Levels Of Gaussian Noise Research Articles

A noise-enhanced machine fault diagnosis method with multi-channel information fusion

ABSTRACT Condition health monitoring and fault diagnosis is able to safeguard against potential threats to machines. Nevertheless, the acquired signals by using a plenty of sensors are often accompanied by noise and meanwhile the useful information contained in the signals is not both complete and reliable, thereby together reducing the accuracy and stability of the fault diagnosis. Therefore, this paper proposes a noise-enhanced intelligent fault diagnosis method with multi-channel information fusion. Here, it would inject the varying levels of Gaussian noise into multi-channel input data as well as intelligent diagnostic models, with a view to elucidating the benefits of noise. Furthermore, the proposed method is validated through three experiments. The experimental results demonstrate that the diagnostic accuracy of the hydraulic motor and the two different bearings reaches 99.85%, 99.89%, and 99.85% by using the proposed method, respectively, which are increased by 2.50%, 4.09%, and 2.50%, respectively, compared with one without the injection of noise. In addition, by comparing the diagnostic accuracy of ones with single-channel and multi-channel information fusion under the optimal noise level in both cases, it is found that one with multi-channel information fusion shows an average of 3.20% increase than the single-channel one.

Adaptive nonlinear filtering algorithms for removal of non-stationary noise in electronystagmographic signals

Non-stationary physiological noise poses significant difficulties due to its time-varying and previously unknown characteristics. When processing electronystagmographic signals, linear filtering can distort diagnostically significant rapid changes caused by saccadic eye movements. In such cases, nonlinear filters based on robust estimators are more appropriate, whereas linear filtering effectively reduces white noise in parts of a signal with linear behaviour. Therefore, an adaptive signal processing approach that varies in nonlinearity from highly nonlinear robust estimation to linear averaging and combines their benefits appears promising. We have proposed a low-complexity adaptive method for switching filter sets and relevant filter parameter settings based on the estimated noise level and local signal behaviour. This method does not require time for filter parameter modification and does not need prior information on the signal model and noise variance. Based on this method, we have designed adaptive nonlinear filtering algorithms to exploit the advantages of both the nonlinear robust and linear averaging estimators. We have evaluated the filtering quality statistically using the minimum mean square error criteria and the maximum signal-to-noise ratio for a model signal with different levels of additive Gaussian noise. The proposed real-time adaptive filtering algorithms demonstrate a significant efficiency improvement compared to the commonly used filters. The proposed adaptive myriad algorithm achieves the highest efficiency by adjusting a sample myriad linearity parameter depending on the local estimate of a signal scale and changing the sliding window length and the coefficient affecting the linearity parameter.

A Violet‐Light‐Responsive ReRAM Based on Zn2SnO4/Ga2O3 Heterojunction as an Artificial Synapse for Visual Sensory and In‐Memory Computing

AbstractDue to the imitation of the neural functionalities of the human brain via optical modulation of resistance states, photoelectric resistive random access memory (ReRAM) devices attract extensive attraction for synaptic electronics and in‐memory computing applications. In this work, a photoelectric synaptic ReRAM (PSR) of the structure of ITO/Zn2SnO4/Ga2O3/ITO/glass with a simple fabrication process is reported to imitate brain plasticity. Electrically induced long‐term potentiation/depression (LTP/D) behavior indicates the fulfillment of the fundamental requirement of artificial neuron devices. Classification of three‐channeled images corrupted with different levels (0.15–0.9) of Gaussian noise is achieved by simulating a convolutional neural network (CNN). The violet light (405 nm) illumination generates excitatory post synaptic current (EPSC), which is influenced by the persistent photoconductivity (PPC) effect after discontinuing the optical excitation. As an artificial neuron device, PSR is able to imitate some basic neural functions such as multi‐levels of photoelectric memory with linearly increasing trend, and learning‐forgetting‐relearning behavior. The same device also shows the emulation of visual persistency of optic nerve and skin‐damage warning. This device executes high‐pass filtering function and demonstrates its potential in the image‐sharpening process. These findings provide an avenue to develop oxide semiconductor‐based multifunctional synaptic devices for advanced in‐memory photoelectric systems.

