, the search for advanced denoising methods is of great research interest, particularly in magnetic resonance imaging (MRI) denoising models, which are based on deep learning networks and achieve satisfactory results. However, the mining of noisy contextual information and effective information-guided transfer are often neglected in the denoising process, which leads to poor extraction of information at different scales, and poor retention of details. This greatly hinders the further development of MR image denoising methods. Here, we propose a denoising method, MSDRA-Net, for the mining and exploitation of different hierarchical noise features and construct a multi-scale dilated residual (MSDR) structure to transfer and retain noise information at different levels across the layer. Next, a contextual guidance attention (CGA) module guides and transfers contextual information, utilizing the features learnt from different layers of the model as weights. A reconstruction refinement block (RRB) is utilized to construct clean images from the obtained noise bias and the given noisy images. Experiments on simulated and clinical MRI data validated the effectiveness of our method, which demonstrated a superior performance compared to several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Inferring a process matrix characterizing a quantum channel from experimental measurements is a key issue of quantum information. Noise affecting the measured counts could bring to matrices different from the expected ones and optimization methods usually employed, i.e. the maximum likelihood estimation (MLE), are characterized by several drawbacks. Lowering the noise could be necessary to increase the experimental resources, e.g. time for each measurement. In this paper, an alternative procedure, based on suitable Neural Networks, has been implemented and optimized to obtain a denoised process matrix and this approach has been tested with a specific quantum channel, i.e. a Control Phase. This promising method relies on the analogy that can be established between the elements of a process matrix and the pixels of an image. [ABSTRACT FROM AUTHOR]

Background: Developing a deep‐learning network for denoising low‐dose CT (LDCT) images necessitates paired computed tomography (CT) images acquired at different dose levels. However, it is challenging to obtain these images from the same patient. Purpose: In this study, we introduce a novel approach to generate CT images at different dose levels. Methods: Our method involves the direct estimation of the quantum noise power spectrum (NPS) from patient CT images without the need for prior information. By modeling the anatomical NPS using a power‐law function and estimating the quantum NPS from the measured NPS after removing the anatomical NPS, we create synthesized quantum noise by applying the estimated quantum NPS as a filter to random noise. By adding synthesized noise to CT images, synthesized CT images can be generated as if these are obtained at a lower dose. This leads to the generation of paired images at different dose levels for training denoising networks. Results: The proposed method accurately estimates the reference quantum NPS. The denoising network trained with paired data generated using synthesized quantum noise achieves denoising performance comparable to networks trained using Mayo Clinic data, as justified by the mean‐squared‐error (MSE), structural similarity index (SSIM)and peak signal‐to‐noise ratio (PSNR) scores. Conclusions: This approach offers a promising solution for LDCT image denoising network development without the need for multiple scans of the same patient at different doses. [ABSTRACT FROM AUTHOR]

Noise suppression is essential in time-domain electromagnetic (TDEM) data processing and interpretation. TDEM data are typically in broadband signal, which makes it difficult to separate the signal in the whole frequency band. The conventional methods tend to process data trace by trace, ignoring the lateral continuity between channels. This paper proposes a workflow based on multivariate variational mode decomposition (MVMD) and multivariate detrended fluctuation analysis (MDFA) to deal with the noise in 2-D TDEM data. The proposed method initially employs MVMD to decompose TDEM signals into a series of intrinsic mode functions (IMFs). Subsequently, MDFA is used to calculate the scaling exponent of each IMF, facilitating the selection of signal-dominant IMFs. Finally, the signal IMFs are summed up to reconstruct the TDEM signal. Both simulation and field results demonstrate that, by considering the lateral continuity of data across channels, the proposed method is more effective at noise removal than other single-channel data processing techniques. [ABSTRACT FROM AUTHOR]

Recent advancements in deep learning have enabled significant progress in image noise type classification and denoising systems. Researchers working on deep learning-based image multi-type denoising either use a single-stage or a two-stage denoising approach. The single-stage approach proposes designing a single denoising autoencoder (DAE), whereas the two-stage approach first classifies the noise type, followed by applying a noise-specific filter. The problem with the single-stage approach is that a generalized DAE fails to be effective. Two-stage approaches work on a limited number of noise types, as researchers typically address only two or three noise types. This paper proposes a framework for two-stage multi-type image denoising that provides classification and denoising of four types of noise with a per-class classification accuracy of 98.2–100% and a denoising technique that obtained promising PSNR and SSIM values for various types of noise, ensuring effective image restoration. The proposed methodology can be applied to any field that requires image denoising without prior knowledge of the type of noise. [ABSTRACT FROM AUTHOR]

Typical point-based rendering algorithms cannot directly handle large outliers or high amounts of noise without either a costly pre-processing of the point cloud or using multiple render passes. In this paper, we propose an A-buffer-based approach that directly renders unprocessed point clouds and filters out outliers in real time, without introducing additional render passes. The core concept of our approach uses bins along each pixel ray in which intermediate information is accumulated. To improve storage efficiency, we extend the binned A-buffer approach using per-ray bin hashing. Our method significantly improves visual quality when rendering noisy point clouds with varying noise levels and large outliers, while only requiring little performance and memory overhead compared to traditional point rendering methods. [ABSTRACT FROM AUTHOR]

