Categories Of Noise Research Articles

Noise and the risk of tinnitus: A two‐sample Mendelian randomized study

AbstractObjectivesObservational studies imply that noise may increase the likelihood of developing tinnitus. However, no causal relationship has been established between the two using Mendelian randomization (MR) analysis, we aimed to determine the potential causal relationship between noise and various categories of tinnitus.MethodsWe extracted single nucleotide polymorphisms (SNPs) associated with noise and tinnitus from a large genome‐wide association study (GWAS) of European individuals. UK Biobank (UKB) provided summary data for both entities. Inverse variance weighting (IVW) was implemented as the primary method for evaluating effect estimates. Using Weighted median and MR–Egger regression, heterogeneity and pleiotropy were evaluated using sensitivity analyses.ResultsThe random‐effects IVW approach revealed a causal relationship between noise and the three onset tinnitus (odds ratio [OR] = 1.052, 95% confidence interval [CI] = 1.013–1.092, p = 0.008; OR = 1.248, 95% CI = 1.177–1.323, p = 0.001; OR = 1.133, 95% CI = 1.058–1.213, p = 0.001). Noise was not a risk factor for tinnitus in the past (OR = 0.999, 95% CI = 0.934–1.068, p = 0.969). Validation with various Mendelian randomization methodologies and sensitivity analyses confirmed the findings' consistency.ConclusionThis Mendelian Randomization study provides causal evidence that noise is a risk factor for the onset of tinnitus but is not a risk factor for developing tinnitus in the past.

Effects of aircraft noise exposure on self-reported health through aircraft noise annoyance: Causal mediation analysis in the DEBATS longitudinal study in France.

Previous studies reported an association between transportation noise and self-reported health status (SRHS). They also suggested a mediating role of noise annoyance using conventional statistical methods. These methods are subject to bias in longitudinal studies with time-dependent exposure, mediator and confounding factors. This study aims to investigate the mediating role of aircraft noise annoyance in the effect of aircraft noise on SRHS using a causal inference approach to address time-dependent variables issues. We used data from 881 participants in all three visits in the DEBATS longitudinal study conducted around three French airports. Participants over 18 years of age reported their self-perceived health status, aircraft noise annoyance, and noise sensitivity by completing a questionnaire at three visits in 2013, 2015 and 2017. Noise maps were used to estimate aircraft noise levels outside their homes. Marginal structural models with inverse probability weighting were used to estimate the total effect of aircraft noise levels on SRHS and its decomposition into direct and indirect effect through aircraft noise annoyance. This study showed a deleterious effect of aircraft noise on SRHS. The odds ratio (OR) corresponding to the total effect and comparing the highest aircraft noise category (≥60 dBA) to the reference category (<50 dBA) was significant (ORpoor/fair_SHRS = 1.25 (95%CI: 1.06 to 2.08)). It also showed no direct effect of aircraft noise levels on SRHS, but an indirect effect through annoyance. This indirect effect increased as aircraft noise levels increased, with a statistically significant OR when comparing the highest noise category (≥60 dBA) to the lowest (<50 dBA) (ORpoor/fair_SHRS = 1.16 (95%CI: 1.03 to 1.52)). Nearly 66% of aircraft noise's effect on SRHS was mediated by aircraft noise annoyance. This study supports the deleterious causal effect of aircraft noise on SRHS. The results highlight the important mediating role of aircraft noise annoyance in the causal pathway from exposure to aircraft noise to poor/fair SRHS.

The pickleball seven decibel challenge

Noise emission from outdoor pickleball play and its potential impact to surrounding community receptors is often characterized as an impulsive source of sound, which would be consistent with ISO 1996-1 definition for a regular impulsive sound source that includes "outdoor ball games" as an example. But some recent noise assessments including those that may be found online are leaning towards elevating pickleball noise emission to the highly impulsive category and thus affording it a 12 dB adjustment instead of the 5 dB adjustment for regular impulsive noise--hence, a 7 dB difference that if confirmed would make pickleball noise compliance with applicable community regulations and policies much more difficult. This paper elaborates on the impulse noise category distinction as it may apply to pickleball play, and summarizes apparent support (or lack thereof) to cross the seven-decibel divide and how that might influence court development growth for the rapidly growing pickleball sport and potentially affected neighboring communities.

