Search

In the field of deep matching, a large amount of noisy data in Chinese long texts affects the matching effect. Most long-form text matching models use all text data indiscriminately, which results in a large amount of noisy data, and thus the PageRank algorithm is combined with Transformer to filter noise. For sentence-level noise detection, after calculating the overlap rate of words to evaluate the similarity, a sentence-level relationship graph is constructed and filtered by using the PageRank algorithm; for word-level noise detection, based on the attention score in Transformer, a word graph is established, then the PageRank algorithm is executed on graph, combined with self-attention weights, to select keywords to highlight topic relevance, the noisy words are filtered sequentially at different layers in the module, layer by layer. In addition, during the model training, PolyLoss is applied to replace the traditional binary Cross-Entropy loss function, thus reducing the difficulty of hyperparameter tuning. Finally, a better filtering strategy is proposed and experiments are conducted to verify it on two Chinese long-form text matching datasets. The result shows that the matching model based on the noise filtering strategy of this paper can better filter the noise and capture the matching signal more accurately. [ABSTRACT FROM AUTHOR]

Application of the nonlinear Kalman filtering method to logarithmically amplified low-coherence fringe signals measured from paper samples is considered. Experimental results of dynamic fringe envelope recovery in optical coherence tomography (OCT) systems are presented. The analog fringe envelope and digital dynamic fringe envelope recoveries from noisy signals are compared. The results show that the nonlinear discrete Kalman filtering method can be applied to estimate envelopes of logarithmically transformed low-coherence fringe signals with high noise immunity. Logarithmic amplification reduces quantization error in dealing with small signal values. The experimental results obtained demonstrate the possibility of purely digital signal processing in OCT. [ABSTRACT FROM AUTHOR]

: We analyze 6500 mm long fracture lines of paper as an example of crack propagation involving disorder. The cracks are asymptotically self-affine, with a roughness exponent close to 0.6. Systematic deviations from the power-law-scaling exist below a lengthscale related to the microscopic heterogeneities and possibly to a cross-over from 3d to 2d crack propagation. Several analysis methods are discussed, including first return analysis and the detection of correlated trends. [ABSTRACT FROM AUTHOR]

Purpose: The aim was to study mortality due to cardiovascular disease as well as total mortality, among female industrial workers, and the association to occupational noise and shift work. Methods: Women from cohorts of soft tissue paper mills (N = 3013) and pulp and paper mills (N = 1483) were merged into one cohort. Job exposure matrices were developed and used for classification of shift work and noise exposure. Every year was classified as shift work excluding nights or shift work including nights. Noise was classified into seven 5 dB(A) bins from < 75 to ≥ 100 dB(A). Mortality from cardiovascular diseases and total mortality during 1956–2013 was calculated as a standardized mortality ratio (SMR) with 95% confidence interval (CI) using the female general population as a reference. Results: Fatal myocardial infarctions (N = 144) were increased in the total cohort, SMR 1.20 (95% CI 1.01–1.41) but not total mortality. The SMR for myocardial infarction for women exposed to noise ≥ 90 dB(A) for > 10 years was 1.41 (95% CI 1.02–1.89) and for those exposed to night shifts > 10 years, 1.33 (95% CI 0.91–1.89). Shift workers without nights ≤ 65 years, with noise exposure ≥ 90 dB(A), had SMR 2.41 (95% CI 1.20–4.31) from myocardial infarction. There was no increased mortality from cerebrovascular disease. Conclusions: Female paper mill workers had an increased mortality from acute myocardial infarction, especially before retirement age, when exposed to noise ≥ 90 dB(A) and with long-time employment. Exposure to shift work and noise usually occurred concurrently. [ABSTRACT FROM AUTHOR]

The paper proposes a smart method to remove network nodes that are highly prone to impulse noise and replacing them with a linear combination of existing more reliable nodes. This is done to reduce communication cost. To reduce the communication cost in a network, a common way is to remove some nodes randomly and then replace the intermediate estimation of these nodes by the corresponding node estimation. In this direction, the contribution of this paper is twofold. First, we suggest to remove the nodes smartly by omitting the unreliable nodes prone to impulsive noise. This is done by computing the disturbance induced in the adaptation step of the diffusion least mean square. Second, we replace the estimation of removing nodes by a linear combination of existing estimations of reliable nodes instead of just replacing by the estimation of the corresponding node. Also, the coefficients of linear combination are optimized based on the minimum disturbance principle. Furthermore, the minimum achievable disturbance is calculated mathematically and a necessary and sufficient condition for stability of the proposed algorithm is presented. Finally, the simulation results show the efficiency of the proposed method in comparison with some state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

In response to the challenges of accurately identifying event triggers and elements in long texts related to aquaculture, existing models struggle to differentiate between elements and triggers, as well as effectively recognize complete entity texts. To tackle this issue, this study proposes an algorithm for extracting fish disease events based on pseudo triggers and augmented event element data. The method starts by constructing pseudo samples using the original dataset. Two types of noise datasets are then generated: a trigger noise dataset constructed based on fish disease triggers and an entity noise dataset with varying levels of entity noise constructed based on fish disease entities. Next, three parallel neural networks are deployed to extract sample features from these datasets. The fish disease event extraction for the source dataset employs multi-label classification. For the trigger noise dataset, the sample features are activated using the sigmoid function, and the MRSE loss is utilized for optimization of this branch. For the entity noise dataset, the sample features are activated using the Relu function, and the XOR loss is used for optimization. Finally, the losses from the three branches are combined with weighted summation to obtain the fusion loss. The experimental results on the fish disease dataset used in this paper show that the proposed algorithm achieves an average accuracy of 78.71%, 78.95%, and 79.43% on F1, recall, and precision, respectively, which is a maximum improvement of 11.201%, 11.849%, and 12.421% in accuracy with respect to the baseline model on F1, recall, and precision, respectively. [ABSTRACT FROM AUTHOR]

A study of 20 factories belonging to textile, printing, publishing and paper products industries in Jeddah was conducted. Data on Leq, Maximum and Minimum SPL at different octave bands, as well as dBA, were collected. It has been found that textile, publishing and paper products industries are the most noisy industries. The paper is concluded with suitable recommendation for noise control and worker protection. [ABSTRACT FROM AUTHOR]

