Noise Detection Research Articles

Detection of Active Infestation by Wood-Boring Insects via Acoustic Emission using the IADS (Insect Activity Detection System)

The preservation of wooden art and cultural artifacts is severely threatened by the infestation of wood-boring insects. Distinguishing between active and inactive infestations in practice poses a significant challenge, often leading to unnecessary treatments or delayed actions. This article focuses on the examination of the Insect Activity Detection System (IADS), an innovative AE measurement device for the detection of feeding noises of wood-boring larvae. Starting with an overview of the theoretical framework, the results of practical experiments are shown. Finally, we will present some possible applications of IADS in the conservation of art and cultural heritage.

Research on optimizing the optical local-oscillator power of Coherent Doppler LiDAR to enhance wind velocity measurements

Due to weak echo signals that become progressively overwhelmed by noise, measurement accuracy and effective detection range of the Coherent Doppler wind LiDAR (CDL) are often compromised. While increasing the optical local-oscillator power (OLP) can amplify the echo signal, it is constrained by the nonlinear effects of the detector. This paper introduces a method for optimizing the OLP in CDL systems. Theoretical analysis has been proposed to explore the amplification effect of OLP on echo signals, and the nonlinear effects of detectors have been studied. Simulations are performed to explore the influence of varying OLP on the signal-to-noise ratio (SNR) across different detector α (quadratic nonlinear coefficient) values. The spectral analysis method is used to directly compute the SNR of actual atmospheric wind field signals under various OLP settings. Results demonstrate consistency between calculated and simulated values, enabling determination of optimal OLP and the detector α values from fitted curves. Comparative experiments confirm significant enhancement in effective detection range (> 1.5 km) with ± 0.5 m/s accuracy. The innovation of this study lies in combining the OLP optimization method with real atmospheric wind field echo signal experiments. It addresses the challenges of directly measuring the nonlinear parameters of the detector and determining the optimal OLP. This study offers valuable theoretical and experimental insights for enhancing the wind measurement performance of CDL.

Integrating street-view images to quantify the urban soundscape: Case study of Fuzhou City's main urban areaa).

Soundscapes are an important part of urban landscapes and play a key role in the health and well-being of citizens. However, predicting soundscapes over a large area with fine resolution remains a great challenge and traditional methods are time-consuming and require laborious large-scale noise detection work. Therefore, this study utilized machine learning algorithms and street-view images to estimate a large-area urban soundscape. First, a computer vision method was applied to extract landscape visual feature indicators from large-area streetscape images. Second, the 15 collected soundscape indicators were correlated with landscape visual indicators to construct a prediction model, which was applied to estimate large-area urban soundscapes. Empirical evidence from 98 000 street-view images in Fuzhou City indicated that street-view images can be used to predict street soundscapes, validating the effectiveness of machine learning algorithms in soundscape prediction.

Use of deep learning to improve seismic data quality analysis

Seismic data are influenced by various types of noise, which are typically categorized into two primary classes: anthropogenic and environmental. However, the detection of instrumental noise or malfunctioning stations also plays a crucial role in ensuring the data quality and the efficiency of a seismic network. The visual inspection of seismic spectral diagrams (e.g. power spectral density) enables us to identify issues that could potentially compromise data quality, thereby affecting subsequent calculations such as Magnitude or Peak Ground Acceleration (PGA). However, this process is time-consuming and demands significant human expertise due to the complexity of the diagrams, compounded by the sheer number of stations requiring examination. Therefore, in this paper, we explore the feasibility of transferring human expertise into an artificial intelligence system to create an automated system capable of rapidly performing such detection. More specifically, in the first part of this paper, we use Probability Density Function (PDF) diagrams, enabling an initial assessment of station performance via visual inspection. We describe this plot type and provide examples that reveal whether a station is functioning correctly or if technical issues exist. A table containing the main evaluation criteria is provided. In the second part of this paper, we demonstrate that these plots can serve as input for a neural network, allowing the development of the aforementioned automated system. Through extensive testing under various conditions, we have observed that the trained network consistently achieves an accuracy rate exceeding 85% across all four conductedtests. In the latest and most significant test, the achieved accuracy is approximately 87%.