In this paper, we propose a unified approach for denoising and super-resolution of document images. The approach is a one shot unpaired technique where a single unpaired example is used as reference for training a SinGAN (Shaham et al., in: Proceedings of the IEEE/CVF international conference on computer vision, 2019) model. The training is carried out in 2 steps. First we use a clean reference image to train a SinGAN to learn the characteristics of the clean image. Then we perform super resolution and denoising of given test image using another SinGAN. Our unique formulation of the loss function helps in this task by prompting the generated images to have characteristics similar to the reference clean image. We conduct experiments on publicly available datasets (Kaggle Dirty Documents Images and DIBCO) and obtain promising results. We also evaluate the performance of our model for OCR and obtain a higher recognition rate compared to competing methods. [ABSTRACT FROM AUTHOR]

Photoplethysmography (PPG) signals are sensitive to motion-induced interference, leading to the emergence of motion artifacts (MA) and baseline drift, which significantly affect the accuracy of PPG measurements. The objective of our study is to effectively eliminate baseline drift and high-frequency noise from PPG signals, ensuring that the signal’s critical frequency components remain within the range of 1 ∼ 10 Hz. This paper introduces a novel hybrid denoising method for PPG signals, integrating Variational Mode Decomposition (VMD) with an improved wavelet threshold function. The method initially employs VMD to decompose PPG signals into a set of narrowband intrinsic mode function (IMF) components, effectively removing low-frequency baseline drift. Subsequently, an improved wavelet thresholding algorithm is applied to eliminate high-frequency noise, resulting in denoised PPG signals. The effectiveness of the denoising method was rigorously assessed through a comprehensive validation process. It was tested on real-world PPG measurements, PPG signals generated by the Fluke ProSim™ 8 Vital Signs Simulator with synthesized noise, and extended to the MIMIC-III waveform database. The application of the improved threshold function let to a substantial 11.47% increase in signal-to-noise ratio (SNR) and an impressive 26.75% reduction in root mean square error (RMSE) compared to the soft threshold function. Furthermore, the hybrid denoising method improved SNR by 15.54% and reduced RMSE by 37.43% compared to the improved threshold function. This study proposes an effective PPG denoising algorithm based on VMD and an improved wavelet threshold function, capable of simultaneously eliminating low-frequency baseline drift and high-frequency noise in PPG signals while faithfully preserving their morphological characteristics. This advancement establishes the foundation for time-domain feature extraction and model development in the domain of PPG signal analysis. [ABSTRACT FROM AUTHOR]

Underwater acoustic technology as an important means of exploring the oceans is receiving more attention. Denoising for underwater acoustic information in complex marine environments has become a hot research topic. In order to realize the hydrophone signal denoising, this paper proposes a joint denoising method based on improved symplectic geometry modal decomposition (ISGMD) and wavelet threshold (WT). Firstly, the energy contribution (EC) is introduced into the SGMD as an iterative termination condition, which efficiently improves the denoising capability of SGMD and generates a reasonable number of symplectic geometry components (SGCs). Then spectral clustering (SC) is used to accurately aggregate SGCs into information clusters mixed-clusters, and noise clusters. Spectrum entropy (SE) is used to distinguish clusters quickly. Finally, the mixed clusters achieve the signal denoising by wavelet threshold. The useful information is reconstructed to achieve the original signal denoising. In the simulation experiment, the denoising effect of different denoising algorithms in the time domain and frequency domain is compared, and SNR and RMSE are used as evaluation indexes. The results show that the proposed algorithm has better performance. In the experiment of hydrophone, the denoising ability of the proposed algorithm is also verified. [ABSTRACT FROM AUTHOR]

Conducted electromagnetic emissions from interconnecting cables in computer systems can lead to internal information leakage and cause information security problems. However, unintentionally leaked EM signals are characterized by low signal-to-noise ratio and random noise, making it difficult to recover the original signal. In this paper, we propose a denoising model (S-DnCNN) based on an improved DnCNN to better recover the original signal. The network structure consists of three parts: feature mapping generation, low-dimensional feature extraction, and original reconstruction. To improve the noise extraction capability, we use Leaky ReLU as the activation function of the CNN, and introduce a residual structure and a convolutional attention module. The residual structure uses residual hopping to implicitly remove potentially clean images by hidden layer operations, thus training noisy data to recover clean data. We construct a one-dimensional selective convolution kernel (SKConv1d) and fuse it with local paths to form a feature extraction network, which improves the performance of the network. The experimental results show that our proposed method can preserve the details in the effective signal during denoising and shows good generalization to complex SNR data. [ABSTRACT FROM AUTHOR]

