Noise Removal Method Research Articles

Noise Reduction in CWRU Data Using DAE and Classification with ViT

With the Fourth Industrial Revolution unfolding worldwide, technologies including the Internet of Things, sensors, and artificial intelligence are undergoing rapid development. These technological advancements have played a significant role in the dramatic growth of the predictive maintenance market for mechanical equipment, prompting active research on noise removal techniques and classification algorithms for the accurate determination of the causes of equipment failure. In this study, time series data were preprocessed using the denoising autoencoder technique, a deep learning-based noise removal method, to improve the accuracy of failure classification from mechanical equipment data. To convert the preprocessed time series data into frequency components, the short-time Fourier transform technique was employed. The fault types of mechanical equipment were classified using the vision transformer (ViT) technique, a deep learning technique that has been actively used in recent image analysis research. Additionally, the classification performance of the ViT-based technique for vibration time series data was comparatively validated against existing classification algorithms. The accuracy of failure classification was the highest when the data, preprocessed using a Denoising Autoencoder (DAE), were classified by a Vision Transformer (ViT).

A new frequency domain denoising method for coal mine transient electromagnetic measuring data

Abstract Due to limitation of space in mine tunnel, only a 2 m × 2 m rectangle coil can be employed to collect the electromagnetic signals for the mine transient electromagnetic analysis. Hence, a small emission magnetic moment and weak detection signal strength will increase the electromagnetic analysis difficulty. Moreover, the transient electromagnetic response signal in mines exhibits exponential decay over time, with late-stage amplitudes being notably small, which makes these signals susceptible to noise interference. As a result, it is necessary to study effective noise removal methods to enhance the signal-to-noise ratio of the late-stage electromagnetic data. Addressing this challenge task, this study proposes a new method for frequency domain denoising of transient electromagnetic data. This new method utilizes the Fourier Transform to convert the original transient electromagnetic data from the time domain to the frequency domain, and then, the noise is identified and removed through the frequency characters. Lastly, the processed frequency domain information is transformed to the time domain by the Fourier Inverse Transform to restore the time domain signals. The effect of this frequency domain denoising method is demonstrated through numerical simulations and underground coal mine field data to show significant noise reduction performance on the abnormality detection in the underground coal mine.

Reconstructing Tibetan Plateau lake bathymetry using ICESat-2 photon-counting laser altimetry

Lake bathymetry is important for quantifying and characterizing underwater morphology and its geophysical state, which is critical for hydrological and ecological studies. Due primarily to the harsh environment of the Tibetan Plateau, there is a severe lack of lake bathymetry measurements, limiting the accurate estimation of total lake volumes and their evolutions. Here, we propose a novel lake bathymetry reconstruction by combining ICESat-2/ATLAS (Advanced Topography Laser Altimetry System) data with a numerical model. An improved grid-based photon noise removal method is used to address the photon signal buried in the background noise during the local daytime. The developed model was validated for seven lakes on the Tibetan Plateau and showed good agreement between simulated and measured lake volumes, with an average absolute percentage error of 8.0 % for maximum water depth and 19.7 % for lake volume simulations. The model was then utilized to estimate the water volume of other lakes by combining it with the self-affine theory. The lake depths obtained from ICESat-2/ATLAS show good agreement (RMSE = 0.69 m; rRMSE = 10.3 %) with available in-situ measurements for lakes with depths <16.5 m, demonstrating the potential of ICESat-2/ATLAS for improved reconstruction of the bathymetry of clear water inland lakes. Our study reveals for the first time, that the Tibetan Plateau has an estimated total lake water volume of 1043.69 ± 341.31 km3 for 33,477 lakes (>0.01 km2) in 2022. Over 70 % (∼734.8 km3) of the lake water storage is concentrated in the Inner Plateau, with the Yellow River basin accounting for 10.9 % (∼113.9 km3), followed by the Indus River basin with 7.2 % (∼75.1 km3). Our study provides a robust method for estimating total lake volumes where in-situ measurements are scarce and can be extended to other clear water lakes, thus contributing to more accurate global assessments and towards comprehensive quantification of Earth's surface water resources distribution.