Pneumonia Detection through Deep Learning: A Comparative Exploration of Classification and Segmentation Strategies

The Convolution Neural Network (CNN) algorithm is one of the most widely used methods for identifying and categorizing lung cancer. This paper covers the most suitable architecture and CNN algorithms for lung cancer and pneumonia deduction and classification. The main contributions to the diagnosis and classification of lung cancer with four steps are Nonlinear transfer learning framework (NLTF), Hierarchical Feature Mapping (HFM), Lifelong Partial Dissection (LPD), and Deep Lifelong Convolutional Neural Network (DLCNN). The application of non-local total fuzzy (NLTF) filtering removes various categories of noise after lung CT imageries and enhances cancer areas. The application of Hybrid Fuzzy Morphology (HFM) constructed segmentation to minimize the region of interest (ROI) for cancer using morphology opening and closing processes. Extraction of traits unique to each disease employing Lung Parenchyma Division (LPD) and extraction of deep seismic features using the Geometric Optimal Algorithm (GOA). Training and testing the proposed Deep Learning Convolutional Neural Network (DLCNN) model using the extracted features to classify benign, malignant lung cancers and Recent advancements in deep learning methods have shown accurate results in the investigation and diagnosis of medical image data, including the detection of pneumonia.

Sample-imbalanced wafer map defects classification based on auxiliary classifier denoising diffusion probability model

This paper research on the classification task of wafer map defects under imbalanced sample. To improve the number of imbalanced wafer maps, a denoising diffusion probabilistic model with auxiliary classifier is proposed to generate new wafer maps. The developed model has an U-net structure with multiple inputs and outputs, taking wafer images, noise degree and category features as inputs, and outputs predicted noise and prediction category. When performing data augmentation, the trained model gradually removes prediction noise from the initial random noise and obtains new wafers. Finally, the balanced wafer defect maps are classified using a residual neural network. The proposed auxiliary classifier denoising diffusion probabilistic model and residual neural networks (ACDDPM-ResNet) method has validated on the MIR-WM811K dataset and MixedWM38 dataset, and the defect classification results of the imbalanced wafer map are remarkable improved after data augmentation. In addition, the paper also discusses and analyzes the influence of the maximum noise addition steps and the data augmentation size on the accuracy of wafer classification. It is further validated that the proposed wafer map classification method based on data augmentation can solve the classification problem caused by sample imbalance.

Efficient parameter inference for gravitational wave signals in the presence of transient noises using temporal and time-spectral fusion normalizing flow* *Supported by the National SKA Program of China (2022SKA0110200, 2022SKA0110203), the National Natural Science Foundation of China (11975072, 11875102, 11835009), and the National 111 Project (B16009)

Glitches represent a category of non-Gaussian and transient noise that frequently intersects with gravitational wave (GW) signals, thereby exerting a notable impact on the processing of GW data. The inference of GW parameters, crucial for GW astronomy research, is particularly susceptible to such interference. In this study, we pioneer the utilization of a temporal and time-spectral fusion normalizing flow for likelihood-free inference of GW parameters, seamlessly integrating the high temporal resolution of the time domain with the frequency separation characteristics of both time and frequency domains. Remarkably, our findings indicate that the accuracy of this inference method is comparable to that of traditional non-glitch sampling techniques. Furthermore, our approach exhibits a greater efficiency, boasting processing times on the order of milliseconds. In conclusion, the application of a normalizing flow emerges as pivotal in handling GW signals affected by transient noises, offering a promising avenue for enhancing the field of GW astronomy research.

Assessing the Influence of Sensor-Induced Noise on Machine-Learning-Based Changeover Detection in CNC Machines.