Purpose: The mechanical fault diagnosis method based on deep learning mainly uses single-scale convolution kernels to extract fault features, which is difficult to extract fault feature information comprehensively. Under strong noise conditions, the performance of fault diagnosis using single-scale convolution kernels will decrease sharply. Methods: An intelligent fault diagnosis method based on multi-scale deep convolution neural network (MSD-CNN) model and data enhancement for strong noise is proposed in this paper. By the multi-scale cascade convolution kernels in the MSD-CNN, the multi-scale information of the original fault signal is extracted, and the ELU activation function is used to retain the negative information contained in the multi-scale information. By the data enhancement method for strong noise, the number and diversity of the MSD-CNN model training samples are improved, which enables the model to learn deeper features in the training stage. Results and Conclusion: Compared six common fault diagnosis models, the proposed model achieves the optimal diagnostic accuracy of 99.98% and 99.66% under normal conditions and strong noise conditions, respectively, which verifies the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, the flocking behavior of a Cucker-Smale model with a leader and noise is studied in a finite time. The authors present a Cucker-Smale system with two nonlinear controls for a complex network with stochastic synchronization in probability. Based on the finite-time stability theory of stochastic differential equations, the sufficient conditions for the flocking of stochastic systems in a finite time are obtained by using the Lyapunov function method. Finally, the numerical simulation of the particle system is carried out for the leader and noise, and the correctness of the results is verified. [ABSTRACT FROM AUTHOR]

Background noises are usually treated as redundant or even harmful to voice conversion. Therefore, when converting noisy speech, a pretrained module of speech separation is usually deployed to estimate clean speech prior to the conversion. However, this can lead to speech distortion due to the mismatch between the separation module and the conversion one. In this paper, a noise-robust voice conversion model is proposed, where a user can choose to retain or to remove the background sounds freely. Firstly, a speech separation module with a dual-decoder structure is proposed, where two decoders decode the denoised speech and the background sounds, respectively. A bridge module is used to capture the interactions between the denoised speech and the background sounds in parallel layers through information exchanging. Subsequently, a voice conversion module with multiple encoders to convert the estimated clean speech from the speech separation model. Finally, the speech separation and voice conversion module are jointly trained using a loss function combining cycle loss and mutual information loss, aiming to improve the decoupling efficacy among speech contents, pitch, and speaker identity. Experimental results show that the proposed model obtains significant improvements in both subjective and objective evaluation metrics compared with the existing baselines. The speech naturalness and speaker similarity of the converted speech are 3.47 and 3.43, respectively. [ABSTRACT FROM AUTHOR]

The brake system is one of the most important systems on the vehicle, especially from the aspect of traffic safety. The use of the braking system comes with many undesirable effects, such as brake wear and noise emission. The noise that originates from brakes is related to the wear of brake elements, the applied materials for manufacture, to the elements which are connected to each other, and all of this represents a very challengeable problem in the automotive industry. In this paper are presented the dominant parameters that influence noise formation, where the main focus was placed on brake pads, as well as how the noise influences people's health. After that, further, in the paper, it was analyzed the influence of the brake pads' construction on the noise formation, and at the end are given the measures for noise reduction. The conclusions of the paper show that the construction of brake pads significantly influences noise emission, noise negatively influences on the people health, and because of the negative influence on the people health, some solutions show that it is necessary to include insulators in the construction of brake pads, and if the space in which people reside is observed, it is necessary during construction to use materials which will prevent noise conduction, into the space in which people reside. [ABSTRACT FROM AUTHOR]

Aiming at the problems of identifying storage pest tobacco pest beetles from images that have few object pixels and considerable image noise, and therefore suffer from lack of information and identifiable features, this paper proposes an automatic monitoring method of tobacco beetle based on Multi-scale Global residual Feature Pyramid Network and Dual-path Deformable Attention (MGrFPN-DDrGAM). Firstly, a Multi-scale Global residual Feature Pyramid Network (MGrFPN) is constructed to obtain rich high-level semantic features and more complete information on low-level features to reduce missed detection; Then, a Dual-path Deformable receptive field Guided Attention Module (DDrGAM) is designed to establish long-range channel dependence, guide the effective fusion of features and improve the localization accuracy of tobacco beetles by fitting the spatial geometric deformation features of and capturing the spatial information of feature maps with different scales to enrich the feature information in the channel and spatial. Finally, to simulate a real scene, a multi-scene tobacco beetle dataset is created. The dataset includes 28,080 images and manually labeled tobacco beetle objects. The experimental results show that under the framework of the Faster R-CNN algorithm, the detection precision and recall rate of this method can reach 91.4% and 98.4% when the intersection ratio (IoU) is 0.5. Compared with Faster R-CNN and FPN, when the intersection ratio (IoU) is 0.7, the detection precision is improved by 32.9% and 6.9%, respectively. The proposed method is superior to the current mainstream methods. [ABSTRACT FROM AUTHOR]

Feature-preserving mesh denoising has received noticeable attention in visual media, with the aim of recovering high-fidelity, clean mesh shapes from the ones that are contaminated by noise. Existing denoising methods often design smaller weights for anisotropic surfaces and larger weights for isotropic surfaces in order to preserve sharp features, such as edges or corners, on the mesh shapes. However, they often disregard the fact that such small weights on anisotropic surfaces still pose negative impacts on the denoising outcomes and detail preservation results on the shapes. In this paper, we propose a novel segmentation-driven mesh denoising method which performs region-wise denoising, and thus avoids the disturbance of anisotropic neighbour faces for better feature preservation results. Also, our backbone can be easily embedded into commonly used mesh denoising frameworks. Extensive experiments have demonstrated that our method can enhance the denoising results on a wide range of synthetic and real mesh models, both quantitatively and visually. [ABSTRACT FROM AUTHOR]