Unusual collection of mass tissue in human body is commonly refereed as tumor. The tumor when it is found in brain. These tumor cells have tendency to multiply and grow in rapid speed. The growth of tumors is generally uncontrollable in nature. Tumor in brain develops along the skull and it evolves to contact with the functioning of the brain. Brain tumor (BT) can be detected at the earlier stages with the help of MRI or CT scan techniques. These scanning techniques are proved to be efficient in detecting the tumor irrespective of its size. Brain tumor being a life‐threatening disease has to be diagnosed at the earliest before it turns to be malignant. The current research work focuses in proposing an efficient image processing techniques by processing the MRI images of human brain which is affected by brain tumor. This process is carried out in two stages as image denoising and image segmentation which are helpful in detecting and localizing the tumor affected region in human brain. Initially, the MRI image is read and preprocessed by converting the input image into a grayscale image and noise removed by involving the proposed method. Later, the proposed image is segmented using sobel edge detection method and the image is enhanced using the image enhancement techniques. It is achieved by using the proficient blended thresholding (PBT) Segmentation method. The performance of the proposed methods is evaluated using PSNR (peak signal noise ratio) and RMSE (root mean square error). The proposed conserve edge scrutinize (CES) filter achieved highest PSNR value. Then segmentation is evaluated by five metrices: Sensitivity, Specificity, Dice, Jaccard, and Accuracy. [ABSTRACT FROM AUTHOR]

Background: Deep learning (DL) CT denoising models have the potential to improve image quality for lower radiation dose exams. These models are generally trained with large quantities of adult patient image data. However, CT, and increasingly DL denoising methods, are used in both adult and pediatric populations. Pediatric body habitus and size can differ significantly from adults and vary dramatically from newborns to adolescents. Ensuring that pediatric subgroups of different body sizes are not disadvantaged by DL methods requires evaluations capable of assessing performance in each subgroup. Purpose: To assess DL CT denoising in pediatric and adult‐sized patients, we built a framework of computer simulated image quality (IQ) control phantoms and evaluation methodology. Methods: The computer simulated IQ phantoms in the framework featured pediatric‐sized versions of standard CatPhan 600 and MITA‐LCD phantoms with a range of diameters matching the mean effective diameters of pediatric patients ranging from newborns to 18 years old. These phantoms were used in simulating CT images that were then inputs for a DL denoiser to evaluate performance in different sized patients. Adult CT test images were simulated using standard‐sized phantoms scanned with adult scan protocols. Pediatric CT test images were simulated with pediatric‐sized phantoms and adjusted pediatric protocols. The framework's evaluation methodology consisted of denoising both adult and pediatric test images then assessing changes in image quality, including noise, image sharpness, CT number accuracy, and low contrast detectability. To demonstrate the use of the framework, a REDCNN denoising model trained on adult patient images was evaluated. To validate that the DL model performance measured with the proposed pediatric IQ phantoms was representative of performance in more realistic patient anatomy, anthropomorphic pediatric XCAT phantoms of the same age range were also used to compare noise reduction performance. Results: Using the proposed pediatric‐sized IQ phantom framework, size differences between adult and pediatric‐sized phantoms were observed to substantially influence the adult trained DL denoising model's performance. When applied to adult images, the DL model achieved a 60% reduction in noise standard deviation without substantial loss in sharpness in mid or high spatial frequencies. However, in smaller phantoms the denoising performance dropped due to different image noise textures resulting from the smaller field of view (FOV) between adult and pediatric protocols. In the validation study, noise reduction trends in the pediatric‐sized IQ phantoms were found to be consistent with those found in anthropomorphic phantoms. Conclusion: We developed a framework of using pediatric‐sized IQ phantoms for pediatric subgroup evaluation of DL denoising models. Using the framework, we found the performance of an adult trained DL denoiser did not generalize well in the smaller diameter phantoms corresponding to younger pediatric patient sizes. Our work suggests noise texture differences from FOV changes between adult and pediatric protocols can contribute to poor generalizability in DL denoising and that the proposed framework is an effective means to identify these performance disparities for a given model. [ABSTRACT FROM AUTHOR]

Background: Although low‐dose computed tomography (CT) imaging has been more widely adopted in clinical practice to reduce radiation exposure to patients, the reconstructed CT images tend to have more noise, which impedes accurate diagnosis. Recently, deep neural networks using convolutional neural networks to reduce noise in the reconstructed low‐dose CT images have shown considerable improvement. However, they need a large number of paired normal‐ and low‐dose CT images to fully train the network via supervised learning methods. Purpose: To propose an unsupervised two‐step training framework for image denoising that uses low‐dose CT images of one dataset and unpaired high‐dose CT images from another dataset. Methods: Our proposed framework trains the denoising network in two steps. In the first training step, we train the network using 3D volumes of CT images and predict the center CT slice from them. This pre‐trained network is used in the second training step to train the denoising network and is combined with the memory‐efficient denoising generative adversarial network (DenoisingGAN), which further enhances both objective and perceptual quality. Results: The experimental results on phantom and clinical datasets show superior performance over the existing traditional machine learning and self‐supervised deep learning methods, and the results are comparable to the fully supervised learning methods. Conclusions: We proposed a new unsupervised learning framework for low‐dose CT denoising, convincingly improving noisy CT images from both objective and perceptual quality perspectives. Because our denoising framework does not require physics‐based noise models or system‐dependent assumptions, our proposed method can be easily reproduced; consequently, it can also be generally applicable to various CT scanners or dose levels. [ABSTRACT FROM AUTHOR]