Objective Determination of Site-of-Lesion in Auditory Neuropathy.

Auditory neuropathy (AN), a complex hearing disorder, presents challenges in diagnosis and management due to limitations of current diagnostic assessment. This study aims to determine whether diffusion-weighted magnetic resonance imaging (MRI) can be used to identify the site and severity of lesions in individuals with AN. This case-control study included 10 individuals with AN of different etiologies, 7 individuals with neurofibromatosis type 1 (NF1), 5 individuals with cochlear hearing loss, and 37 control participants. Participants were recruited through the University of Melbourne's Neuroaudiology Clinic and the Murdoch Children's Research Institute specialist outpatient clinics. Diffusion-weighted MRI data were collected for all participants and the auditory pathways were evaluated using the fixel-based analysis metric of apparent fiber density. Data on each participant's auditory function were also collected including hearing thresholds, otoacoustic emissions, auditory evoked potentials, and speech-in-noise perceptual ability. Analysis of diffusion-weighted MRI showed abnormal white matter fiber density in distinct locations within the auditory system depending on etiology. Compared with controls, individuals with AN due to perinatal oxygen deprivation showed no white matter abnormalities ( p > 0.05), those with a neurodegenerative conditions known/predicted to cause VIII cranial nerve axonopathy showed significantly lower white matter fiber density in the vestibulocochlear nerve ( p < 0.001), while participants with NF1 showed lower white matter fiber density in the auditory brainstem tracts ( p = 0.003). In addition, auditory behavioral measures of speech perception in noise and gap detection were correlated with fiber density results of the VIII nerve. Diffusion-weighted MRI reveals different patterns of anatomical abnormality within the auditory system depending on etiology. This technique has the potential to guide management recommendations for individuals with peripheral and central auditory pathway abnormality.

Extension of the characterization of non-Gaussianity in gravitational wave detectors with a statistical hypothesis test

Abstract In gravitational wave (GW) astronomy, non-Gaussian noise, such as scattered light noise disturbs stable interferometer operation, limiting the interferometer’s sensitivity, and reducing the reliability of the analyses. In scattered light noise, the non-Gaussian noise dominates the sensitivity in a low frequency range of less than a few hundred Hz, which is sensitive to GWs from compact binary coalescence. This non-Gaussian noise prevents reliable parameter estimation, since several analysis methods are optimized only for Gaussian noise. Therefore, identifying data contaminated by non-Gaussian noise is important. In this work, we extended the conventional method to evaluate non-Gaussian noise, the Rayleigh statistic, by using a statistical hypothesis test to determine a threshold for non-Gaussian noise. First, we estimated the distribution of the Rayleigh statistic against Gaussian noise, called the background distribution, and validated that our extension serves as the hypothetical test. The threshold on the Rayleigh statistic is estimated at 0.73 and 1.28 when the significance level is 0.05, and the sample size is 39. Moreover, we investigated the detection efficiency by assuming two non-Gaussian noise models. For example, for the model with strong scattered light noise, the true positive rate (TPR) was always above 0.7 when the significance level was 0.05. For the demonstration, we applied our extension with the estimated thresholds to the real data. We confirmed our extension provides the binarized outputs of the statistical tests and contributes to finding the non-Gaussian noise in the real data. The results showed that our extension can contribute to an initial detection of non-Gaussian noise and lead to further investigation of the origin of the non-Gaussian noise.