Mechanical equipment usually operates in noisy and variable load environments, which presents serious challenges for existing intelligent diagnostic models. In addition, there are few labelled fault samples in real engineering scenarios, which makes it difficult to perform accurate fault identification for mechanical equipment. Thus, to solve the problem of diagnostic model performance degradation under small sample, noisy and variable load environments, this paper proposes a Multiscale Dilated Convolution and Swin-Transformer (MSDC-Swin-T) method for small sample gearbox fault diagnosis. First, we design the Coordinate Reconstruction Attention Mechanism (CRAM), which enhances the capture of impulse information by coordinate reconstruction. In addition, a multiscale convolutional token embedding module is constructed to extract local features at different scales, and its ability for capturing important features is adaptively enhanced by CRAM. Then, Swin-Transformer is utilized for modeling global dependencies, thus mining more subtle fault features. Finally, the effectiveness and stability of the MSDC-Swin-T is proved on two gearbox datasets. The experiments show that MSDC-Swin-T has superior diagnostic performance under small sample with noise and variable load environments. The diagnostic accuracy is better than the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Image smoothing is an important processing operation that highlights low-frequency structural parts of an image and suppresses the noise and high-frequency textures. In the paper, we post an intriguing question of how to combine the paired unsmoothed/smoothed images and meaningful edge information to improve the performance of image smoothing. To this end, we propose a structure-preserving image smoothing network, which consists of a main interpreter (MI) and an edge map extractor (EME). The network is trained via contrastive learning on the extended BSD500 dataset. In addition, an edge-aware total variation loss function is utilized to distinguish between non-edge regions and edge maps via a pre-trained EME module, therefore improving the capability of structure preservation. In order to maintain the consistency in structure and background brightness, the outputs from MI are used as anchors for a ternary loss in 1:1 paired positive and negative samples. Experiments on different datasets show that our network outperforms state-of-the-art image smoothing methods in terms of SSIM and PSNR. [ABSTRACT FROM AUTHOR]

To solve the significant performance degradation in the blind equalization for multi-level quadrature amplitude modulation (QAM) signals, an improved multimodulus algorithm based on the real part (or the imaginary part) of the transmitted signals is developed in this paper. Theoretical analysis illustrates that the proposed algorithm can roughly half the computational complexity and fundamentally suppress the well-known steady-state maladjustment of classical constant modulus algorithm and multimodulus algorithm. Moreover, the large maladjustment in the iteration process can be completely removed, thus the proposed algorithm can work well in impulsive noise environment. Finally, simulation results show the effectiveness of the proposed algorithm under both Gaussian and impulsive noise environments. [ABSTRACT FROM AUTHOR]

The mechanism of selectivity in ion channels is still an open question in biology. Recent studies suggest that the selectivity filter may exhibit quantum coherence, which could help explain how ions are selected and conducted. However, environmental noise causes decoherence and loss of quantum effects. It is hoped that the effect of classical noise on ion channels can be modeled using the framework provided by quantum decoherence theory. In this paper, the behavior of the ion channel system was simulated using two models: the Spin–Boson model and the stochastic Hamiltonian model under classical noise. Additionally, using a different approach, the system's evolution was modeled as a two-level Spin–Boson model with tunneling, interacting with a bath of harmonic oscillators, based on decoherence theory. We investigated under what conditions the decoherence model approaches and deviates from the noise model. Specifically, we examined Gaussian noise and Ornstein-Uhlenbeck noise in our model. Gaussian noise shows a very good agreement with the decoherence model. By examining the results, it was found that the Spin–Boson model at a high hopping rate of potassium ions can simulate the behavior of the system in the classical noise approach for Gaussian noise. [ABSTRACT FROM AUTHOR]

The Quantum Approximate Optimization Algorithm (QAOA) is a variational quantum algorithm for Near-term Intermediate-Scale Quantum computers (NISQ) providing approximate solutions for combinatorial optimization problems. The QAOA utilizes a quantum-classical loop, consisting of a quantum ansatz and a classical optimizer, to minimize some cost function, computed on the quantum device. This paper presents an investigation into the impact of realistic noise on the classical optimizer and the determination of optimal circuit depth for the Quantum Approximate Optimization Algorithm (QAOA) in the presence of noise. We find that, while there is no significant difference in the performance of classical optimizers in a state vector simulation, the Adam and AMSGrad optimizers perform best in the presence of shot noise. Under the conditions of real noise, the SPSA optimizer, along with ADAM and AMSGrad, emerge as the top performers. The study also reveals that the quality of solutions to some 5 qubit minimum vertex cover problems increases for up to around six layers in the QAOA circuit, after which it begins to decline. This analysis shows that increasing the number of layers in the QAOA in an attempt to increase accuracy may not work well in a noisy device. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method to recognize the digital modulation communication signals with alpha-stable noise over fading channels. Specifically, the probability density function of alpha-stable noise is determined by kernel density estimation, and the fading channel parameters are measured by utilizing the improved expectation conditional maximization algorithm. Then we leverage the compound hypothesis test model, which serves as a classifier, to implement modulation recognition. Simulation results show that the proposed method is robust to alpha-stable noise over fading channels. Moreover, the correct average recognition rates of the digital modulation communication signals under alpha-stable noise is more than 90%, when the generalized signal-to-noise ratio is 10dB. [ABSTRACT FROM AUTHOR]

Reinforcement learning (RL) algorithms with deterministic actors (policy) commonly apply noise to the action space for exploration. These exploration methods are either undirected or require extra knowledge of the environment. In the aim of addressing these fundamental limitations, this paper introduces a parameterized stochastic action-noise policy (as a probability distribution) that correlates with the objectivity of the RL algorithm. This policy is optimized based on state-action values of predicted future states. Consequently, the optimization does not rely on the explicit definition of the reward function which improves the adaptability of this exploration strategy for different environments and algorithms. Moreover, this paper presents a predictive model of system dynamics (transitional probability) with the capacity to capture the uncertainty of the environments with optimal design and fewer parameters. It significantly reduces the model complexity while maintaining the same level of accuracy as current methods. This research evaluates and analyzes the proposed method and models while demonstrating significant increase in performance and reliability across various locomotion and control tasks in comparison with current methods. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the traditional deep learning algorithms have unsatisfactory speech enhancement effect under low Signal-to-Noise Ratio (SNR) conditions, this paper improves Deep Neural Network (DNN) and Multiresolution Residual U Network (MultiResU_Net) to discuss the speech enhancement effect. In this paper, the Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator (MMSE-STSA) is used to reduce the noise of the Multi-Resolution Cochleagram (MRCG) features that including the local and global characteristics of speech and using the improved features Improved Multi-Resolution Cochleagram (I-MRCG) as the input of Skip-DNN network to build Skip-DNN speech enhancement model. The short-time Fourier transformed features of the speech signal at low SNR are used as the input of MultiResU_Net network and the output features of residual path and upsampling are rearranged by the hybrid channel to build an improved MultiResU_Net speech enhancement model. Using LibriSpeech ASR corpus, under different SNR conditions, analyze the speech enhancement effects of different network models and different features as the input of the Skip-DNN model. The experimental results show that when the SNR is -5dB, the perceptual evaluation effect of the average speech quality is better that I-MRCG is used as the feature input of the Skip-DNN model. The average short-time objective intelligibility (STOI), the average perceptual evaluation of speech quality (PESQ) and Source-to-Distortion Ratio (SDR) of the improved MultiResU_Net speech enhancement model are higher than other models. It can be seen that both the improved Skip-DNN and MultiResU_Net proposed in this paper have better speech enhancement effect, especially the improved MultiResU_Net network is more suitable for speech enhancement at low SNR. [ABSTRACT FROM AUTHOR]