Low-dose computed tomography (LDCT) imaging can significantly reduce the radiation dose to a patient. However, a low radiation dose will cause considerable noise and artifacts in the image, seriously impacting the clinical diagnosis. To better solve the problems, we propose an edge protection and global attention mechanism densely connected convolutional network (EP–GAMNet) for LDCT denoising. First, edge information was extracted using the improved eight-directional Prewitt operator and then, passed to each convolutional block through skip connections. Subsequently, a multiscale feature extractor and global attention mechanism were used for feature extraction. The final predicted images were then obtained by the noise reduction module. Further, a compound loss function based on mean squared error and perceptual loss was used to enhance the texture detail and improve the visual quality of the image. Extensive experiments on Mayo and piglet datasets showed the effectiveness of the proposed method in reducing noise/artifacts while preserving edges. The peak-signal-to-noise ratio value of CT images of the AAPM dataset processed by the new model is 33.5712, and the structural similarity (SSIM) value is 0.9244. Moreover, it performed better than some classical methods in terms of objective indicators and subjective effects. The proposed model is robust and can effectively retain edge information and extract effective features from LDCT images. Moreover, it is effective in improving LDCT image quality. [ABSTRACT FROM AUTHOR]

Wind energy is gaining importance owing to its renewable and environmentally friendly characteristics. However, the variability and stochastic nature of wind speed makes accurate forecasting difficult. Hence, this study introduces a novel approach (VMD-SCINet) for wind speed forecasting (WSF) by integrating the strengths of variational mode decomposition (VMD) and sample convolution and interaction network (SCINet) architecture for the prediction of wind speed. This study utilizes VMD as a denoising technique for wind speed data and incorporates SCINet to capture global patterns and long-range dependencies for the WSF. The wind speed data acquired from two distinct sites: Leicester, and Portland is used for the evaluation. To evaluate the WSF capability of the proposed hybrid model, it's performance is compared to robust models using data from two wind farms across six different time horizons such as 5-min, 10-min, 15-min, 30-min, 1-hour, and 2-hours. The results from two experiments demonstrate that the proposed approach outperforms other models, leading to a significant improvement in WSF accuracy across all evaluated time intervals. [ABSTRACT FROM AUTHOR]

This paper presents a weakly supervised machine learning method, which we call DAS-N2N, for suppressing strong random noise in distributed acoustic sensing (DAS) recordings. DAS-N2N requires no manually produced labels (i.e. pre-determined examples of clean event signals or sections of noise) for training and aims to map random noise processes to a chosen summary statistic, such as the distribution mean, median or mode, whilst retaining the true underlying signal. This is achieved by splicing (joining together) two fibres hosted within a single optical cable, recording two noisy copies of the same underlying signal corrupted by different independent realizations of random observational noise. A deep learning model can then be trained using only these two noisy copies of the data to produce a near fully denoised copy. Once the model is trained, only noisy data from a single fibre is required. Using a data set from a DAS array deployed on the surface of the Rutford Ice Stream in Antarctica, we demonstrate that DAS-N2N greatly suppresses incoherent noise and enhances the signal-to-noise ratios (SNR) of natural microseismic icequake events. We further show that this approach is inherently more efficient and effective than standard stop/pass band and white noise (e.g. Wiener) filtering routines, as well as a comparable self-supervised learning method based on masking individual DAS channels. Our preferred model for this task is lightweight, processing 30 s of data recorded at a sampling frequency of 1000 Hz over 985 channels (approximately 1 km of fibre) in <1 s. Due to the high noise levels in DAS recordings, efficient data-driven denoising methods, such as DAS-N2N, will prove essential to time-critical DAS earthquake detection, particularly in the case of microseismic monitoring. [ABSTRACT FROM AUTHOR]

Deep network design is a fundamental challenge. A right trade‐off between depth and complexity of convolutional neural networks is of significant importance to applications in low‐level vision tasks. Wider feature maps could be beneficial to performance and generality but would increase computational complexity. In this paper, we rethink the balance between width of the feature maps and depth of the network especially for image restoration tasks including deblurring, dehazing, super‐resolution, and denoising. We explore a new approach to network structure by encouraging more depth to deal with restoration requirements while decreasing the width of some feature maps. Such a slimmer and deeper approach can enhance the performance while maintaining the same level of computational costs. We have experimentally evaluated the performances of the proposed approach on four image restoration tasks and obtained state‐of‐the‐art results on quantitative measures and qualitative assessments, demonstrating the effectiveness of the approach. [ABSTRACT FROM AUTHOR]