SwinDenoising: A Local and Global Feature Fusion Algorithm for Infrared Image Denoising

Infrared image denoising is a critical task in various applications, yet existing methods often struggle with preserving fine details and managing complex noise patterns, particularly under high noise levels. To address these limitations, this paper proposes a novel denoising method based on the Swin Transformer architecture, named SwinDenoising. This method leverages the powerful feature extraction capabilities of Swin Transformers to capture both local and global image features, thereby enhancing the denoising process. The proposed SwinDenoising method was tested on the FLIR and KAIST infrared image datasets, where it demonstrated superior performance compared to state-of-the-art methods. Specifically, SwinDenoising achieved a PSNR improvement of up to 2.5 dB and an SSIM increase of 0.04 under high levels of Gaussian noise (50 dB), and a PSNR increase of 2.0 dB with an SSIM improvement of 0.03 under Poisson noise (λ = 100). These results highlight the method’s effectiveness in maintaining image quality while significantly reducing noise, making it a robust solution for infrared image denoising.

Low-sampling and noise-robust single-pixel imaging based on the untrained attention U-Net

The single-pixel imaging (SPI) technique illuminates the object through a series of structured light fields and detects the light intensity with a single-pixel detector (SPD). However, the detection process introduces a considerable amount of unavoidable white noise, which has a detrimental effect on the image quality and limits the applicability of SPI. In this paper, we combine the untrained attention U-Net with the SPI model to reduce noise and achieve high-quality imaging at low sampling rates. The untrained U-Net has the advantage of not requiring pre-training for better generalization. The attention mechanism can highlight the main features of the image, which greatly suppresses the noise and improves the imaging quality. Numerical simulations and experimental results demonstrate that the proposed method can effectively reduce different levels of Gaussian white noise. Furthermore, it can obtain better imaging quality than existing methods at a low sampling rate of less than 10%. This study will expand the application of SPI in complex noise environments.

Simultaneous prediction of petrophysical properties and formation layered thickness from acoustic logging data using a modular cascading residual neural network (MCARNN) with physical constraints

Predicting petrophysical properties from logging data using deep neural networks (DNNs) improves the efficiency of subsurface exploration. Traditional methods, however, heavily rely on data pre-processing. Therefore, a novel Modular Cascading Residual Neural Network (MCARNN) is proposed to simultaneously retrieve layered thickness and petrophysical properties of porous media directly from raw acoustic logging data without pre-processing. The MCARNN mainly comprises two cascading modules: the first is tasked with retrieving layered thickness, while the second one further reconstructs petrophysical properties based on the thickness information. To more accurately simulate the uncertainties of the real world, we incorporate some known geophysical knowledge, including the distribution range of actual petrophysical parameters, physical constraints among porous medium parameters, configurations of logging instruments, and stratified geological models. During this process, all Biot's porous parameters are independently randomized to cover a wide range of geological rock types. Furthermore, to enhance MCARNN's generalization ability under different random noise distributions, we independently generate the training and testing datasets using distinct numerical algorithms, thus preventing the “inverse crime” phenomenon. Additionally, varying levels of Gaussian white noises are added to the training dataset, and the transmitter-receiver configuration of the logging instrument is varied to enhance the training dataset. Two numerical experiments are implemented to validate the reliability and superiority of the MCARNN. It is shown that the proposed MCARNN can not only accurately predict porous petrophysical parameters when the background layer configurations are known but also be able to simultaneously reconstruct layered thickness and petrophysical parameters with low model misfit. Notably, MCARNN successfully predicts the porous velocity dispersion curves within a broad frequency band based on limited frequency points—a task typically requiring auxiliary equations in traditional inversion methods, demonstrating the advanced predictive capability of the proposed MCARNN. Through this research, we not only address the deficiencies in existing real-world logging datasets in terms of sample volume and label reliability but also effectively integrate rock physics models with data-driven neural networks, providing a novel and effective pathway for reservoir parameter prediction in the field of geophysical logging.

Plant-Denoising-Net (PDN): A plant point cloud denoising network based on density gradient field learning