Automatic modulation classification plays a critical role in the intelligent reception of unknown wireless signals. In practice, the dynamic wireless environment brings a great challenge, and the actual test model is inconsistent with the training model. Therefore, aiming at the problem of noise mismatch, this paper proposes a new modulation classification method based on KD-GoogLeNet and Squeeze-Excitation (KD-GSENet). Using the k-dimensional tree, the complex wireless signals are converted into color images rather than normal constellations, which can enhance the classification features. Considering the attention block has the inherent advantage of assigning more weights to important features, this paper further uses it to improve the GoogLeNet. Finally, extensive experiments are presented including Gaussian noise, non-Gaussian noise, and the scenarios of noise mismatch. Numerical results verify the superior classification performance of the proposed KD-GSENet under different scenarios. [ABSTRACT FROM AUTHOR]

Faced with the accelerated growth of cities and the consequent increase in the number of motor vehicles, urban noise levels caused by vehicular traffic have increased considerably. To assess noise levels in cities and implement noise control measures or identify the problem's location in different urban areas, it is necessary to obtain the noise levels to which people are exposed. Noise maps are tools that have applications as they are cartographic representations of the noise level distribution in an area and over a period of time. This article aims to identify, select, evaluate, and synthesize information, through a systematic literature review, on using different road noise prediction models, in sound mapping computer programs in countries that do not have a standard noise prediction model. The analysis period was from 2018 to 2022. From a previous analysis of articles, the choice of topic was based on identifying various models for predicting road noise in countries without a standardized sound mapping model. The papers compiled by a systematic literature review showed that studies concentrated in China, Brazil, and Ecuador, the most used traffic noise prediction models, were the RLS-90 and the NMPB, and the most used mapping programs were SoundPLAN and ArcGIS with a grid size of 10 × 10 m. Most measurements were carried out during a 15-min period at a height from the ground level of 1.5 m. In addition, it was observed that research on noise maps in countries that do not have a local model has been increasing over time. [ABSTRACT FROM AUTHOR]

In this paper, we consider the problem of augmenting a set of histological images with adversarial examples to improve the robustness of neural network classifiers trained on the augmented set against adversarial attacks. In recent years, neural network methods have been developing rapidly, achieving impressive results. However, they are vulnerable to so-called adversarial attacks; i.e., they make incorrect predictions on input images with added carefully crafted imperceptible noise. Hence, the reliability of neural network methods remains an important area of research. In this paper, we compare different methods for training set augmentation to improve the robustness of neural histological image classifiers against adversarial attacks. For this purpose, we augment the training set with adversarial examples generated by several popular methods. [ABSTRACT FROM AUTHOR]

Tyre cavity resonance noise is one kind of low-frequency and narrow-band noise that particularly affects the passengers inside the cabin of vehicle, especially when driving at a medium speed. In this paper, a noise reduction structure made of multiple resonators is proposed to reduce this type of noise. Based on the local resonance principle, the dimension of the resonator unit is determined by the tyre cavity resonance frequency. In order to obtain this characteristic frequency and the acoustic feature, the acoustic-structure coupling model of the tyre and cavity is established by the finite element method (FEM), and the modal frequency and shape of the tyre cavity are calculated and validated by the experimental results. Based on these analyses, the geometric and material parameters of the sound reduction structure are calculated to match the resonant frequency of the tyre cavity. A long belt filled with multiple resonators is designed to fit the profile of the tyre cavity, and simulations and experimental tests are conducted to investigate the noise reduction performance. The results show that the multiple resonators can significantly reduce the sound pressure inside the tyre cavity due to the vibroacoustic coupling effect. This paper provides a novel solution for reducing tyre cavity resonance noise. [ABSTRACT FROM AUTHOR]

The piezoelectric coupling principle is widely used (along with capacitive coupling and piezoresistive coupling) for MEMS accelerometers. Piezoelectric MEMS accelerometers are used primarily for vibration monitoring. Polymer piezoelectric MEMS accelerometers offer the merits of heavy-metal-free structure material and simple microfabrication flow. More importantly, polymeric piezoelectric MEMS accelerometers may be the basis of novel applications, such as fully organic inertial sensing microsystems using polymer sensors and organic integrated circuits. This paper presents a novel polymer piezoelectric MEMS accelerometer design using PVDF films. A simple and rapid microfabrication flow based on laser micromachining of thin films and 3D stereolithography was developed to fabricate three samples of this design. During proof-of-concept experiments, the design achieved a sensitivity of 21.82 pC/g (equivalent open-circuit voltage sensitivity: 126.32 mV/g), a 5% flat band of 58.5 Hz, and a noise density of 6.02 µg/√Hz. Thus, this design rivals state-of-the-art PZT-based counterparts in charge sensitivity and noise density, and it surpasses the performance capabilities of several commercial MEMS accelerometers. Moreover, this design has a 10-times smaller device area and a 4-times larger flat band than previous state-of-the-art organic piezoelectric MEMS accelerometers. These experimentally validated performance metrics demonstrate the promising application potential of the polymeric piezoelectric MEMS accelerometer design presented in this article. [ABSTRACT FROM AUTHOR]