Enabling Low‐Noise, High‐Detectivity, Stable, and Flexible Perovskite Mesh Nanowire Photodetectors by Phenylethylamine Iodine Doping Strategy

AbstractThe poor stability, high noise, and low detectivity (D*) of perovskite mesh nanowire (PMN) photodetectors (PDs) seriously hinder their practical applications. Here, a phenylethylamine iodine doping strategy (PIDS) is introduced to solve these problems. The PIDS leads to the formation of 2D perovskite PEA2MAx‐1PbxI3x+1 (PEA = phenylethylamine, MA = methylamine) within MAPbI3 PMN, which not only prevents water and oxygen erosion to thwart PMN degradation but also inhibits the transport of dark state carriers to reduce dark current. As a result, the noise, D*, and stability of the PMN PD are simultaneously improved. The device exhibits low noise current (7.61 × 10−15 A Hz−1/2) and high D* of 3.2 × 1014 Jones, the highest D* value for PMN PDs reported to date. Moreover, the unpacked device sustains 100% of its initial performance after 2880 h of storage in the air (45–55% humidity), enabling it as the most stable MAPbI3 perovskite micro/nanostructure PD reported to date. Furthermore, the flexible device with PIDS exhibits comparable performance to that of the rigid device as well as great mechanical stability. Finally, the flexible device with PIDS demonstrates excellent optical imaging capability and a higher precision optical imaging potential than the commercial silicon photodiode S2386.

A cloud‐based hybrid intrusion detection framework using XGBoost and ADASYN‐Augmented random forest for IoMT

AbstractInternet of Medical Things have vastly increased the potential for remote patient monitoring, data‐driven care, and networked healthcare delivery. However, the connectedness lays sensitive patient data and fragile medical devices open to security threats that need robust intrusion detection solutions within cloud‐edge services. Current approaches need modification to be able to handle the practical challenges that result from problems with data quality. This paper presents a hybrid intrusion detection framework that enhances the security of IoMT networks. There are three modules in the design. First, an XGBoost‐based noise detection model is used to identify data anomalies. Second, adaptive resampling with ADASYN is done to fine‐tune the class distribution to address class imbalance. Third, ensemble learning performs intrusion detection through a Random Forest classifier. This stacked model coordinates techniques that filter noise and preprocess imbalanced data, identifying threats with high accuracy and reliability. These results are then experimentally validated on the UNSW‐NB15 benchmark to demonstrate effective detection under realistically noisy conditions. The novel contributions of the work are a new hybrid structural paradigm coupled with integrated noise filtering, and ensemble learning. The proposed advanced oversampling with ADASYN gives a performance that surpasses all others with a reported 92.23% accuracy.

Screening diabetic retinopathy and exudates in retinal images using dual functional convolutional neural networks

Exudates are the abnormal pattern lesions in Diabetic Retinopathy (DR) images, which is the primary cause of DR in diabetic patients. Therefore, its detection process is essential for further severity estimation of DR images. Automated detection systems’ robustness can be hampered by training datasets that are not representative. In this paper, the DR image is detected and classified using the proposed Dual Functional Convolutional Neural Networks (DFCNN). This proposed system consists of a noise detection and removal subblock, enhancement subblock, Gabor transform subblock, Feature computation subblock, and the proposed CNN classification architecture subblock. This proposed methodology is divided into two modules: a training module and a testing module. In the training module, the proposed DFCNN classification architecture is used to train both the abnormal case (DR case) and the healthy case (HCA) retinal images. In the testing module, the test source retinal image is classified as either a beneficial or DR case retinal image. From the classified DR case retinal image, the exudates are identified through the segmentation process in this research work. This developed DR and exudates detection system stated in this paper are evaluated on DRIVE, and DIARETDB1 retinal images and the experimental results are conducted with respect to various performance metrics in this paper. Once the suggested methodology was compared to other classification approaches, the proposed method’s accuracy was found to be greater (99.4 %).

Classification and detection of noise in IoT based MQ gas sensors using artificial neural network

Abstract IoT-based Metal Oxide Semiconductor (MOS) gas sensors have potential applications in health, industrial, and agriculture sectors. MQ gas sensors are easy to use, have a large detection range, high sensitivity, and efficiency, and can be interfaced with Arduino for effective use. However, like other any other sensors, the MQ gas sensors are also not able to escape the effect of noise that affects the sensitivity and selectivity causing the unwanted wrong classification and identification of gases, etc finally leading to a wrong justification of results and data. Hence, the study of noise and its removal is very crucial for greater accuracy in its analysis. The main aim of our work is to check whether one can classify different types of noises or noisy signals accurately using even simple ANNs so that after testing the different filtration techniques for the signals we can obtain an independent system specifically for the MQ gas sensors, that can classify as well as filter the noisy signals based on the category to which they are classified. The best and most effective noise filtration method is then obtained. During the study Narrow Neural Network model and Medium Neural Network demonstrated high accuracy in validation and testing, with ROC curves indicating their efficiency and effectiveness.