The time-domain electromagnetic (TDEM) method is acknowledged for its simplicity in setup and non-intrusive detection capabilities, particularly within shallow subsurface detection methodologies. However, extant TDEM systems encounter constraints when detecting intricate topographies and hazardous zones. The rapid evolution in unmanned aerial vehicle (UAV) technology has engendered the inception of UAV-based time-domain electromagnetic systems, thereby augmenting detection efficiency while mitigating potential risks associated with human casualties. This study introduces the UAV-TDEM system designed explicitly for discerning shallow subsurface targets. The system comprises a UAV platform, a host system, and sensors that capture the electromagnetic response of the area while concurrently recording real-time positional data. This study also proposes a processing technique rooted in robust local mean decomposition (RLMD) and approximate entropy (ApEn) methodology to address noise within the original data. Initially, the RLMD decomposes the original data to extract residuals alongside multiple product functions (PFs). Subsequently, the residual is combined with various PFs to yield several cumulative sums, wherein the approximate entropy of these cumulative sums is computed, and the resulting output signals are filtered using a predetermined threshold. Ultimately, the YOLOv8 (You Only Look Once version 8) network is employed to extract anomalous regions. The proposed denoising method can process data within one second, and the trained YOLOv8 network achieves an accuracy rate of 99.0% in the test set. Empirical validation through multiple flight tests substantiates the efficiency of UAV-TDEM in detecting targets situated up to 1 m below the surface. Both simulated and measured data corroborate the proposed workflow's effectiveness in mitigating noise and identifying targets. [ABSTRACT FROM AUTHOR]

Denoising serves as a critical preprocessing step for the subsequent analysis of the hyperspectral image (HSI). Due to their high computational efficiency, low-rank-based denoising methods that project the noisy HSI into a low-dimensional subspace identified by certain criteria have gained widespread use. However, methods employing second-order statistics as criteria often struggle to retain the signal of the small targets in the denoising results. Other methods utilizing high-order statistics encounter difficulties in effectively suppressing noise. To tackle these challenges, we delve into a novel criterion to determine the projection subspace, and propose an innovative low-rank-based method that successfully preserves the spectral characteristic of small targets while significantly reducing noise. The experimental results on the synthetic and real datasets demonstrate the effectiveness of the proposed method, in terms of both small-target preservation and noise reduction. [ABSTRACT FROM AUTHOR]

A new segmentation and topology denoising method is proposed wherein the laser scanning three-dimensional (3-D) point cloud data and datum points are extracted. The laser scanned 3-D point cloud model is cut in the horizontal plane. The minimum distance between the point cloud data on the horizontal cutting plane and the geodesic line of the datum point is the feature points. The skeleton of the 3-D point cloud model is constituted by the feature points and the point cloud data are segmented according to the skeleton feature points. In the 3-D space of laser scanning point cloud data the original point cloud is transformed in two-dimensional (2-D) space by the spatial topological mapping function. The distance weight is computed by segmented point cloud data. In the process of topological transformation, combining with the distance weight of the sampling point, the topology transformation function is built. The noise point and the non-noise point can be separated by the topology transformation. The large-scale noise points are removed by comparison with a set threshold. The fairing direction of small scale noise is calculated according to the curvature and point cloud density. The small scale noise point is moved along the fairing direction to achieve the effect of denoising of the point cloud data. The method is verified by the point cloud data of laser scanning ring forgings in this paper. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSIs) denoising is a preprocessing step that plays a crucial role in many applications used in Earth observation missions. Low-rank tensor representation can be utilized to restore mixed-noise HSIs, such as those affected by mixed Gaussian, impulse, stripe, and deadline noises. Although there is a considerable body of research on spatial and spectral prior knowledge concerning subspace, the correlation between the spectral continuity and the nonlocal sparsity of the spectral and spatial factors is not yet fully understood. To address this deficiency, in the present study, we determined the correlation between these factors using a cascaded technique, and we describe in this paper the double-factor tensor cascaded-rank (DFTCR) minimization method that was used. The information existing in the nonlocal sparsity property of the spatial factor was employed to promote a geometrical feature representation, and a tensor cascaded-rank minimization approach was introduced as a nonlocal self-similarity to promote restoration quality. The continuity between the difference and nonlocal gradient sparsity constraints of the spectral factor was also introduced to learn the basis. Furthermore, to estimate the solutions of the proposed model, we developed an algorithm based on the alternating direction method of multipliers (ADMM). The performance of the DFTCR method was tested by a comparison with eleven established denoising methods for HSIs. The results showed that the proposed DFTCR method exhibited superior performance in the removal of mixed noise from HSIs. [ABSTRACT FROM AUTHOR]