Fundamental study on ambient noise reduction for analysis of hitting sound of professional baseball players

In recent years, the sound of a hitting ball during a baseball game has focused attention on the American Major League Baseball and Japanese professional baseball. It is reported that information such as the direction and distance of a batted ball can be detected from the sound. The sounds of players hitting the ball are sometimes expressed using various onomatopoeic. In our previous study, we recorded the sound of a baseball hit during hitting practice for players of a university baseball team in the Tokyo metropolitan area in Japan. Relationships between the acoustic characteristics of the sound and the distance and direction of the ball were clarified. In this research, acoustic analysis of professional baseball players' batted ball sounds from Youtube and other videos is used to identify the acoustic features and characteristics of the batted ball. This paper describes the method and accuracy of noise removal around the hitting sound extracted from the video using a convolutional neural network with images.

Averaging fractional Fourier domains for background noise removal applied to digital lensless holographic microscopy

A background noise removal method based on averaging fractional Fourier domains is presented. The method is applied to Digital Lensless Holographic Microscopy (DLHM) intensity reconstructions, where the background is perturbed by the weak yet detrimental presence of information of the twin image. A set of fractional Fourier domains of a DLHM intensity reconstruction is computed and thereafter averaged leading to a sensible reduction of the background noise and, therefore, an increase in the overall contrast of the resulting image. The maximum reach of the fractional rotations used in the method is determined by measuring the spatial resolution in a regular star test target such that the spatial resolution is kept within the span of interest for a given application. The set of images to be averaged is composed of fractional rotations of the original intensity reconstruction that are smaller than the previously determined maximum reach. The number of fractional rotations that are finally averaged is determined by the sought increase in the contrast of the resulting image. Experimental samples of micrometer-sized objects and an intricate biological specimen have been used to validate the proposal.

Destriping model for adaptive removal of arbitrary oriented stripes in remote sensing images

Abstract Destriping in remote sensing image processing remains a challenging problem, particularly when dealing with stripe noise of arbitrary orientations. Conventional methods struggle to eliminate oblique stripes, leaving a crucial gap in the production of higher-level remote sensing products. In response, we propose a novel destriping model, the Adaptive Stripe Noise Removal (ASNR) Method, designed to adapt to different orientations of stripe noise, aiming for accuracy, robustness, speed, and simplicity. The paper first addresses the conventional challenges in stripe removal, emphasizing the unintended loss of information during the process. To overcome this, we conduct a detailed study of stripe noise characteristics, employing traditional Fast Fourier Transform (FFT) for stripe orientation approximation. However, conventional techniques using spatial representations risk damaging detailed structures. To go beyond these limitations, the proposed method combines spectral processing technology with an image guidance mechanism. This approach aims to generate a guided image that retains both denoised features and important details. In the frequency domain, the method corrects the stripe image by estimating a guidance image. Experimental results, both qualitative and quantitative, demonstrate the superiority and stability of the proposed method in removing stripe noise and preserving image details without introducing artifacts. The novel approach fills a critical gap in destriping methods, offering a fast, accurate, and adaptable solution for arbitrary orientations of stripe noise in remote sensing images.

A Novel Multi-Image Stripe Noise Removal Method Based on Wavelet and Recurrent Networks

A Novel Multi-Image Stripe Noise Removal Method Based on Wavelet and Recurrent Networks

Revisiting the OBS seafloor compliance signal removal with a stationarity and stacking-based approach: the BRUIT-FM toolbox

Summary This study focuses on improving the seafloor compliance noise removal method, which relies on estimates of the compliance transfer function frequency response (the deformation of the seafloor under long-period pressure waves). We first propose a new multi-scale deviation analysis of broadband ocean bottom seismometer data to evaluate stationarity properties that are key to the subsequent analysis. We then propose a new approach to removing the compliance noise from the vertical channel data, by stacking daily estimated transfer function frequency responses over a period of time. We also propose an automated transient event detection and data selection method based on a cross-correlation criterion. As an example, we apply the method to data from the Cascadia Initiative (network 7D2011). We find that the spectral extent of long-period forcing waves varies significantly over time so that standard daily transfer function calculation techniques poorly estimate the transfer function frequency response at the lowest frequencies, resulting in poor denoising performance. The proposed method more accurately removes noise at these lower frequencies, especially where coherence is low, reducing the mean deviation of the signal in our test case by 27 % or more. We also show that our calculated transfer functions can be transfered across time periods. The method should allow better estimates of seafloor compliance and help to remove compliance noise at stations with low pressure-acceleration coherence. Our results can be reproduced using the BRUIT-FM Python toolbox, available at https://gitlab.ifremer.fr/anr-bruitfm/bruit-fm-toolbox.