Development of PIND system based on resonant sensors and research on material identification methods for redundant particles

Abstract Aiming at the problems of the existing particle impact noise detection (PIND) system, such as low detection accuracy, high rate of misjudgment and missed judgment, and the inability to judge the material of internal redundant particles in real time, a method for automatic detection and material identification of redundant particles based on neural network recognition is proposed, and an automatic detection system for redundant particles of sealed electronic devices is developed. The system is equipped with multi-channel piezoelectric resonant sensors, which convert the redundant particle impact noise signal into a voltage signal, and then transmit the signal to the host using a high-speed data acquisition system. The upper computer uses a short-term energy threshold detection method to extract signal pulses; Then, a variety of time and frequency domain features are extracted and combined with wavelet domain features; Finally, by training the multi output neural network prediction model, it can automatically judge whether there are redundant particles in the tested parts, and automatically give the material information of the redundant particles. Experiments show that the accuracy of the system for material recognition of redundant particles with a mass greater than 0.1 mg can reach 88.6%.

Magnetic Indicator for Evaluating Cu Clustering and Hardening Effect in RPV Model Alloy

The reactor pressure vessel (RPV) is a critical barrier in nuclear power plants, but its embrittlement during service poses a significant safety challenge. This study investigated the effects of Cu-enriched clusters on the mechanical and magnetic properties of Fe-0.9 wt.%Cu model alloys through thermal aging. Using Vickers hardness tests, Magnetic Barkhausen Noise (MBN) detection, and Atom Probe Tomography (APT), the study aimed to establish a quantitative correlation between MBN signals, Vickers hardness, and Cu-enriched clusters, facilitating the non-destructive testing of RPV embrittlement. Experimental results showed that the hardness and MBN parameters (RMS and Vpp values) changed significantly with aging time. The hardness increased rapidly in the early stage (under-aged), followed by a plateau and then a decreasing trend (over-aged). In contrast, MBN parameters decreased initially and then increased. APT analysis revealed that Cu-enriched clusters increase in size to 4.60 nm and coalesced during aging, with their number density peaking to 3.76 × 1023 m−3 before declining. An inverse linear correlation was found between MBN signals and the combined factor Nd2Rg (product of the number density squared and the mean radius of Cu-enriched clusters). This correlation was consistent across both under-aged and over-aged states, suggesting that MBN signals can serve as applicable indicators for the non-destructive evaluation of RPV steel embrittlement.

Rapid identification of time-frequency domain gravitational wave signals from binary black holes using deep learning* *Supported by the National SKA Program of China (2022SKA0110200, 2022SKA0110203), the National Natural Science Foundation of China (12473001, 11975072, 11875102, 11835009), and the National 111 Project (B16009)

Recent developments in deep learning techniques have provided alternative and complementary approaches to the traditional matched-filtering methods for identifying gravitational wave (GW) signals. The rapid and accurate identification of GW signals is crucial to the advancement of GW physics and multi-messenger astronomy, particularly considering the upcoming fourth and fifth observing runs of LIGO-Virgo-KAGRA. In this study, we used the 2D U-Net algorithm to identify time-frequency domain GW signals from stellar-mass binary black hole (BBH) mergers. We simulated BBH mergers with component masses ranging from 7 to 50 and accounted for the LIGO detector noise. We found that the GW events in the first and second observation runs could all be clearly and rapidly identified. For the third observing run, approximately 80% of the GW events could be identified. In contrast to traditional convolutional neural networks, the U-Net algorithm can output time-frequency domain signal images corresponding to probabilities, providing a more intuitive analysis. In conclusion, the U-Net algorithm can rapidly identify the time-frequency domain GW signals from BBH mergers.