Ship noise analysis is a critical area of research in hydroacoustic remote sensing due to its practical implications in identifying ship direction, type, and even specific ship identities. However, the limited availability of data poses challenges in developing accurate ship noise classification models. Previous studies have mainly focused on small-sample learning approaches, resulting in complex network structures. Nonetheless, underwater robots often have limited computing power, making it essential to develop simpler recognition networks. In this paper, we address the issue of data scarcity by introducing positive incentive noise. We propose a CNN-based hydroacoustic signal recognition method that achieves comparable or superior performance to previous studies, using a simple network structure as a back-end decision system. We describe the feature extraction process using a dataset with added noise and compare the performance of various features. Additionally, we compare our proposed method with previous studies. Experimental results demonstrate that simple neural networks can achieve high performance and excellent generalizability without the need for complex network structures like adversarial learning models. [ABSTRACT FROM AUTHOR]

Up to now, the inaccurate supervision problem caused by label noises poses a big challenge for regression modeling. Regularized noise-robust models provide a valid way for dealing with label noises in regression tasks. They generally use robust losses to cope with label noises and further enhance model robustness by feature selection. But most of them may not work well on data sets contaminated by severe noises (whose magnitudes are extreme), because severe noises do not coincide with their noise assumptions. To address this concern, this paper proposes a robust adaptive linear regression method named TC-ALASSO (Truncated Cauchy Adaptive LASSO), in which model learning and feature selection are finished simultaneously. The fat-tailed Cauchy distribution and truncation theory are adopted to deal with moderate noises and identified extreme noises, respectively, and construct the Truncated Cauchy loss for regression tasks. Moreover, TC-ALASSO applies the adaptive regularizer to finish feature selection well. Note that its adaptive regularizer weights are acquired according to regression coefficient estimations under the truncated Cauchy loss. We also theoretically analyze the robustness of proposed TC-ALASSO in this paper. The experimental results on artificial and benchmark data sets all confirm the robustness and effectiveness of TC-ALASSO. In addition, experimental results on face recognition databases validate the performance advantage of TC-ALASSO over state-of-the-art methods in dealing with extreme illumination variations. [ABSTRACT FROM AUTHOR]

This paper presents an analysis of acoustic emission and performance data of a UAV rotor equipped with a variable pitch propeller. The proposed study aims to show propeller noise features that indicate stall flow regime on the blade. Analysis of the noise characteristics around the propeller in terms of power spectral density allow to detect the stall. The study shows that a microphone located at different angles around the propeller can provide data sufficient to determine if the blade angle of attack has forced the propeller into the stall regime. In this range, the propeller’s efficiency in hover decreases and leads to an increase in power consumption. The reresearch is a suggests a method of data treatment to obtain a single parameter indicating a blade stall. [ABSTRACT FROM AUTHOR]

To accurately determine the strength and the waveform of the partial discharge (PD) signal, especially if the source position is far from the ultra-high frequency (UHF) sensor or if the signal is weak, it is necessary to properly extract the most prominent PD from the background noise in the recorded signal. This paper provides a new procedure for the extraction of PD signal in the predominant very high frequency (VHF) range from the strong noise in each of the signals recorded online and onsite using the UHF sensor in the power transformer during its normal operation in a thermal power plant. A standard UHF drain valve sensor was used with good sensitivity in the high frequency and VHF bands. First, it is necessary to determine as precisely as possible the period in which the most prominent PD occurs in the middle part of each signal. Second, it is to compare the frequency spectra of the dominant, strong noise in the left and right parts in relation to the corresponding middle part of each recorded signal. And third, it is to extract the PD with the largest amplitudes from the estimated noise in the middle part of each recorded signal by finding the cutoff frequency and performing high-pass filtering in MATLAB. The new criterion for cutoff frequency is that there are no time shifts of the first peaks of the most prominent PD of each recorded signal. The results show some obvious similarities of PDs in the recorded signals, such as frequency range, duration, repetition rate, and the same dominant frequency, which sufficiently indicates that it is the same type of PD. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) has become a widely used medical imaging method. Affected by imaging mechanism, magnetic field inhomogeneity and other factors, MRI images are often interfered by non-Gaussian noise such as Rician noise and non-central chi-square distribution noise. However, the existing MRI denoising methods cannot effectively remove different kinds of noise, and the image is prone to blur and detail loss, even artifacts. Thus, this paper proposes an adaptive denoising algorithm for MRI based on Nonlocal Structural Similarity and Low-Rank Sparse Representation (NSS-LRSR). Different from the existing methods, it is a new paradigm to adaptively filter non-Gaussian noise of MRI and it has a good effect on both spatially stable and spatially varying Rician or non-central chi-square distribution noise. The forward variance stable transformation is used to correct the deviation caused by non-Gaussian noise, and then the non-local information is regrouped. And considering the sparse of similar image blocks, we use improved weighted kernel norm minimization to represent the non-local image blocks based on estimation of noise's standard deviation; thereby the processed image block are aggregated and outputted. Experimental results show that compared with the currently popular algorithms, the proposed NSS-LRSR achieves better results in PSNR and SSIM quantitative indexes. [ABSTRACT FROM AUTHOR]

Unsupervised domain adaptation (UDA) is an important solution for the cross-domain problem in semantic segmentation. Existing segmentation UDA methods mainly consider the domain shift as the major challenge. This paper, from a novel viewpoint, disentangles the cross-domain problem into two negative factors beyond the domain shift. Specifically, we find that apart from the domain shift factor, the dispersed within-class distribution on the target domain is another factor that compromises cross-domain segmentation. This paper finds that the neglected target domain distribution dispersion is a challenge as crucial as the domain shift. In response to the joint of these two negative factors, we propose a "Pull-and-Concentrate" (PuCo) method comprised of two consistencies: (1) A cross-domain consistency "pulls" the source and target domain distribution (of the same class) close to each other based on a novel statistical style transfer. (2) An intra-domain consistency "concentrates" the within-class distribution on the target domain in a new unsupervised teacher-student method. Both consistencies have the advantage of being robust (or insulated) from pseudo-label noises. This advantage allows PuCo to bring consistent improvement over a battery of pseudo-label-based UDA methods. For example, on GTA5 to Cityscapes and SYNTHIA to Cityscapes, PuCo achieves 60.3 % and 57.2 % mean IoU, respectively. Code is available at https://github.com/Jarvis73/PuCo. [ABSTRACT FROM AUTHOR]