The conventional back projection (BP) algorithm is an accurate time-domain algorithm widely used for multiple-input multiple-output (MIMO) radar imaging, owing to its independence of antenna array configuration. The time-delay curve correction back projection (TCC-BP) algorithm greatly reduces the computational complexity of BP but suffers from spatial-variant correction, sidelobe interference and background noise due to the use of coherent superposition of echo time-delay curves. In this article, a residual attention U-Net-based (RAU-Net) MIMO radar imaging method that adapts complex noisy scenarios with spatial variation and sidelobe interference is proposed. On the basis of the U-Net underlying structure, we develop the RAU-Net with two modules: a residual unit with identity mapping and a dual attention module to obtain resolution spatial-variant correction and denoising on real-world MIMO radar images. The network realizes MIMO radar imaging based on the TCC-BP algorithm and substantially reduces the total computational time of the BP algorithm on the basis of improving the imaging resolution and denoising capability. Extensive experiments on the simulated and measured data demonstrate that the proposed method outperforms both the traditional methods and learning-imaging methods in terms of spatial-variant correction, denoising and computational complexity. [ABSTRACT FROM AUTHOR]

Gaining the ability to audit the behavior of deep learning (DL) denoising models is of crucial importance to prevent potential hallucinations and adversarial clinical consequences. We present a preliminary version of AntiHalluciNet, which is designed to predict spurious structural components embedded in the residual noise from DL denoising models in low-dose CT and assess its feasibility for auditing the behavior of DL denoising models. We created a paired set of structure-embedded and pure noise images and trained AntiHalluciNet to predict spurious structures in the structure-embedded noise images. The performance of AntiHalluciNet was evaluated by using a newly devised residual structure index (RSI), which represents the prediction confidence based on the presence of structural components in the residual noise image. We also evaluated whether AntiHalluciNet could assess the image fidelity of a denoised image by using only a noise component instead of measuring the SSIM, which requires both reference and test images. Then, we explored the potential of AntiHalluciNet for auditing the behavior of DL denoising models. AntiHalluciNet was applied to three DL denoising models (two pre-trained models, RED-CNN and CTformer, and a commercial software, ClariCT.AI [version 1.2.3]), and whether AntiHalluciNet could discriminate between the noise purity performances of DL denoising models was assessed. AntiHalluciNet demonstrated an excellent performance in predicting the presence of structural components. The RSI values for the structural-embedded and pure noise images measured using the 50% low-dose dataset were 0.57 ± 31 and 0.02 ± 0.02, respectively, showing a substantial difference with a p-value < 0.0001. The AntiHalluciNet-derived RSI could differentiate between the quality of the degraded denoised images, with measurement values of 0.27, 0.41, 0.48, and 0.52 for the 25%, 50%, 75%, and 100% mixing rates of the degradation component, which showed a higher differentiation potential compared with the SSIM values of 0.9603, 0.9579, 0.9490, and 0.9333. The RSI measurements from the residual images of the three DL denoising models showed a distinct distribution, being 0.28 ± 0.06, 0.21 ± 0.06, and 0.15 ± 0.03 for RED-CNN, CTformer, and ClariCT.AI, respectively. AntiHalluciNet has the potential to predict the structural components embedded in the residual noise from DL denoising models in low-dose CT. With AntiHalluciNet, it is feasible to audit the performance and behavior of DL denoising models in clinical environments where only residual noise images are available. [ABSTRACT FROM AUTHOR]

The constant development and the wider usage of computed tomography (CT) has gained the attention of researchers during medical practice related to radiation dose. The intention to eradicate the dosage causes increased artefacts and noise influences the confidentiality of the radiologist. Specifically, various noises like speckle, pepper, impulse, salt and Gaussian noise are determined as the complex source of image noise. Therefore, the enhancements in image reconstruction from the CT image need to be enhanced with the diagnostic performance are a challenging issue related to ill-posed nature. Various CT prediction approaches have given superior outcomes. Moreover, there are fewer works in image denoising using learning approaches as these approaches pretend to reduce mean square error (MSE) among the denoised CT images. The outcomes of the models are compromising and show the visibility of aggressive denoising. This research focuses on modelling an efficient approach for CT image denoising with an adaptive adversarial network model that uses weighted similarity measure ( aa - WSM ). The anticipated model has the key concept of enhancing the performance and reducing the error rate. The proposed model concentrates on migrating the noise distribution and learning the visual perception knowledge to perform the denoising task. The PSNR of the proposed model is 16.6 and SSIM is 0.64 which is comparatively better than existing methods. The suppressed noise is 5.2, artefacts reduction is 3.6 and the overall quality is 3.8 which is nominal than others. The model handles the essential information and manages the error rate with promising outcomes. [ABSTRACT FROM AUTHOR]

Seismic interpretation aims to extract quantitative and interpretable attributes from a seismic image produced using some migration method to inform characteristics of a subsurface reservoir or target of interest. Current paradigms for computing seismic attributes mostly rely on single-task algorithms. We develop an iterative, multitask machine learning method to learn and infer multiple attributes from a seismic image. This method is composed of two stages: a multitask inference stage and a multimodal, multitask refinement stage. The basic mechanism of this method is that we train a multitask inference neural network to estimate a set of attributes, including a relative geological time volume, a denoised higher-resolution seismic image and multiple fault attributes (including probability, dip and strike), from a low-resolution, noisy seismic image; then we input the inferred attributes to a multitask refinement NN to enhance the raw inference results iteratively. The two multitask neural networks are trained separately based on synthetic seismic images and associated labels generated by geological modelling. Applications of this multitask learning and inference method to synthetic and field seismic images show that our method can improve the structural consistency among output seismic attributes compared with single-task neural networks, leading to more reliable automatic interpretation and subsurface characterization. [ABSTRACT FROM AUTHOR]