The noise in sensor data has a substantial impact on the reliability and accuracy of (ML) algorithms. A comprehensive framework is proposed to analyze the effects of diverse noise inputs in sensor data on the accuracy of ML models. Through extensive experimentation and evaluation, this research examines the resilience of a LightGBM ML model to ten different noise models, namely, Flicker, Impulse, Gaussian, Brown, Periodic, and others. A thorough analytical approach with various statistical metrics in a Monte Carlo simulation setting was followed. It was found that the Gaussian and Colored noise were detrimental when compared to Flicker and Brown, which are identified as safe noise categories. It was interesting to find a safe threshold limit of noise intensity for the case of Gaussian noise, which was missing in other noise types. This research work employed the use case of changeover detection in (CNC) manufacturing machines and the corresponding data from the publicly funded research project (OBerA).

Effective Surrogate Gradient Learning With High-Order Information Bottleneck for Spike-Based Machine Intelligence.

Brain-inspired computing technique presents a promising approach to prompt the rapid development of artificial general intelligence (AGI). As one of the most critical aspects, spiking neural networks (SNNs) have demonstrated superiority for AGI, such as low power consumption. Effective training of SNNs with high generalization ability, high robustness, and low power consumption simultaneously is a significantly challenging problem for the development and success of applications of spike-based machine intelligence. In this research, we present a novel and flexible learning framework termed high-order spike-based information bottleneck (HOSIB) leveraging the surrogate gradient technique. The presented HOSIB framework, including second-order and third-order formation, i.e., second-order information bottleneck (SOIB) and third-order information bottleneck (TOIB), comprehensively explores the common latent architecture and the spike-based intrinsic information and discards the superfluous information in the data, which improves the generalization capability and robustness of SNN models. Specifically, HOSIB relies on the information bottleneck (IB) principle to prompt the sparse spike-based information representation and flexibly balance its exploitation and loss. Extensive classification experiments are conducted to empirically show the promising generalization ability of HOSIB. Furthermore, we apply the SOIB and TOIB algorithms in deep spiking convolutional networks to demonstrate their improvement in robustness with various categories of noise. The experimental results prove the HOSIB framework, especially TOIB, can achieve better generalization ability, robustness and power efficiency in comparison with the current representative studies.

Automated noise source identification and respective level estimation on mixed-noise construction environments

Noise control on construction sites is essential to manage project risks including safety accidents, worker's health, and civil complaints. This paper presents two advanced Audio Spectrogram Transformer-based models to identify noise source types and estimate their respective noise levels on complex construction environments. The classification model first differentiated the noise sources from mixed noise. Receiving the classification results, the regression model then estimated their noise levels. Nine categories of on-site noise (i.e., six construction and three external noises) were collected, a total of 234.4-min audio files, and mixed randomly with different ratios for the validation purpose. As a result, the models successfully classified the noise sources with F1-score of 0.901 and estimated the respective noise levels with an average absolute error of 0.573 dB. This study is expected to clarify the contributors of the measured noise levels, enabling strategic noise management and sophisticated feedback from on-site noise data.

Distantly Supervised Relation Extraction via Contextual Information Interaction and Relation Embeddings

Distantly supervised relation extraction (DSRE) utilizes an external knowledge base to automatically label a corpus, which inevitably leads to the problem of mislabeling. Existing approaches utilize BERT to provide instances and relation embeddings to capture a wide set of relations and address the noise problem. However, the method suffers from a single method of textual information processing, underutilizing the feature information of entity pairs in the relation embeddings part and being interfered with by noisy labels when classifying multiple labels. For this reason, we propose the contextual information interaction and relation embeddings (CIRE) method. First, we utilize BERT and Bi-LSTM to construct a neural network model to enhance contextual information interaction by filtering and supplementing sequence information through the error repair capability of the Bi-LSTM gating mechanism. At the same time, we combine the vector difference between entity pairs and entity pairs in the relation embeddings layer to improve the relation embeddings accuracy. Finally, we choose sparse softmax as the classifier, which improves the ability to control the noise categories by controlling the number of output categories. The experimental results show that our method significantly outperforms the baseline method and improves the AUC metric by 2.6% on the NYT2010 dataset.

Fast and Noise-Resilient Magnetic Field Mapping on a Low-Cost UAV Using Gaussian Process Regression.

