Search

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. [ABSTRACT FROM AUTHOR]

In this research work, six different filters are applied on a low resolution 8 b/pixel gray-scale images, which operate on small sub-images (windows of 3×3 to 11×11 pixels). The enhanced images are used to compare the efficiency of the different six filters using the peak signal to noise ratio (PSNR) image quality measure. Noise peak elimination filter (PSNR)=36.63) outperforms others, such as median filter (PSNR=36.61), while corruption estimation (PSNR=36.03) significantly cuts processing time by only processing the corrupted pixels while maintaining image details. Mean filter (PSNR=34.05) is sensitive to outliers, which cause the image's sharpness and fine features to be lost. By avoiding averaging across edges, bimodal-averaging filter (PSNR=35.30), which improves on the mean filter, chooses the mean of the biggest population. The median-mean filtering (PSNR=36.32), which combines median and mean filters and determines the output pixel by averaging the median and some nearby pixels, is another improvement above averaging. [ABSTRACT FROM AUTHOR]

Knowledge graph reasoning (KGR) aims to infer new knowledge or detect noises, which is essential for improving the quality of knowledge graphs. Recently, various KGR techniques, such as symbolic- and embedding-based methods, have been proposed and shown strong reasoning ability. Symbolic-based reasoning methods infer missing triples according to predefined rules or ontologies. Although rules and axioms have proven effective, it is difficult to obtain them. Embedding-based reasoning methods represent entities and relations as vectors, and complete KGs via vector computation. However, they mainly rely on structural information and ignore implicit axiom information not predefined in KGs but can be reflected in data. That is, each correct triple is also a logically consistent triple and satisfies all axioms. In this paper, we propose a novel NeuRal Axiom Network (NeuRAN) framework that combines explicit structural and implicit axiom information without introducing additional ontologies. Specifically, the framework consists of a KG embedding module that preserves the semantics of triples and five axiom modules that encode five kinds of implicit axioms. These axioms correspond to five typical object property expression axioms defined in OWL2, including ObjectPropertyDomain, ObjectPropertyRange, DisjointObjectProperties, IrreflexiveObjectProperty and AsymmetricObjectProperty. The KG embedding module and axiom modules compute the scores that the triple conforms to the semantics and the corresponding axioms, respectively. Compared with KG embedding models and CKRL, our method achieves comparable performance on noise detection and triple classification and achieves significant performance on link prediction. Compared with TransE and TransH, our method improves the link prediction performance on the Hits@1 metric by 22.0% and 20.8% on WN18RR-10% dataset, respectively. [ABSTRACT FROM AUTHOR]

Knowledge graphs are used to store structured facts, which are presented in the form of triples, i.e., (head entity, relation, tail entity). Current large-scale knowledge graphs are usually constructed with (semi-) automated methods for knowledge extraction and the process inevitably introduces noise, which may affect the effectiveness of the knowledge representation. However, most traditional representation learning methods assume that the triples in knowledge graphs are correct and represent knowledge in a distributed manner accordingly. Therefore, noise detection on knowledge graphs is a crucial task. In addition, the incompleteness of knowledge graphs has also attracted people’s attention. The above problems are studied and a knowledge representation learning framework combining logical rules and relation path information is proposed, which accomplishes knowledge representation learning and achieves a mutual enhancement effect while detecting possible noise. Specifically, the framework is divided into a triple embedding part and a triple trustworthiness estimation part. In the triple embedding part, relation path information and logical rule information are introduced to construct a better knowledge representation based on the triple structure information, the latter of which is used to enhance the ability of relation path reasoning and the interpretability of the representation learning. In the triple trustworthiness estimation part, three types of information are further utilized to detect possible noise. Experiments are conducted on three public evaluated datasets and the results show that the model achieves significant performance improvement in tasks such as knowledge graph noise detection and knowledge complementation compared with all baseline methods.

When a digital image with a lot of healthy salt and pepper (SP) pixels is corrupted by salt and pepper noises (SPNs) current solutions for SPN removal have difficulty distinguishing the healthy SP pixels from the noisy ones. Consequently, they often exhibit low performance when the original image contains patches of salt or/and pepper pixels. This paper introduces a new SPN removal approach called Supervised Hierarchical Clustering Filter (SHCF) capable of removing high density SP noises. SHCF first assigns a label to each pixel: W to white, B to black and N to the remaining pixels. Next, a supervised hierarchical clustering (SHC) approach is employed to build a tree of pixels called SHC-tree. SHC-trees are constructed maximizing cluster purities in the intermediate nodes. After the tree has been fully built, it is trimmed by extracting 100% purity clusters from the tree. Clusters with black or white pixels of size smaller than a user-defined minimum cluster size threshold are considered outliers and their pixels are marked as corrupted. The rest of the pixels in the image are marked as healthy. In its final step—unlike existing approaches—SHCF uses a replacement method that is order independent; that is, the order in which the corrupt pixels are replaced does not have any bearing on the final restoration result. We conducted experiments on images containing a lot of salt/pepper pixels as well as on standard test images. The results show that SHCF exhibits competitive performances compared to its direct competitors on standard test images. At high density noise level, it outperforms its competitors on average by 16% on images containing large amount of black and white pixels. [ABSTRACT FROM AUTHOR]