Concerning decision support in specific disease areas, making faster and more accurate medical diagnoses has become more challenging. Due to indeterminate, inconsistent, and huge patient data, judging a specific disease may be challenging. Similarity is an effective method to enhance healthcare systems by simplifying medical diagnostic generation compared with illness profiles. This paper proposes a new medical diagnosis algorithm that uses interval type-2 fuzzy similarity measures (IT-2FSMs). This algorithm calculates the degree of similarity between varieties of components of patient data and establishes methods of clustering patients based on close distances between some of their features. The proposed approach will be evaluated on UCI Machine Learning Repository medical datasets. Comparative studies will be done between different IT-2 FSMs (Cherif, Jaccard, Bustince, Mitchell, Gorzalczany, Zeng and Li) to demonstrate the capability of IT-2FSMs to make quick medical diagnoses, even with different noise levels. The proposed IT-2FSMs are utilized as a clustering method and compared against existing clustering algorithms such as type-2 fuzzy c-means, cluster forest, bagged clustering, evidence accumulation, and random projection. The IT-2FSMs demonstrate a pertinent classification accuracy comparable to the other algorithms, as assessed by the clustering quality parameter R. [ABSTRACT FROM AUTHOR]

High-dimensional data is characterized by its sparsity and noise, which can increase the likelihood of overfitting and compromise the model's generalizability performance. In this paper, a novel robust subspace learning method based on stable adaptive spectral clustering is put forward for dimensionality reduction. Firstly, a robust estimator is used to distinguish the role of normal and abnormal samples in constructing the model, thereby small values are assigned to the outliers, then the influence of outliers on the construction of the learning models will be reduced. Secondly, the p-order of L 2 -norm distance is applied as the distance metric, replacing the square of L 2 -norm distance metric. The L 2 , p -norm often commendably tolerates the biases caused by the outliers in sample data, especially when the outliers are away from the normal data distributions. Thirdly, the adaptive stable spectral clustering based on the L 2 , p -norm is proposed to construct similarity matrix of the novel robust subspace to carry out reflexive embedding learning to learn the local and globe features of the raw data. In the subspace, the data is reconstructed to reduce the influence of noise and outliers, and the similarity matrix is structured by the new features, that is more conducive to subspace learning. Three main roles of the objective function of our model are: (1) preserving the consistency between the original data and the estimation; (2) achieving a "clean" subspace and further removing the outliers; (3) avoiding the trivial solution for each node in the graph. Finally, the random forest algorithm is used to classify and predict the learned subspace with different feature selections. Experimental results show that the proposed method is superior to other subspace learning methods in classification performance. The results of noise experiment and statistical analysis demonstrate the effectiveness of the proposed method once again. [ABSTRACT FROM AUTHOR]

Segmentation is a significant stage for the recognition of old newspapers. Text-line extraction in the documents like newspaper pages which have very complex layouts poses a significant challenge. Old newspaper documents printed in Gurumukhi script present several forms of hurdles in segmentation due to noise, degradation, bleed-through of ink, multiple font styles and sizes, little space between neighboring text lines, overlapping of lines, etc. Because of the low quality and the complexity of these documents, automatic text line segmentation remains an open research field. Very few researches are available in the literature to segment news articles in Gurumukhi script. This is one of the first few attempts to recognize Gurumukhi newspaper text. The goal of this paper is to present a new methodology for text-line extraction by integrating median calculation and strip height calculation techniques. Non-suitability of existing techniques to segment newspaper text lines have also been discussed with results in the article. The efficiency of the proposed algorithm is demonstrated by experimentation directed on two diverse own made datasets: (a) on the data set of single-column documents with headlines block (b) on the dataset of multi-column documents with headlines block. [ABSTRACT FROM AUTHOR]

We address the issue of detecting hidden periodicity when the signal exhibits periodic correlation, but is additionally affected by non-Gaussian noise with unknown characteristics. This scenario is common in various applications. The conventional approach for identifying periodically correlated (PC) behavior involves the frequency domain-based analysis. In our investigation, we also employ such an approach; however, we use a robust version of the discrete Fourier transform incorporating the Huber function-based M-estimation, unlike the classical algorithm. Building upon this approach, we propose robust coherent and incoherent statistics originally designed to identify hidden periodicity in pure PC models. The novelty of this paper lies in introducing robust coherent and incoherent statistics through the application of the robust discrete Fourier transform in classical algorithms and proposing a new technique for period estimation based on the proposed methodology. We explore two types of PC models and two types of additive noise, resulting in PC signals disturbed by non-Gaussian additive noise. Detecting hidden periodicity in such cases proves to be significantly more challenging than in classical scenarios. Through Monte Carlo simulations, we demonstrate the effectiveness of the proposed robust approaches and their superiority over classical. To further substantiate our findings, we analyze three datasets in which hidden periodicity had previously been confirmed in the literature. Among them, two datasets correspond to the condition monitoring area, being a main motivation of our research. [ABSTRACT FROM AUTHOR]

Background: The potential effect of image noise artefacts on Digital Volume Correlation (DVC) analysis has not been thoroughly studied and, more particularly quantified, even though DVC is an emerging technique widely used in life and material science over the last decade. Objective: This paper presents the results of a sensitivity study to shed light on the effect of various noise artefacts on the full-field kinematic fields generated by DVC, both in zero and rigid body motion. Methods: Various noise artefacts were studied, including the Gaussian, Salt & Pepper, Speckle noise and embedded Ring Artefacts. A noise-free synthetic microstructure was generated using Discrete Element Modelling (DEM), representing an idealistic case, and acting as the reference dataset for the DVC analysis. Noise artefacts of various intensities (including selected extreme cases) were added to the reference image datasets using MATLAB (R2022) to form the outline of the parametric study. DVC analyses were subsequently conducted employing AVIZO (Thermo Fisher). A subset-based local approach was adopted. A three-dimensional version of the Structural Similarity Index Measure (SSIM) was used to define the similarity between the compared image datasets on each occasion. Sub-pixel rigid body motion was applied on the DEM-generated microstructure and subsequently "poisoned" with noise artefacts to evaluate mean bias and random error of the DVC analysis. Results: When the local approach is implemented, the sensitivity study on zero motion data revealed the insignificant effect of the Gaussian, Salt & Pepper, and Speckle noise on the DVC-computed kinematic field. Therefore, the presence of such noise artefacts can be neglected when DVC is executed. On the contrary, Ring Artefacts can pose a considerable challenge and therefore, DVC results need to be evaluated cautiously. A linear relationship between SSIM and the correlation index is observed for the same noise artefacts. Gaussian noise has a pronounced effect on the mean bias error for sub-pixel rigid body motion. Conclusions: Generating synthetic image datasets using DEM enabled the investigation of a variety of noise artefacts that potentially affect a DVC analysis. Given that, any microstructure – resembling the material studied – can be simulated and used for a DVC sensitivity analysis, supporting the user in appropriately evaluating the computed kinematic field. Even though the study is conducted for a two-phase material, the method elaborated in this paper also applies to heterogeneous multi-phase materials also. The conclusions drawn are valid within the environment of the AVIZO DVC extension module. Alternative DVC algorithms, utilising different approaches for the cross-correlation and the sub-pixel interpolation methods, need to be investigated. [ABSTRACT FROM AUTHOR]