This study presents a comprehensive approach to mapping local magnetic field anomalies with robustness to magnetic noise from an unmanned aerial vehicle (UAV). The UAV collects magnetic field measurements, which are used to generate a local magnetic field map through Gaussian process regression (GPR). The research identifies two categories of magnetic noise originating from the UAV's electronics, adversely affecting map precision. First, this paper delineates a zero-mean noise arising from high-frequency motor commands issued by the UAV's flight controller. To mitigate this noise, the study proposes adjusting a specific gain in the vehicle's PID controller. Next, our research reveals that the UAV generates a time-varying magnetic bias that fluctuates throughout experimental trials. To address this issue, a novel compromise mapping technique is introduced, enabling the map to learn these time-varying biases with data collected from multiple flights. The compromise map circumvents excessive computational demands without sacrificing mapping accuracy by constraining the number of prediction points used for regression. A comparative analysis of the magnetic field maps' accuracy and the spatial density of observations employed in map construction is then conducted. This examination serves as a guideline for best practices when designing trajectories for local magnetic field mapping. Furthermore, the study presents a novel consistency metric intended to determine whether predictions from a GPR magnetic field map should be retained or discarded during state estimation. Empirical evidence from over 120 flight tests substantiates the efficacy of the proposed methodologies. The data are made publicly accessible to facilitate future research endeavors.

Restoring speech intelligibility for hearing aid users with deep learning

Almost half a billion people world-wide suffer from disabling hearing loss. While hearing aids can partially compensate for this, a large proportion of users struggle to understand speech in situations with background noise. Here, we present a deep learning-based algorithm that selectively suppresses noise while maintaining speech signals. The algorithm restores speech intelligibility for hearing aid users to the level of control subjects with normal hearing. It consists of a deep network that is trained on a large custom database of noisy speech signals and is further optimized by a neural architecture search, using a novel deep learning-based metric for speech intelligibility. The network achieves state-of-the-art denoising on a range of human-graded assessments, generalizes across different noise categories and—in contrast to classic beamforming approaches—operates on a single microphone. The system runs in real time on a laptop, suggesting that large-scale deployment on hearing aid chips could be achieved within a few years. Deep learning-based denoising therefore holds the potential to improve the quality of life of millions of hearing impaired people soon.

The impact of covid-19 restrictions on complaints of noise made to a local authority in Northern Ireland - a case study.

The covid pandemic with national lockdowns and restrictions profoundly affected people's lives in many ways including the experience of neighbourhood noise. While initial research indicated a rise in noise complaints at the start of restrictions in London during Spring 2020 (Tong, 2021), a case study involving a single local authority in Northern Ireland indicates a different experience when the full 2020 year was analysed. Total number of complaints did not see a statistically significant increase when compared to the 5-year average. While there were increases in some categories of noise of interest (loud music and parties, noise associated with anti-social behaviour), the comparison with the 5-year average did not show a statistically significant difference. The only category of noise that seen an increase of significance was noise complaints relating to retail. This may be explained by increased demand in essential food retail as well as social distancing requirements, limitations to customers inside premises and changes made as the retail sector adapted. A wider study involving local authorities across Northern Ireland, the UK and across countries that experienced lockdown measures may reveal a more accurate picture of the impact of neighbourhood noise experienced during the covid pandemic.

Comparison of spectral subtraction noise reduction algorithms

Noise in media is any undesirable signal that masks relevant information content. The addition of noise to real-world data in any context is practically inevitable. Noise reduction algorithms in the past have addressed the problem but lacked adaptability to various real-world applications while also being time and resource extensive. Spectral subtraction provides a hybrid approach to noise reduction that incorporates versatility and efficient resource usage. This research tested the performance of two spectral subtraction noise reduction algorithms (stationary and non-stationary) across five categories of real-world noise (speech only, speech with natural noise, music, animal sounds, and noise only). The research question under study was how stationary and non-stationary spectral subtraction algorithms differ in their noise reduction performance when subjected to the various categories of noise. The testing was done based on normalized cross-correlation, which is the similarity between the noise-reduced audio and the original recording in each case. Non-stationary spectral subtraction performed better in samples where human speech was the target: speech only and speech with natural noise. Stationary spectral subtraction performed better when denoising music and animal sounds. This anomaly in performance between the two algorithms was only noted in categories with no human speech. These results exemplify the performance and versatility of different spectral subtraction algorithms. The category-specific results can be used to employ specific spectral subtraction algorithms for specific tasks for optimum performance.