Effective point cloud denoising is critical in 3D plant phenotyping applications, which reduces interference in subsequent algorithms and improves the accuracy of plant phenotypes measurement. Deep learning-based point cloud denoising algorithms have shown excellent denoising performance on simple CAD models. However, these algorithms suffer from issues including over-smoothing or shrinkage and low efficiency when applied on density uneven, incomplete, various types of noise and complex plant point clouds. We proposed a plant point cloud denoising network (PDN) based on point cloud density gradient field learning, which can effectively address the challenges posed by plant point clouds. PDN consists of three main modules: point density feature (PDF) exception module, umbrella operator feature (UOF) computation module, and point density gradient (DG) estimation module. The performance of PDN was evaluated in experiments using point clouds of multiple plant species with noise of different types. Under different levels of Gaussian noise, our method achieved a relative performance improvement of 7.6%-19.3% compared to the state-of-the-art baseline methods, reaching state-of-the-art denoising performance. For noise of different types, the majority of our denoising results outperformed the baseline methods. In addition, our method was 0.5 and 8.6 times faster than the baseline methods when processing point clouds with low and high noise level, respectively. The good robustness, generalization, and computational efficacy of PDN are expected to facilitate the acquisition of high-precision 3D point clouds for various plant species, enhance the versatility of 3D phenotyping methods, improve the accuracy of the measurement of structural phenotypes, and increase the throughput of data processing, therefore facilitate the development of modern breeding research. The source code and the datasets used in this study is available on GitHub at https://github.com/suetme/PDN-plant-denoising-net.

Using a deep learning prior for accelerating hyperpolarized 13C MRSI on synthetic cancer datasets.

We aimed to incorporate a deep learning prior with k-space data fidelity for accelerating hyperpolarized carbon-13 MRSI, demonstrated on synthetic cancer datasets. A two-site exchange model, derived from the Bloch equation of MR signal evolution, was firstly used in simulating training and testing data, that is, synthetic phantom datasets. Five singular maps generated from each simulated dataset were used to train a deep learning prior, which was then employed with the fidelity term to reconstruct the undersampled MRI k-space data. The proposed method was assessed on synthetic human brain tumor images (N = 33), prostate cancer images (N = 72), and mouse tumor images (N = 58) for three undersampling factors and 2.5% additive Gaussian noise. Furthermore, varied levels of Gaussian noise with SDs of 2.5%, 5%, and 10% were added on synthetic prostate cancer data, and corresponding reconstruction results were evaluated. For quantitative evaluation, peak SNRs were approximately 32 dB, and the accuracy was generally improved for 5 to 8 dB compared with those from compressed sensing with L1-norm regularization or total variation regularization. Reasonable normalized RMS error were obtained. Our method also worked robustly against noise, even on a data with noise SD of 10%. The proposed singular value decomposition + iterative deep learning model could be considered as a general framework that extended the application of deep learning MRI reconstruction to metabolic imaging. The morphology of tumors and metabolic images could be measured robustly in six times acceleration using our method.

An Experimental Study for Evaluating the Performance of CNN Pre-Trained Models in Noisy Environments

This work aims at testing the efficiency of the pre-trained models in terms of classifying images in noisy environments. To this end, we proposed injecting Gaussian noise into the images in the used datasets gradually to see how the performance of that models can be affected by the proportion of the noise in the image. Afterward, three different case studies have been conducted for evaluating the performance of six different well-known pre-trained models namely MobileNet, ResNet, GoogleNet, EfficientNet, VGG19, and Xception. In the first case study, it has been proposed to train these models using a high-quality image dataset and test them using the same datasets after injecting their images with different levels of Gaussian noise. In the second case study, we proposed training the models using the created noisy image datasets in order to investigate how the training process can be affected by the noises in the environment. In the third case study, we proposed using the non-local means algorithm to denoise the images in the noisy datasets and testing the models trained using the original datasets using these de-noised image datasets. To the best of our knowledge, this is the first time that the effects of noise on well-known pre-trained CNN architectures have been comprehensively investigated with this number of considered models. The obtained results showed that while these types of models can work very well in ideal environments their performances can drop down due to the conditions of the working environment, which reflects the need for some auxiliary models that should be used as a pre-processing phase to improve the performance of these models.

Echo State Property upon Noisy Driving Input

The echo state property (ESP) is a key concept for understanding the working principle of the most widely used reservoir computing model, the echo state network (ESN). The ESP is achieved most of the operation time under general conditions, yet the property is lost when a combination of driving input signals and intrinsic reservoir dynamics causes unfavorable conditions for forgetting the initial transient state. A widely used treatment, setting the spectral radius of the weight matrix below the unity, is not sufficient as it may not properly account for the nature of driving inputs. Here, we characterize how noisy driving inputs affect the dynamical properties of an ESN and the empirical evaluation of the ESP. The standard ESN with a hyperbolic tangent activation function is tested using the MNIST handwritten digit datasets at different additive white Gaussian noise levels. The correlations among the neurons, input mapping, and memory capacity of the reservoir nonlinearly decrease with the noise level. These trends agree with the deterioration of the MNIST classification accuracy against noise. In addition, the ESP index for noisy driving input is developed as a tool to help easily assess ESPs in practical applications. Bifurcation analysis explicates how the noise destroys an asymptotical convergence in an ESN and confirms that the proposed index successfully captures the ESP against noise. These results pave the way for developing noise-robust reservoir computing systems, which may promote the validity and utility of reservoir computing for real-world machine learning applications.