Pothole detection and International Roughness Index (IRI) calculation using ATVs for road monitoring

The accelerated deterioration of roads is conditioned by parameters such as climate change, poor construction, and heavy vehicle traffic. Two relevant measures to monitor the condition of a road are the International Roughness Index (IRI) and the number of functional failures in a segment, mainly potholes, since they are associated with higher risks such as accidents or damage to vehicle mechanics. In the state of the art, pothole detection or International Roughness Index (IRI) calculation algorithms are proposed, but they use vehicles designed to produce less vibration and use phones that decrease the performance of the embedded sensors. In addition, some works propose complex algorithms of higher computational load that leads to use more hardware and power consumption. In this context, the present work aims to monitor the condition of a road through low-cost dedicated sensors implemented in an urban patrolling all-terrain vehicles (ATVs), where energy consumption is optimized using low-complexity signal processing techniques for noise reduction and detection algorithms. The results show an average accuracy of 90.5% in the detection of potholes, a relative error of 8.41% in the calculation of the International Roughness Index (IRI) and an average reduction of 65.4% in the monitoring time.

Performance of the SOAR Speckle Instrument

The High Resolution Camera (HRCam) speckle imager at the 4.1 m Southern Astrophysical Research telescope is a highly productive instrument that has accumulated about 40K observations to date. Its performance (detected flux, level of the speckle signal, signal-to-noise ratio, and limiting magnitude) is studied here using both the actual data and realistic simulations, including the detector noise. In the calculation of the speckle power spectrum, signal clipping is essential to reduce the noise impact and maximize the sensitivity. Increasing exposure time of individual frames beyond 30 ms does not improve the limiting magnitude, which ranges from 11.5 to 14 mag under a seeing from 1.″6 to 0.″6 in the wide-band I filter. A gain of at least one magnitude is expected if the current electron multiplication CCD is replaced by a high-end CMOS detector with a subelectron readout noise. This study will help in planning, executing, and automating future speckle observations with HRCam and other speckle imagers.

Generative adversarial networks with deep blind degradation powered terahertz ptychography

Ptychography is an imaging technique that uses the redundancy of information generated by the overlapping of adjacent light regions to calculate the relative phase of adjacent regions and reconstruct the image. In the terahertz domain, in order to make the ptychography technology better serve engineering applications, we propose a set of deep learning terahertz ptychography system that is easier to realize in engineering and plays an outstanding role. To address this issue, we propose to use a powerful deep blind degradation model which uses isotropic and anisotropic Gaussian kernels for random blurring, chooses the downsampling modes from nearest interpolation, bilinear interpolation, bicubic interpolation and down-up-sampling method, and introduces Gaussian noise, JPEG compression noise, and processed detector noise. Additionally, a random shuffle strategy is used to further expand the degradation space of the image. Using paired low/high resolution images generated by the deep blind degradation model, we trained a multi-layer residual network with residual scaling parameters and dense connection structure to achieve the neural network super-resolution of terahertz ptychography for the first time. We use two representative neural networks, SwinIR and RealESRGAN, to compare with our model. Experimental result shows that the proposed method achieved better accuracy and visual improvement than other terahertz ptychographic image super-resolution algorithms. Further quantitative calculation proved that our method has significant advantages in terahertz ptychographic image super-resolution, achieving a resolution of 33.09 dB on the peak signal-to-noise ratio (PSNR) index and 3.05 on the naturalness image quality estimator (NIQE) index. This efficient and engineered approach fills the gap in the improvement of terahertz ptychography by using neural networks.