Digital Reference Objects (DROs) are mathematical phantoms that can serve as a basis for evaluating MR image quality (IQ) in an objective way. Their main purpose is to facilitate the establishment of fully automated and perfectly reproducible IQ metrics to objectively compare different algorithms in MR image formation in a standardized manner. They also allow to re-build parts of standard phantoms. We sample DROs directly in k -space, using analytical formulas for the continuous Fourier transform of primitive shapes. We demonstrate this DRO approach by applying a state-of-the-art CNN-based denoising algorithm that is robust to varying noise levels to noisy images of the resolution section of the well-known ACR phantom for IQ assessment, reconstructed from both measured and simulated k -space data. Applying the CNN-based denoising algorithm to the measured and simulated version of the ACR phantom resolution section produced virtually identical results, as confirmed by visual and quantitative comparison. DROs can help guide technology selection during the development of new algorithms in MR image formation, e.g. , via deep learning. This could be an important step towards reproducible MR image formation. [ABSTRACT FROM AUTHOR]

Multi-shot echo planar imaging is a promising technique to reduce geometric distortions and increase spatial resolution in diffusion-weighted MRI (DWI), at the expense of increased scan time. Moreover, performing DWI in the body requires multiple repetitions to obtain sufficient signal-to-noise ratio, which further increases the scan time. This work proposes to reduce the number of repetitions and perform denoising of high b-value images using a convolutional network denoising trained on single-shot DWI to accelerate the acquisition of multi-shot DWI. Convolutional network denoising is demonstrated to accelerate the acquisition of 2-shot DWI by a factor of 4 compared to the clinical standard on patients with rectal cancer. Image quality was evaluated using qualitative scores from expert body radiologists between accelerated and non-accelerated acquisition. Additionally, the effect of convolutional network denoising on each image quality score was analyzed using a Wilcoxon signed-rank test. Convolutional network denoising would enable to increase the number of shots without increasing scan time for significant geometric artifact reduction and spatial resolution increase. [ABSTRACT FROM AUTHOR]

When a remote sensing camera work in push-broom mode, the obtained image usually contains significant stripe noise and random noise due to differences in detector response and environmental factors. Traditional approaches typically treat them as two independent problems and process the image sequentially, which not only increases the risk of information loss and structural damage, but also faces the situation of noise mutual influence. To overcome the drawbacks of traditional methods, this paper leverages the double low-rank characteristics in the underlying prior of degraded images and presents a novel approach for addressing both destriping and denoising tasks simultaneously. We utilize the commonality that both can be treated as inverse problems and place them in the same optimization framework, while designing an alternating direction method of multipliers (ADMM) strategy for solving them, achieving the synchronous removal of both stripe noise and random noise. Compared with traditional approaches, synchronous denoising technology can more accurately evaluate the distribution characteristics of noise, better utilize the original information of the image, and achieve better destriping and denoising results. To assess the efficacy of the proposed algorithm, extensive simulations and experiments were conducted in this paper. The results show that compared with state-of-the-art algorithms, the proposed method can more effectively suppress random noise, achieve better synchronous denoising results, and it exhibits a stronger robustness. [ABSTRACT FROM AUTHOR]

AbstractIn order to separate the effective components and the noise components after variational mode decomposition (VMD) and improve the denoising effect of VMD, a denoising approach combining VMD with energy value (EV) and VMD (VMD-EV-VMD) is proposed. First, VMD decomposes the original signal into K intrinsic mode functions (IMF) and then calculates the EV of the probability density function of each IMF component. According to the changing trend of energy value, the effective components and the noise components are distinguished. Subsequently, each noise component is decomposed by VMD again, the effective components are selected by calculating the correlation coefficient (CC) between the input component of the second VMD and the IMF obtained from the second VMD. The effective components selected by VMD twice are used for signal reconstruction. Simulation experiments and pipeline leakage signal processing show that the method of VMD-EV-VMD achieves a greater SNR than the methods of EEMD, VMD-EV, and VMD-WT. and it has a smaller MSE and MAE, A better denoising effect is achieved and the pipeline leakage characteristics are more accurately preserved. In addition, the accuracy of the SVM classifier is used to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Laser ultrasonic detection of rail defects has become a new method of rail nondestructive testing. Obtaining accurate rail defect signal is a prerequisite to judge the size of defects and avoid train accidents and ensure driving safety. In order to effectively improve the SNR of defect echo, a denoising algorithm combining CEEMD and wavelet soft threshold was proposed. First, CEEMD decomposition was performed on the signal to determine the demarcation point k of IMF components by autocorrelation function. The signal after k + 1 component was reconstructed. Then, the reconstructed signals were decomposed by wavelet transform. The high frequency coefficients after soft threshold processing and the low frequency coefficients of wavelet transform were reconstructed to complete the denoising of rail surface defect signals. The rail with defect of a depth of 0.5 mm and a width of 0.5 mm was tested and verified by laser ultrasonic experiment. By experiment the denoising method combining CEEMD and wavelet soft threshold suppressed effectively the noise. It retained the detailed characteristics of the defective reflected waves. It achieved the good denoising characteristics. It improves the signal-to-noise ratio by 7.12 and 0.77 dB, respectively, over the EMD denoising algorithm and CEEMD denoising algorithm at 1 dB noise intensity and improves the signal-to-noise ratio by 3.37 and 1.23 dB, respectively, over the EMD denoising algorithm and CEEMD denoising algorithm at 20 dB noise intensity. [ABSTRACT FROM AUTHOR]