Wave-based fault detection in concrete by the Full Waveform Inversion considering noise

In the field of non-destructive testing of concrete, the use of ultrasonic waves became state of the art, among other techniques. Nevertheless, there is still room for improvement, in particular concerning the resolution and robustness of the monitoring results.One approach is the application of the Full Waveform Inversion (FWI) originating from geotechnical engineering, known here as seismic tomography. The forward and backpropagation of waves within a numerical model are deployed to identify material parameters, like the primary and secondary wave velocity as well as density. This approach forms a non-linear, and ill-posed mathematical problem. Its solution is computationally demanding and time-consuming.Within the presented approach, the Full Waveform Inversion is used on a numerically simulated artificial concrete specimen of relatively large dimensions. Here, the synthetic ultrasound data is compromised by the consideration of different levels of Gaussian white noise. Additionally, several sizes and positions of faults are computed to simulate a variety of possible defects within the concrete material as in reality. Subsequently, the identifiability of the fault together with its recognition quality are investigated. Additionally, recommendations on sensor positioning and layout are given.

Nonconvex fractional order total variation based image denoising model under mixed stripe and Gaussian noise

In this paper, we propose a minimization-based image denoising model for the removal of mixed stripe and Gaussian noise. The objective function includes the prior information from both the stripe noise and image. Specifically, we adopted a unidirectional regularization term and a nonconvex group sparsity term for the stripe noise component, while we utilized a nonconvex fractional order total variation (FTV) regularization for the image component. The priors for stripes enable adequate extraction of periodic or non-periodic stripes from an image in the presence of high levels of Gaussian noise. Moreover, the nonconvex FTV facilitates image restoration with less staircase artifacts and well-preserved edges and textures. To solve the nonconvex problem, we employed an iteratively reweighted $ \ell_1 $ algorithm, and then the alternating direction method of multipliers was adopted for solving subproblems. This led to an efficient iterative algorithm, and its global convergence was proven. Numerical results show that the proposed model provides better denoising performance than existing models with respect to visual features and image quality evaluations.

High precision of sign language recognition based on In2O3 transistors gated by AlLiO solid electrolyte

In recent years, the synaptic properties of transistors have been extensively studied. Compared with liquid or organic material-based transistors, inorganic solid electrolyte-gated transistors have the advantage of better chemical stability. This study uses a simple, low-cost solution technology to prepare In2O3 transistors gated by AlLiO solid electrolyte. The electrochemical performance of the device is achieved by forming a double electric layer and electrochemical doping, which can mimic basic functions of biological synapses, such as excitatory postsynaptic current, paired-pulse promotion, and spiking time-dependent plasticity. Furthermore, complex synaptic behaviors such as Pavlovian classical conditioning is successfully emulated. With a 95% identification accuracy, an artificial neural network based on transistors is built to recognize sign language and enable sign language interpretation. Additionally, the handwriting digit’s identification accuracy is 94%. Even with various levels of Gaussian noise, the recognition rate is still above 84%. The above findings demonstrate the potential of In2O3/AlLiO TFT in shaping the next generation of artificial intelligence.

Distribution system identification using FISTA algorithm

The network parameters of the distribution system play a very important role for the network operator in performing a timely and satisfactory operation. Therefore, they require to be updated on a time-to-time basis otherwise it may lead to non-optimal operation of the distribution system. To deal with this issue, the reformulation strategy and the fast iterative shrinkage-thresholding approach (FISTA) algorithm are designed herein to accomplish the network identification objectives using distribution phasor measurement units (D-PMUs) measurements. The presented algorithm has capabilities to determine the manifold tasks such as the identification of structure of the distribution system, variation in network configuration, branch parameters (e.g., conductance and susceptance), and changes in branch parameters. Simulation is performed with the help of the synchronized dataset to validate the efficacy of the presented algorithm on the manifold benchmarked testbeds such as IEEE 34-bus and IEEE 13-bus systems. Additionally, the FISTA algorithm demonstrates excellent performance even with the presence of a certain level of Gaussian noise in the D-PMU measurements. To illustrate the efficacy of the presented work over the state-of-art methods, the comparative analysis is carried out on the benchmarked test cases.