Speech Enhancement via Mask-Mapping Based Residual Dense Network

Masking-based and spectrum mapping-based methods are the two main algorithms of speech enhancement with deep neural network (DNN). But the mapping-based methods only utilizes the phase of noisy speech, which limits the upper bound of speech enhancement performance. Masking-based methods need to accurately estimate the masking which is still the key problem. Combining the advantages of above two types of methods, this paper proposes the speech enhancement algorithm MM-RDN (masking-mapping residual dense network) based on masking-mapping (MM) and residual dense network (RDN). Using the logarithmic power spectrogram (LPS) of consecutive frames, MM estimates the ideal ratio masking (IRM) matrix of consecutive frames. RDN can make full use of feature maps of all layers. Meanwhile, using the global residual learning to combine the shallow features and deep features, RDN obtains the global dense features from the LPS, thereby improves estimated accuracy of the IRM matrix. Simulations show that the proposed method achieves attractive speech enhancement performance in various acoustic environments. Specifically, in the untrained acoustic test with limited priors, e.g., unmatched signal-to-noise ratio (SNR) and unmatched noise category, MM-RDN can still outperform the existing convolutional recurrent network (CRN) method in the measures of perceptual evaluation of speech quality (PESQ) and other evaluation indexes. It indicates that the proposed algorithm is more generalized in untrained conditions.

Noise Signal Recognition and Noise Reduction Algorithm of Ships

Based on the study of the sensing property of fiber bragg grating (FBG) sensor network, this paper takes hybrid wavelength division/time division multiplexing sensor network with high-capacity FBG as the research object to study noise source, noise category and traditional noise reduction algorithm. In accordance with the characteristic of crosstalk accumulation noise in the network, this paper proposes LCEEMD-LWT signal processing method, which uses the local complementary ensemble empirical mean decomposition (LCEEMD) method for signal preprocessing, and then adopts LWT technology to refine high-frequency signal and solve the related problems. Then this paper put forwards detrended fluctuation analysis (DFA) to evaluate the sensing signal of high-capacity FBG, preprocesses the sensing signal by LCEEWD-LWT method, and conducts a temperature sensing experiment. The average temperature error of the demodulating system is reduced from 0.2923℃ to 0.2357℃, which not only overcomes the shortcoming that the traditional signal processing method is not meticulous for high-frequency signal processing, but also avoids the problem that the signal processing time is too long, exerting a good effect on the signal pre-processing of high-capacity FBG. The method in this paper has certain theoretical and technical reference value for the signal processing and the improvement of sensing property of high-capacity FBG sensing demodulating system in engineering application.

Research on Sparse Denoising of Strong Earthquakes Early Warning Based on MEMS Accelerometers.

In view of the fact that the noise in the same frequency band as the useful signal in the MEMS acceleration sensor observation data cannot be effectively removed by traditional filtering methods, a denoising method for strong earthquake signals based on the theory of sparse representation and compressive sensing is proposed in this paper. This skillfully realized the separation of strong earthquake signals from noise by adopting a fixed dictionary and utilizing sparse characteristics. Furthermore, considering the weakness of the sparse denoising method based on the fixed dictionary in the high signal-to-noise ratio, a spare denoising method based on learning an over-complete dictionary is proposed. Through the initial given seismic data, the ideal over-complete dictionary is trained to achieve seismic data denoising. In addition, for the interference waves of non-seismic events, this paper proposes an idea based on sparse representation classification to remove such non-seismic interference directly. Combining the ideas of noise reduction and non-seismic event elimination, we can obtain a standard sparse anti-interference denoising model for earthquake early warning. It's innovative that this model implements the sparse theory into the field of earthquake early warning. According to the experimental results, in the case of heavy noise, the denoising model based on sparse representation can reach average SNR of 8.73 and an average MSE of 29.53, and the denoising model based on compression perception can reach average SNR of 7.29 and an average MSE 41.34, and the denoising model based on learning dictionary can reach average SNR 11.07 and average MSE 17.32. The performance of these models is better than the traditional FIR filtering method (average SNR -0.73 and average MSE 260.37) or IIR filtering method (average SNR 4.73 and average MSE 73.95). On the other hand, the anti-interference method of the sparse classification proposed in this paper can accurately distinguish non-seismic interference events from natural earthquakes. The classification accuracy of the method based on the noise category of the selected test data set reaches 100% and achieves good results.