Adaptive dual-domain filtering for random seismic noise removal

Random noise significantly reduces the signal-to-noise ratio of seismic data and affects the accuracy of seismic interpretation. Traditional denoising methods typically require manual parameter tuning to increase robustness and accuracy across various random noise levels. In this study, based on the statistical definition of random noise, we use the variance of random noise as the level of random noise and develop an adaptive dual-domain filter (ADDF). The ADDF method estimates the random noise variance in the seismic data and uses this estimation to effectively denoise the seismic data. First, we use a difference operator in two directions to remove the useful structures from the seismic data. The processed data are then used to estimate the global random noise variance through iterative statistical processing. In the denoising process of the ADDF, the seismic data are masked by a bilateral filter in the spatial domain, followed by a short-time Fourier transform with wavelet shrinkage in the frequency domain, both controlled by the adaptively estimated random noise variance. The dual-domain filter is applied iteratively for the best performance. Synthetic experiments demonstrate the robustness of the ADDF in accurately estimating the noise variance without tuning parameters, and its superior denoising performance is evident in synthetic examples and field data when compared with two typical denoising methods: f- x deconvolution and curvelet domain thresholding. As an adaptive random noise estimation and removal method, ADDF relies only on seismic data, making denoising random noise more objective and accurate without manual adjustment.

Interpretation and use of coherence in multi-channel measurements

The coherence function can be a powerful tool when analyzing data from multi-channel measurements. Often, coherence is used to describe the amount of incoherent noise in an output signal, though more generally the coherence between two signals is a representation of the linearity of the relationship between the signals as a function of frequency. Such degradation in the coherence then can be understood to not only be caused by potential incoherent noise, but also by moving sensors or a changing acoustic environment. Aside from its use as a diagnostic tool, coherence can also be used to condition measured data. For example, a sensor can be placed on a source of unwanted sound, and the portion of the desired signal coherent with the sensor's output (the "coherent output power") can be removed. In this paper, methods for coherent noise removal and signal enhancement are presented in both the frequency and time domains. Example measurements are used to demonstrate the effectiveness of the techniques for situations where separating noise sources is otherwise difficult.

Nonlocal Matrix Rank Minimization Method for Multiplicative Noise Removal

Nonlocal Matrix Rank Minimization Method for Multiplicative Noise Removal

Identifying Plausible Labels from Noisy Training Data for a Land Use and Land Cover Classification Application in Amazônia Legal

Most studies in the field of land use and land cover (LULC) classification in remote sensing rely on supervised classification, which requires a substantial amount of accurate label data. However, reliable data are often not immediately available, and are obtained through time-consuming manual labor. One potential solution to this problem is the use of already available classification maps, which may not be the true ground truth and may contain noise from multiple possible sources. This is also true for the classification maps of the MapBiomas project, which provides land use and land cover (LULC) maps on a yearly basis, classifying the Amazon basin into more than 24 classes based on the Landsat data. In this study, we utilize the Sentinel-2 data with a higher spatial resolution in conjunction with the MapBiomas maps to evaluate a proposed noise removal method and to improve classification results. We introduce a novel noise detection method that relies on identifying anchor points in feature space through clustering with self-organizing maps (SOM). The pixel label is relabeled using nearest neighbor rules, or can be removed if it is unknown. A challenge in this approach is the quantification of noise in such a real-world dataset. To overcome this problem, highly reliable validation sets were manually created for quantitative performance assessment. The results demonstrate a significant increase in overall accuracy compared to MapBiomas labels, from 79.85% to 89.65%. Additionally, we trained the L2HNet using both MapBiomas labels and the filtered labels from our approach. The overall accuracy for this model reached 93.75% with the filtered labels, compared to the baseline of 74.31%. This highlights the significance of noise detection and filtering in remote sensing, and emphasizes the need for further research in this area.

Importing Diffusion and Re-Designed Backward Process for Image De-Raining.