A Bearing Fault Diagnosis Method Based on Dilated Convolution and Multi-Head Self-Attention Mechanism

Rolling bearings serve as the fundamental components of rotating machinery. Failure to detect damage early in these components can result in equipment shutdown, leading not only to economic losses but also to a threat to worker safety. Given the diverse range of rotating parts, it is crucial to promptly identify and accurately diagnose early bearing failures during the maintenance of large-scale machinery. To achieve quick and precise fault diagnosis, this study proposes a method based on dilated convolution, a Bidirectional Gated Recurrent Unit (BiGRU), and a multi-head self-attention mechanism. The key advantage lies in its ability to directly process raw 1D sampled data without requiring complex time–frequency domain conversion. To validate the model’s accuracy and stability, we conducted empirical studies using both the HUST bearing dataset proposed by Thuan, Nguyen et al. and the CWRU bearing dataset from Western Reserve University. The results demonstrate that our model achieves an impressive accuracy rate of 99.94%, along with an f1 value for the test set when dealing with multiple operating conditions for all five types of bearings in the HUST dataset. Moreover, when applied to the CWRU dataset, these two metrics even reached 99.95%. Furthermore, the proposed model achieves a significant prediction accuracy of more than 98.5% on two datasets containing different types of noise and different levels of white Gaussian noise, highlighting its great potential in practical applications of early bearing fault diagnosis.

F-NIDS — A Network Intrusion Detection System based on federated learning

The rise of IoT networks has presented fresh challenges in terms of scalability and security for distributed Network Intrusion Detection Systems (NIDS) due to privacy concerns. While some progress has been made in addressing these challenges, there are still unanswered questions regarding how to achieve a balance between performance and robustness to ensure privacy in a distributed manner. Additionally, there is a need to develop a reliable and scalable architecture for distributed NIDS that can be effectively deployed in various IoT scenarios. These questions about robustness relied mainly on choosing privacy-secured and distributed Machine Learning techniques. In this work, we propose the F-NIDS, an intrusion detector that utilizes federated artificial intelligence and asynchronous communication techniques between system entities to provide horizontal scalability, along with differential privacy techniques to address data confidentiality concerns. The architecture of F-NIDS is designed to be adaptable for usage in IoT networks, suited to be used in cloud or fog-based environments. Results from our experiments have shown that the confidential detection model employed in F-NIDS – considering multi-class accuracy, binary accuracy, precision, and recall metrics – was capable of predicting and determining the nature of attacks when they occur. In order to determine optimal parameters that strike a balance between data privacy and classification performance, three strategies were employed, each evaluated for its corresponding robustness performance. Firstly, models were trained with varying Gaussian noise values, and subjected to membership inference black box rule-based attacks. Secondly, regular membership inference black box attacks were performed, utilizing different stolen samples with varying sizes to determine the maximum amount of data that could be securely stored on the detection agents for training tasks. Lastly, the robustness of the trained models was evaluated against a model inversion attack, and the results were compared through graphical comparisons. Based on these evaluations, Gaussian noise level and sample size values of 21 were obtained for each detection agent in the system, with sample sizes ranging from 10K to 25K.

Dual-Core Adaptive NLM Image Denoising Algorithm Based on Variable-Size Window and Neighborhood Multifeatures

To solve the problem that the similarity calculation between neighbors was easily disturbed by noise in the traditional nonlocal mean (NLM) denoising algorithm, a dual-core NLM denoising algorithm based on neighborhood multifeatures and variable-size search window was proposed. The algorithm first proposed to use the eigenvalues of the structure tensor to classify the region where the target pixel points were located and used different sizes of the search window to search for similar neighborhoods for target pixel points in different categories of the region, thus effectively avoiding the problem of oversmoothing or inadequate denoising of the image caused by the use of the global size. Then, the gradient features between image blocks were defined and combined with grayscale features and spatial features to measure the similarity of neighborhood blocks, which solved the problem of noise interfering with the search of similar blocks. Then, an adaptive algorithm with Gaussian–Sinusoidal dual kernel function and quantitative estimation of the optimal values of the filtering parameters was designed to calculate the neighborhood similarity weights to improve the accuracy of image denoising. Finally, the similarity weights were used to weight and average the search neighborhood of the target pixel points to achieve the denoising of the target pixel points. To test the effectiveness of the algorithm, denoising tests were performed using multiple standard grayscale images with different levels of Gaussian white noise added and compared with several advanced denoising algorithms. The experimental results showed that the algorithm was effective. The algorithm improved the image peak signal-to-noise ratio by more than 56.54% on average when Gaussian white noise was removed, and the structural similarity reached more than 0.701 on average. Compared with the traditional NLM algorithm and other improved algorithms, the algorithm proposed in this paper had strong denoising ability, better protection of edges and texture details, and the quality of the image was greatly improved, which had a good application prospect.