A parametric study of nose landing gear noise in a large-scale aeroacoustic wind tunnel

The nose landing gear (NLG) of an aircraft considerably contributes to the undercarriage noise. In this paper, a large-scale testing program was conducted within the FL-17 5.5 m×4 m aeroacoustic wind tunnel in CARDC to characterize the effects from various parameters on the acoustic performance of a generic NLG model. Those investigated parameters include incoming flow velocity, wheel size, height, angle of attack and yaw angles. The test was majorly comprised of noise source localization and free-field sound pressure level spectra analysis. Two categories of tonal noise were distinguished depending on variation between frequency and incoming flow speed. Effects of the sideline directivity were analyzed, and it was found that the side distribution of OASPL shows a saddle-like trend with the flow/flight direction and the tonal noise changes significantly with directivity angle. Regarding spectral scaling, U∞7 was found to be more appropriate for a large-scale NLG model, while for a compact small-scale NLG model, the traditional U∞6 is still recommended. As to transitional size, a combination of U∞7 and U∞6 showed to be more suitable for scaling within the high and low frequency ranges respectively. Contributions of different elements to NLG noise to different noise sources were discussed, which were found not to be dependent on their relative sizes. Analysis of the wheel diameter showed it does not cause obvious changes to the overall spectra trend but can induce variation of the amplitude and frequency tones. When the wheel is sufficiently small, the upper head of the sliding piston can be directly exposed to the incoming flow and thus generate sharp tonal noise. In terms of NLG height, the main effects on the acoustic performance was found to be associated not with the change in the height itself, but rather with the accompanying changes from other elements. Finally, the effects of angle of attack (α) and yaw angle (β) were analyzed with results showing that the angle of attack could potentially lead to substantial changes in the acoustic performance, while the yaw angle within 0°-8° has minimal effects.

Recognition of Air Passengers' Willingness to Pay for Seat Selection for Imbalanced Data Based on Improved XGBoost

Passenger-paid seat selection is one of the important sources of ancillary revenue for airlines, and machine learning-based willingness-to-pay identification is of great practicality for airlines to accurately tap potential willing passengers. However, affected by periodic statistical errors, air passenger order data often has some problems such as high noise, high latitude, and unbalanced category. In view of this, this paper proposes a method for identifying air passengers' willingness to pay for seat selection based on improved XGBoost, which is improved and integrated from three stages: data, feature, and algorithm. The feasibility of the proposed multi-stage improved integration method is verified by real airline passenger dataset, and the experimental results show that the proposed improved method has better classification effect when compared with the classical six imbalance classification models, which provides a basis for accurate marketing of airline paid seat selection programs.

Perturbation-Based Frequency Domain Linear and Nonlinear Noise Estimation

In this paper, a new method for the separation of noise categories based on Four-Wave Mixing is presented. The theoretical analysis is grounded in the Gaussian Noise model and verified by split step simulations. The noise categories react differently to the introduced perturbations, by performing a set of perturbations the behaviour of the different categories can be separated by means of a least-square fitting. Given ASE is independent of the induced perturbations, it is possible to separate noise contributions. The analysis includes constant and variable power perturbations. The estimation of the noise categories is discussed from two points of view: NSR evolution post-DSP processing, and over the power spectral density in a notched region. The NSR estimation can only be performed at reception, whereas the power spectral density approach can be performed along the optical link if a high resolution Optical Spectrum Analyzer is available. Additionally, we perform a simple experimental verification considering of two WaveLogic 3 transceivers for the NSR, successfully estimating the nonlinear noise contributions.