Measurement and evaluation of personal attenuation rating before and after the training of the noise-exposed workers wearing foam earplugs

Objective: To measure and compare the difference of personal attenuation rating (PAR) of the workers wearing foam earplugs before and after the training, and to evaluate the effect of ear protector wearing training on the noise protection. Methods: In February 2023, 94 workers exposed to noise in a machinery manufacturing factory were selected as subjects. The production noise in the workplace was measured and subjects were trained to wear earplugs. The PAR values of wearing 3M 1110 foam test earplugs were measured and recorded before and after the training by using the fit testing of hearing protection device. The differences between the actual PAR values with nominal values and the noise attenuation values in related standards were compared, and the protective effect of hearing protection device before and after training was evaluated. Results: The average age of the subjects was (36.76±11.48) years old, the average length of service was (16.34±11.64) years, and the average exposure time to noise was (15.67±11.64) years. The noise detection results of the subjects' posts were ranged from 80.1 to 94.3 dB (A). The results of subjects wore 3M 1110 foam test earplugs for fit testing showed that the binaural PAR value after training was (19.3±6.4) dB (A), which was significantly higher than that before training (11.1±7.4) dB (A) (t=13.31, P<0.001). After training, 11 people (11.70%) could reach the corrected noise reduction value (NRR value), 26 people (27.66%) could reach the standard of single noise reduction value (SNR value) ×0.6, and 84 people (89.36%) could reach the standard of (NRR-7) /2. The under protection rate of hearing protectors after training (7.45%) was significantly lower than that before training (45.74%), and the difference of different protection levels before and after training was statistically significant (χ(2)=40.83, P<0.001) . Conclusion: It is suggested that enterprises should use the fit testing instead of nominal value estimation to evaluate the noise reduction effect of hearing protection device. Special training on the selection and use of hearing protection device should be strengthened, so as to ensure that workers wear them correctly and improve the protective effect of hearing protection device.

Denoising Drug Discovery Data for Improved Absorption, Distribution, Metabolism, Excretion, and Toxicity Property Prediction.

Predicting absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties of small molecules is a key task in drug discovery. A major challenge in building better ADMET models is the experimental error inherent in the data. Furthermore, ADMET predictors are typically regression tasks due to the continuous nature of the data, which makes it difficult to apply existing denoising methods from other domains as they largely focus on classification tasks. Here, we develop denoising schemes based on deep learning to address this. We find that the training error (TE) can be used to identify the noise in regression tasks while ensemble-based and forgotten event-based metrics fail to detect the noise. The most significant performance increase occurs when the original model is finetuned with the denoised data using TE as the noise detection metric. Our method has the ability to improve models with medium noise and does not degrade the performance of models with noise outside this range (low noise and high noise regimes). To our knowledge, our denoising scheme is the first to improve model performance for ADMET data and has implications for improving models for experimental assay data in general.

PET digitization chain for Monte Carlo simulation in GATE

Objective. We introduce a versatile methodology for the accurate modelling of PET imaging systems via Monte Carlo simulations, using the Geant4 application for tomographic emission (GATE) platform. Accurate Monte Carlo modelling involves the incorporation of a complete analytical signal processing chain, called the digitizer in GATE, to emulate the different count rates encountered in actual positron emission tomography (PET) systems. Approach. The proposed approach consists of two steps: (1) modelling the digitizer to replicate the detection chain of real systems, covering all available parameters, whether publicly accessible or supplied by manufacturers; (2) estimating the remaining parameters, i.e. background noise level, detection efficiency, and pile-up, using optimisation techniques based on experimental single and prompt event rates. We show that this two-step optimisation reproduces the other experimental count rates (true, scatter, and random), without the need for additional adjustments. This method has been applied and validated with experimental data derived from the NEMA count losses test for three state-of-the-art SiPM-based time-of-flight (TOF)-PET systems: Philips Vereos, Siemens Biograph Vision 600 and GE Discovery MI 4-ring. Main results. The results show good agreement between experiments and simulations for the three PET systems, with absolute relative discrepancies below 3%, 6%, 6%, 7% and 12% for prompt, random, true, scatter and noise equivalent count rates, respectively, within the 0–10 kBq·ml−1 activity concentration range typically observed in whole-body 18F scans. Significance. Overall, the proposed digitizer optimisation method was shown to be effective in reproducing count rates and NECR for three of the latest generation SiPM-based TOF-PET imaging systems. The proposed methodology could be applied to other PET scanners.

Robust Signal Detection in Complex Noise and Interference Environment Based on MoG Modeling

Robust Signal Detection in Complex Noise and Interference Environment Based on MoG Modeling