In this paper we construct a new type of noise of fractional nature that has a strong regularizing effect on differential equations. We consider an equation driven by a highly irregular vector field and study the effect of this noise on such dynamical systems. We employ a new method to prove existence and uniqueness of global strong solutions, where classical methods fail because of the "roughness" and non-Markovianity of the driving process. In addition, we prove the rather remarkable property that such solutions are infinitely many times classically differentiable with respect to the initial condition in spite of the vector field being discontinuous. The technique used in this article corresponds, in a certain sense, to the Nash–Moser iterative scheme in combination with a new concept of "higher order averaging operators along highly fractal stochastic curves". This approach may provide a general principle for the study of regularization by noise effects in connection with important classes of partial differential equations. [ABSTRACT FROM AUTHOR]

Label noise poses a significant challenge to supervised learning algorithms. Extensive research has been conducted on classification and regression tasks, but label noise filtering methods specifically designed for ordinal regression are lacking. In this paper, we propose a set of ordinal label noise filtering frameworks by theoretically exploring the generalization error bound in noisy environments. Besides, we present a robust label noise estimation method voted by inter-class distance. It takes into account the nonuniformity of ordinal labels and the reliability of the base model. This estimator is integrated into our framework in the proposed Inter-Class Distance-based Filtering (ICDF) algorithm. We empirically demonstrate the effectiveness of ICDF in identifying label noise and achieving improved generalization performance. Our experiments conducted on benchmark and real age estimation datasets show the superiority of ICDF over the existing filters in ordinal label noise cleaning. [ABSTRACT FROM AUTHOR]

Noising in X-ray imaging has been one of the biggest challenges that leads to insufficient and improper diagnosis. Despite the fact that X-rays are one of the most widespread and acceptable imaging techniques among the medical and scientific fraternity, still Gaussian and Poisson noise lead to a lot of image deterioration. Over the past few decades, several denoising techniques have been explored using traditional, hybrid and deep learning techniques which have been reported in this paper. Poisson noise was best removed by the application of bilateral filter with a maximum Peak Signal to Noise Ratio (PSNR) of 36.22 and for the removal of Gaussian noise, median filter proved to be unparalleled with a PSNR of 32.92 for the variance of 0.01, 31.4 for the variance of 0.04, 31.03 for the variance of 0.07, and 30.58 for the variance of 0.1 amongst the conventional filters. The Noise2Noise model employing the deep learning approach has given the best PSNR value of 34.38 amongst all the other alternatives for the images with gaussian noise. This paper serves as a comprehensive review for beginners working in this domain, that would aid them to select the best filter for the image pre-processing and noise removal. [ABSTRACT FROM AUTHOR]

To establish the sound quality evaluation model of roller chain transmission system, we collect the running noise under different working conditions. After the noise samples are preprocessed, a group of experienced testers are organized to evaluate them subjectively. Mel frequency cepstral coefficient (MFCC) of each noise sample is calculated, and the MFCC feature map is used as an objective evaluation. Combining with the subjective and objective evaluation results of the roller chain system noise, we can get the original dataset of its sound quality research. However, the number of high-quality noise samples is relatively small. Based on the sound quality research of various chain transmission systems, a novel method called multi-source transfer learning convolutional neural network (MSTL-CNN) is proposed. By transferring knowledge from multiple source tasks to target task, the difficulty of small sample sound quality prediction is solved. Compared with the problem that single source task transfer learning has too much error on some samples, MSTL-CNN can give full play to the advantages of all transfer learning models. The results also show that the MSTL-CNN proposed in this paper is significantly better than the traditional sound quality evaluation methods. [ABSTRACT FROM AUTHOR]

At present, many algorithms use a single minimum eigenvalue to estimate the real noise level, and the levels estimated by these algorithms have been proven to be less than the real noise levels, this is known as underestimation. To address this problem, this paper uses multiple eigenvalues to obtain the relationship between eigenvalues and the real noise level through sample training, calculates the learning coefficients for different noise levels in the relationship expression by linear fitting, and then inputs the learning coefficients into the noise image for noise level estimation. Experiments demonstrate that the algorithm proposed in this paper can significantly improve the underestimation problem of the traditional algorithm and has better estimation accuracy for various noise levels in gray images, color images, and texture images of various scenes. [ABSTRACT FROM AUTHOR]

In 1976–1977, Polyak published in the journal Avtomatica i Telemekhanika (Automation and Remote Control) two remarkable papers on how to study the properties of estimates of iterative pseudogradient algorithms. The first paper published in 1976 considered the general case based on the stochastic Lyapunov function, and the second one considered the linear case. The assumptions formulated in these papers and the estimates obtained in them can still be considered the state-of-the art. In the current paper, Polyak's approach is applied to the study of the properties of estimates of a (randomized) stochastic approximation search algorithm for the case of unknown-but-bounded noise in observations. The obtained asymptotic estimates were already known earlier, and exact estimates for a finite number of observations are published for the first time. [ABSTRACT FROM AUTHOR]