All‐In‐One Hardware Devices with Event‐Based Vision Sensor Arrays for Image Sensing, Computing, and Learning

AbstractMetal oxide semiconductors (MOSs) are considered as potential candidates for the low‐cost, large‐area fabrication of flexible optoelectronic devices. However, the current optoelectronic devices based on MOSs are limited to unidirectional photoresponse, which constrains the performance of MOSs‐based vision sensors for artificial vision systems. Herein, for the first time, a flexible artificial vision system integrated with optical perception, computation, and learning functionalities is demonstrated using SnO optoelectronic synaptic transistor‐based event‐driven vision sensors to enable dynamic image perception, noise reduction, detection, and recognition. Specifically, an ambipolar SnO transistor is demonstrated by introducing HfO2 passivation layer, which facilitates the movement of O atoms around Sn‐vacancy sites to the HfO2 layer to achieve the transformation from p‐type to ambipolar transport behaviors. More importantly, the HfO2‐passivated SnO transistors exhibit gate‐tunable bidirectional photoresponse behavior, which is essential to simulate the neurobiological functionalities of bipolar cells. This way, the multilayer neural network learning circuit built from SnO transistors achieves fast recognition at a 16% Gaussian noise level and high recognition accuracy up to 95.2% for pattern letters. Under the bending states, recognition accuracies are still retained at 91.2%. These properties are well retained even under the influence of 100% offset of the synaptic programming value.

Poisson image restoration via an adaptive Euler’s elastica regularization

Many recent studies have shown that Euler’s elastica regularization performs better than the famous total variation (TV) regularization on keeping image features in smooth regions during the process of denoising. In addition, an adaptive weighted matrix combined with total variation is a key technique for well restoring local features of image. Considering these two factors, in this paper, we propose an adaptive Euler’s elastica model for Poisson image restoration so as to well preserve both image features in smooth regions and local features of image. To solve this non-smooth and non-convex model efficiently, we design an alternating direction method of multipliers. Experiments on both natural and synthetic images illustrate the effectiveness and efficiency of the proposed method over the state-of-the-art methods in Poisson restoration and denoising, respectively. In particular, for Poisson restoration, our proposed method improves the TV method up to 2.46 about PSNR for dealing with the Peppers image with Gaussian blur and noise level σ = 1. In addition, the proposed method for Poisson denoising gets higher PSNR and SSIM values than the TAC method, while costing less CPU time.

Adaptive myriad filtering algorithms for removal of nonstationary noise in electrooculograms

Suppressing nonstationary noise present in biomedical signals is important to provide high-quality diagnoses. Nonstationary noise is difficult for removing due to its time-varying and previously unknown characteristics. The application of linear filtering to the electrooculograph (EOG) signals leads to the smoothing of diagnostically important rapid changes in a signal caused by saccadic eye movements. In this respect, for processing edges and other discontinuous transitions, nonlinear filters based on robust estimators are more appropriate. The paper introduces novel adaptive algorithms for real-time nonlinear filtering of nonstationary noise in EOG signal with a noise- and signal-dependent filter switching, which is more appropriate for processing a local vicinity of the current input signal sample. One of the algorithms is based on myriad filters and sub-filter weighted FIR (which inite Impulse Responce) myriad hybrid filters. It suggests replacing the median with a myriad operation, calculated by Newton¢s numerical technique with adaptive switching of window length and linearity parameter settings. The other algorithm adaptively switches sub-filter weighted FIR median hybrid and averaging filters with different window lengths, offering simpler calculations and high-speed performance. These algorithms do not require time for filter parameters modification and their exact tuning during real-time signal processing and a prior knowledge of the signal model and noise variance. Numerical simulations were conducted to evaluate the filtering quality based on criteria of mean-square error and signal-to-noise ratio for a model signal under different levels of Gaussian noise. The achieved results show good performance and algorithm high quality for suppression of nonstationary noise in EOG. The myriad type adaptive algorithm prevails over the median in effectiveness but requires a numerical technique for cost function minimization, however, myriad filtering real-time implementation is possible with utilization of high-speed computers. Suggested adaptive algorithms significantly improve the efficiency of nonadaptive filters.