In recent years, with the increasing demand for high-quality images in various fields, more and more attention has been focused on noise removal techniques for image processing. The effective elimination of unwanted noise plays a crucial role in improving image quality. To meet this challenge, many noise removal methods have been proposed, among which the diffusion model has become one of the focuses of many researchers. In order to make the restored image closer to the real image and retain more features of the image, this paper proposes a DIR-SDE method with reference to the diffusion models of IR-SDE and IDM, which improve the feature retention of the image in the de-raining process, and then improve the realism of the image for the image de-raining task. In this study, IR-SDE was used as the base structure of the diffusion model, IR-SDE was improved, and DINO-ViT was combined to enhance the image features. During the diffusion process, the image features were extracted using DINO-ViT, and these features were fused with the original images to enhance the learning effect of the model. The model was also trained and validated with the Rain100H dataset. Compared with the IR-SDE method, it improved 0.003 in the SSIM, 0.003 in the LPIPS, and 1.23 in the FID. The experimental results show that the diffusion model proposed in this study can effectively improve the image restoration performance.

Projection domain decomposition denoising algorithm based on low rank and similarity-based regularization.

Projection Domain Decomposition (PDD) is a dual energy reconstruction method which implements the decomposition process before image reconstruction. The advantage of PDD is that it can alleviate beam hardening artifacts and metal artifacts effectively as energy spectra estimation is considered in PDD. However, noise amplification occurs during the decomposition process, which significantly impacts the accuracy of effective atomic number and electron density. Therefore, effective noise reduction techniques are required in PDD. This study aims to develop a new algorithm capable of minimizing noise while simultaneously preserving edges and fine details. In this study, a denoising algorithm based on low rank and similarity-based regularization (LRSBR) is presented. This algorithm incorporates the low-rank characteristic of tensors into similarity-based regularization (SBR) framework. This method effectively addresses the issue of instability in edge pixels within the SBR algorithm and enhances the structural consistency of dual-energy images. A series of simulation and practical experiments were conducted on a dual-layer dual-energy CT system. Experiments demonstrate that the proposed method outperforms exiting noise removal methods in Peak Signal-to-noise Ratio (PSNR), Root Mean Square Error (RMSE), and Structural Similarity (SSIM). Meanwhile, there has been a notable enhancement in the visual quality of CT images. The proposed algorithm has a significantly improved noise reduction compared to other competing approach in dual-energy CT. Meanwhile, the LRSBR method exhibits outstanding performance in preserving edges and fine structures, making it practical for PDD applications.

Non-proportionality quantification of noisy stress-time signals using a new rainflow-based noise removal method for fatigue assessment

Non-proportional stresses near welded joints are well known to cause increased fatigue damages as compared to proportional stresses. In this paper, a new method to remove noise from stress-time signals is developed and implemented in a principal component analysis-based approach for non-proportionality quantification. The noise removal method makes it possible to remove noise from stress-time signals causing low stress ranges, while still keeping the overall shape of the signal. When the signal shape is kept it is possible to accurately predict the levels of non-proportionality. The noise removal method is based on the standard rainflow counting method. By choosing a lower stress range limit, the stress ranges assumed to be caused by noise can be excluded and the original signal shape is kept by utilizing simple polynomial fitting. This makes the approach easy to implement and easy to control as it requires only two inputs. The noise removal method and non-proportionality quantification approach are then validated against simulated signals with noise and a simple experiment with proportional loading. The results show that the newly developed method for noise reduction accurately removes noise while keeping the signal shape.

Evaluation of high-frequency roughness measurement errors for composite and ceramic surfaces after machining

Precise characterisation of surface topography is of the greatest importance since many factors directly affect the accuracy of the whole measurement process. In this paper, the variety of surface topographies from machined composite and ceramic workpieces was studied with a special emphasis on the measurement results. Surfaces were subjected to the ground diamond, honing and milling processes. Measurement results were analysed in terms of the application of the procedure for the removal of the high-frequency noise. Bandwidth characteristics were supported by the studies of autocorrelation and power spectral functions. It was found, that examination of noisy data, especially its isotropic properties, is crucial in the enhancement of the noise-removal methods. The proposed procedure was validated through direction and profile characterisation. The spline filtering technique with a 7.5 μm cut-off was encouraged against other generally used filtering techniques for the reduction of high-frequency measurement noise considering the study based on the power spectral, autocorrelation and direction functions. The proposed methodology was validated by comparing it to the averaged results of 3 time repeated measurements of the composite and ceramic surfaces after machining. The main advantage of the proposal is reducing the time of data processing due to the fast and easy-to-implement usage of general surface topography analysis functions, available in the commercial software of the measuring instrument.