With the gradual transformation of chemical industry park to digital and intelligent, various types of environmental data in the park are extremely rich. It has high application value to provide safe production environment by deeply mining environmental data law and providing data support for industrial safety and workers' health in the park through prediction means. This paper takes the noise data of the chemical industry park as the main research object, and innovatively applies the 3σ principle to the zero-value processing of the noise data, and builds an LSTM model that integrates multivariate information based on the characteristics of the wind direction classification noise data combined with the wind speed and vehicle flow information. The Prophet model integrating multi-site noise information was adopted, and the Multi-PL model was constructed by fitting the above two models to predict the noise. This paper designs and implements a comparative experiment with Kalman filter, BP neural network, Prophet, LSTM, Prophet + LSTM weighted combination prediction model. R2 was used to evaluate the fitting effect of single model in Multi-PL, RMSE and MAE that were used to evaluate the prediction effect of Multi-PL on noise time series. The experimental results show that the RMSE and MAE of the data processed by the 3σ principle are reduced by 32.2% and 23.3% in the multi-station ordered Prophet method, respectively. Compared with the above comparison models, the Multi-PL model prediction method is more stable and accurate. Therefore, the Multi-PL method proposed in this paper can provide a new idea for noise prediction in digital chemical parks. [ABSTRACT FROM AUTHOR]

Purpose: The braking system used on a recently upgraded metro vehicle showed very high low-frequency noise and vibrations levels in service affecting passengers' comfort and leading to both brake calliper lever failures and to premature wear of brake pads. The characteristics of the phenomenon were such that it was classified as a groan noise type. As brake pads with different characteristics were tested trying to attenuate the issue without success, the paper describes the approach adopted by the authors to tackle the issue. Methods: The dynamic behaviour of all the components involved during the braking phase (wheelset, callipers, brake discs and part of the bogie frame) was analysed by numerical simulations and tests during service, finding a coincidence of the natural frequencies of the wheelset and the brake support. As this resonance was believed to be the root cause of the problem, a number of structural modifications were proposed. Results and Conclusions: After a careful selection process that included robustness and sensitivity analyses, the accepted modification proved to be effective in solving the issue and was applied with satisfaction to the whole fleet. [ABSTRACT FROM AUTHOR]

This paper investigates quantum error correction schemes for fully-correlated noise channels on an n-qubit system, where error operators take the form W ⊗ n , with W being an arbitrary 2 × 2 unitary operator. In previous literature, a recursive quantum error correction scheme can be used to protect k qubits using (k + 1) -qubit ancilla. We implement this scheme on 3-qubit and 5-qubit channels using the IBM quantum computers, where we uncover an error in the previous paper related to the decomposition of the encoding/decoding operator into elementary quantum gates. Here, we present a modified encoding/decoding operator that can be efficiently decomposed into (a) standard gates available in the qiskit library and (b) basic gates comprised of single-qubit gates and CNOT gates. Since IBM quantum computers perform relatively better with fewer basic gates, a more efficient decomposition gives more accurate results. Our experiments highlight the importance of an efficient decomposition for the encoding/decoding operators and demonstrate the effectiveness of our proposed schemes in correcting quantum errors. Furthermore, we explore a special type of channel with error operators of the form σ x ⊗ n , σ y ⊗ n and σ z ⊗ n , where σ x , σ y , σ z are the Pauli matrices. For these channels, we implement a hybrid quantum error correction scheme that protects both quantum and classical information using IBM's quantum computers. We conduct experiments for n = 3 , 4 , 5 and show significant improvements compared to recent work. [ABSTRACT FROM AUTHOR]

Automatic Speech Recognition (ASR) system is an emerging technology used in various fields such as robotics, traffic controls, and healthcare, etc. The leading cause of ASR performance degradation is mismatch between the training and testing environments. The main reason for this mismatch is the presence of noise during the testing phase of an ASR system. Various techniques have been used by different researchers in front and backend phases of ASR, to detect and handle the noise. However, a very few review papers have considered noise as a criterion to present the comparison among the existing research works. Hence, the objective of this survey is to analyze and review all the effective methods proposed by different scientists and researchers to boost the noise robustness of an ASR system. Initially, the paper discusses the basic architecture of an ASR system, the factors affecting the its performance, and noise problem formulation. Secondly, the work analysis existing state of the art noise robust ASR methods in terms of front end feature extraction techniques and backend classification model. Then, a detailed review in terms of various speech databases, that are used by these methods, is given. Finally, an analysis in terms of performance metrics of all these noise-resistant ASR techniques is presented. Also, the paper discusses various feature extraction techniques, backend classification methods, different speech databases and performance metrics in detail, while presenting the analysis. The paper also discusses the existing challenges, and describes future research directions in the area of building noise-resistant ASR systems. [ABSTRACT FROM AUTHOR]

In recent years, time-domain electromagnetic method, as a rookie of electromagnetic method, is widely used in shallow surface physical survey. When the terrain is too steep, the survey points are distributed unevenly. This paper proposes a quasi-three-dimensional inversion method suitable for general conditions, which has universality. In addition, the current electrical survey and inversion methods have problems such as rough results and low accuracy. In order to obtain a better geological interpretation, this paper proposes a pseudo-three-dimensional inversion method suitable for non-uniform distribution. The simulation sets up a set of 3D models of underground isomers and background noise to simulate the actual environment. In geological interpretation, the outline of the model and the boundary of the strata are complete and smooth. The experimental results demonstrate the rationality and reliability of the method, and it is suitable for non-uniform field surveys. [ABSTRACT FROM AUTHOR]

The aim of this scoping review was to synthesize research assessing the effect of classroom acoustic conditions on children's physical health and identify areas for future research. This scoping review followed the PRISMA-ScR protocol. A comprehensive search of four online databases (ERIC, PubMed, Scopus, and Web of Science) was conducted using the search term classroom AND (acoustic* OR noise OR reverb*) AND health. Peer-reviewed journal articles were included if they were written in English, included children in the primary school age range (i.e. 5–12 years), and included a measure of children's physical health. Eight papers out of the 407 papers returned in the search met the criteria to be included in the review. The results were analysed according to the effect of traffic noise, aircraft noise, and internal classroom noise on children's physical health. The results were somewhat mixed, but overall they suggest that noise may have a negative effect on children's physical health by inducing a stress response that results in asthma, fatigue, and headaches. Future research avenues are proposed to better understand the relationship between classroom acoustic conditions and children's physical health. [ABSTRACT FROM AUTHOR]