Elevated seismic noise for moderate‐size earthquakes recorded at teleseismic distances has limited our ability to see their complexity. We develop a machine‐learning‐based algorithm to separate noise and earthquake signals that overlap in frequency. The multi‐task encoder‐decoder model is built around a kernel pre‐trained on local (e.g., short distances) earthquake data (Yin et al., 2022, https://doi.org/10.1093/gji/ggac290) and is modified by continued learning with high‐quality teleseismic data. We denoise teleseismic P waves of deep Mw5.0+ earthquakes and use the clean P waves to estimate source characteristics with reduced uncertainties of these understudied earthquakes. We find a scaling of moment and duration to be M0 ≃ τ4, and a resulting strong scaling of stress drop and radiated energy with magnitude (Δσ≃M00.21 ${\Delta }\sigma \simeq {M}_{0}^{0.21}$ and ER≃M01.24 ${E}_{R}\simeq {M}_{0}^{1.24}$). The median radiation efficiency is 5%, a low value compared to crustal earthquakes. Overall, we show that deep earthquakes have weak rupture directivity and few subevents, suggesting a simple model of a circular crack with radial rupture propagation is appropriate. When accounting for their respective scaling with earthquake size, we find no systematic depth variations of duration, stress drop, or radiated energy within the 100–700 km depth range. Our study supports the findings of Poli and Prieto (2016, https://doi.org/10.1002/2016jb013521) with a doubled amount of earthquakes investigated and with earthquakes of lower magnitudes. Plain Language Summary: The vibration of the Earth's ground recorded at seismometers carries the seismic signatures of distant earthquakes superimposed to the Earth's natural or anthropogenic noise surrounding the seismic station. We use artificial intelligence technology to separate the weak signals of distant earthquakes from other sources of ground vibrations unrelated to the earthquakes. The separated signal provides new insights into earthquakes, especially those within the Earth's deep interior, most of which have not been investigated due to noise levels. In contrast with shallow earthquakes, deep earthquakes are less efficient at radiating energy, though they exhibit a higher rate of increase in both stress drop and radiated energy as they grow. This may suggest that deep earthquakes tend to be more confined fault surfaces. A dual mechanism between nucleation in the subduction‐zone core and propagation of larger events in the dry mantle explains our observations. Key Points: A neural network is used to double the number of earthquakes for source analyses compared to previous studies by improving the data qualityDenoising teleseismic waves improves the source signature in Mw5.0–6.0 events and reduces uncertainties over all magnitudesLarge deep earthquake ruptures are dissipative and compact relative to crustal earthquakes [ABSTRACT FROM AUTHOR]

Denoising a stationary process |$(X_{i})_{i \in \mathbb{Z}}$| corrupted by additive white Gaussian noise |$(Z_{i})_{i \in \mathbb{Z}}$| is a classic, well-studied and fundamental problem in information theory and statistical signal processing. However, finding theoretically founded computationally efficient denoising methods applicable to general sources is still an open problem. In the Bayesian set-up where the source distribution is known, a minimum mean square error (MMSE) denoiser estimates |$X^{n}$| from noisy measurements |$Y^{n}$| as |$\hat{X}^{n}=\mathrm{E}[X^{n}|Y^{n}]$|⁠. However, for general sources, computing |$\mathrm{E}[X^{n}|Y^{n}]$| is computationally very challenging, if not infeasible. In this paper, starting from a Bayesian set-up, a novel denoising method, namely, quantized maximum a posteriori (Q-MAP) denoiser is proposed and its asymptotic performance is analysed. Both for memoryless sources, and for structured first-order Markov sources, it is shown that, asymptotically, as |$\sigma _{z}^{2} $| (noise variance) converges to zero, |${1\over \sigma _{z}^{2}} \mathrm{E}[(X_{i}-\hat{X}^{\mathrm{QMAP}}_{i})^{2}]$| converges to the information dimension of the source. For the studied memoryless sources, this limit is known to be optimal. A key advantage of the Q-MAP denoiser, unlike an MMSE denoiser, is that it highlights the key properties of the source distribution that are to be used in its denoising. This key property leads to a new learning-based denoising approach that is applicable to generic structured sources. Using ImageNet database for training, initial simulation results exploring the performance of such a learning-based denoiser in image denoising are presented. [ABSTRACT FROM AUTHOR]