Design and Implementation of DSLMS Algorithm Based Photoelectric Detection of Weak Signals

Accurately extracting weak signals is extremely important for overall performance and application in optoelectronic imaging and optical communication systems. While weak signals are susceptible to noise, adaptive filtering is a commonly used noise removal method. Still, its convergence speed is slow, the steady-state error is large, and the anti-interference ability is weak. To solve the above problems, this paper proposes a new type of variable-step-length adaptive filtering algorithm (DSLMS) based on the minutiae function, which effectively reduces the noise component in error through its combination with the pair cancelation system, utilizing the low correlation property of the noise signal, to improve the anti-noise interference ability of the adaptive filter. Using FPGA and Matlab (2018b) for experimental verification, the results show that this algorithm shows significant advantages in noise suppression, accelerated algorithm convergence, and low steady-state error, and it has effectiveness and application potential for the optoelectronic detection of weak signal processing.

Snoring noise removal method for bowel sound signal during sleep

Monitoring of bowel sounds is an important method to assess bowel motility during sleep, but it is seriously affected by snoring noise. In this paper, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method was applied to remove snoring noise from bowel sounds during sleep. Specifically, the noisy bowel sounds were first band-pass filtered, then decomposed by the CEEMDAN method, and finally the appropriate components were selected to reconstruct the pure bowel sounds. The results of semi-simulated and real data showed that the CEEMDAN method was better than empirical mode decomposition and wavelet denoising method. The CEEMDAN method is used to remove snoring noise from bowel sounds during sleep, which lays an important foundation for using bowel sounds to assess the intestinal motility during sleep.

Joint magnetic resonance imaging artifacts and noise reduction on discrete shape space of images

Magnetic resonance (MR) images can be corrupted by artifacts and noise, potentially leading to misinterpretation of the images. In this paper, we propose a novel approach based on the discrete shape space of images (DSSI) to jointly reduce artifacts and noise in MR images. The proposed method restores MR images in multiple domains based on the distinct generation mechanisms of noise and artifacts. The images in multiple domains are analyzed in a non-Euclidean space. The DSSI is constructed as a Riemannian manifold to measure the intrinsic properties of images. Images are considered shapes from a geometric perspective, and the impact of similarity transformations (e.g., rotation, scaling, and translation) on image analysis is eliminated. The patch-based rank-ordered difference (PROD) detector is defined in k-space within the framework of DSSI to detect and remove sparse outliers that cause artifacts. In addition, a novel similarity function for images is defined using the DSSI and be used to design the improved filter. Finally, the convergence of the improved filter is theoretically analyzed, indicating that our method offers an effective estimator of the ideal image. The experimental results of various MR images demonstrate that the proposed approach outperforms classical and state-of-the-art methods for artifact correction and noise removal, both qualitatively and quantitatively.

EMD AND WAVELET-BASED ECG SIGNAL DENOISING AND QRS COMPLEX DETECTION

This project presents a novel method for noise removal and QRS complex detection in electrocardiogram (ECG) signals, employing Empirical Mode Decomposition (EMD), windowing, and wavelet thresholding techniques. Noise is added to the ECG signal, and EMD is applied to obtain denoised components. Local minima detection and peak matching identify QRS complex boundaries. Windowing isolates the QRS regions, followed by wavelet thresholding for further denoising. Evaluation metrics like improved Signal-to-Noise Ratio, Mean Square Error, and Percent Root Mean Square Difference are calculated at different input SNR values, demonstrating the method's effectiveness in preserving the QRS complex while removing noise.. Keywords: ECG signal processing, QRS complex detection, Empirical Mode Decomposition (EMD), Windowing, Wavelet thresholding, QRS complex extraction, Signal-to-Noise Ratio (SNR), Mean Square Error (MSE), Percent Root Mean Square Difference (PRD).