Audio recording in classrooms is a common practice in educational research, with applications ranging from detecting classroom activities to analyzing student behavior. Previous research has employed neural networks for classroom activity detection and speaker role identification. However, these recordings are often affected by background noise that can hinder further analysis, and the literature has only sought to identify noise with general filters and not specifically designed for classrooms. Although the use of high-end microphones and environmental monitoring can mitigate this problem, these solutions can be costly and potentially disruptive to the natural classroom environment. In this context, we propose the development of a novel neural network model that specifically detects and filters out problematic audio sections in classroom recordings. This model is particularly effective in reducing transcription errors, achieving up to a 96% success rate in filtering out segments that could lead to incorrect automated transcriptions. The novelty of our work lies in its targeted approach for low-budget, aurally complex environments like classrooms, where multiple speakers are present. By allowing the use of lower-quality recordings without compromising analysis capability, our model facilitates data collection in natural educational settings and reduces the dependency on expensive recording equipment. This advancement not only demonstrates the practical application of specialized neural network filters in challenging acoustic environments but also opens new avenues for enhancing audio analysis in educational research and beyond. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

ObjectiveIn order to solve the problem that noise detection inside a cabin is difficult due to the complexity and narrow space, a local space planning method of a manipulator based on the goal-oriented rapidly-exploring random tree (RRT) algorithm is proposed. MethodA six-degrees-of-freedom (6-DOF) manipulator is used as the carrier, and a fixture is installed at the end of the manipulator. The four fixed points inside the cabin are used as the reference points to study the mechanical arm in the local space. The trajectory planning is traversed and the reference point-1 is taken as an example to measure the noise of its 6 measurement surfaces and 147 measurement points. The noise signal and the position and attitude information of the space to be measured are matched and analyzed, and the environmental noise of the current measurement point is fed back to form a sound pressure cloud map. ResultsThe experimental results show that the robotic arm can realize trajectory planning and noise measurement for all measurement points corresponding to the four reference points without collision. ConclusionThe proposed method has practical value in being able to realize intelligent planning and internal noise detection in narrow cabin areas.

Chemical Exchange Saturation Transfer (CEST) magnetic resonance imaging (MRI) provides a novel method for analyzing biomolecule concentrations in tissues without exogenous contrast agents. Despite its potential, achieving a high signal-to-noise ratio (SNR) is imperative for detecting small CEST effects. Traditional metrics such as Magnetization Transfer Ratio Asymmetry (MTRasym) and Lorentzian analyses are vulnerable to image noise, hampering their precision in quantitative concentration estimations. Recent noise-reduction algorithms like principal component analysis (PCA), nonlocal mean filtering (NLM), and block matching combined with 3D filtering (BM3D) have shown promise, as there is a burgeoning interest in the utilization of neural networks (NNs), particularly autoencoders, for imaging denoising. This study uses the Bloch–McConnell equations, which allow for the synthetic generation of CEST images and explores NNs efficacy in denoising these images. Using synthetically generated phantoms, autoencoders were created, and their performance was compared with traditional denoising methods using various datasets. The results underscored the superior performance of NNs, notably the ResUNet architectures, in noise identification and abatement compared to analytical approaches across a wide noise gamut. This superiority was particularly pronounced at elevated noise intensities in the in vitro data. Notably, the neural architectures significantly improved the PSNR values, achieving up to 35.0, while some traditional methods struggled, especially in low-noise reduction scenarios. However, the application to the in vivo data presented challenges due to varying noise profiles. This study accentuates the potential of NNs as robust denoising tools, but their translation to clinical settings warrants further investigation. [ABSTRACT FROM AUTHOR]

Ensuring bridge safety and longevity through precise vehicle load characterization is crucial for maintaining structural integrity and efficiency. This research highlights the efficacy of deep convolutional neural networks (DCNNs) in analyzing bridge responses. The proposed methodology incorporates abridge model developed in ANSYS APDL, integrated subsequently with Universal Mechanism (UM) software for simulating vehicle-bridge interactions, considering factors such as vehicle load, speed, road surface roughness, and ambient noise. To validate the accuracy and robustness of the DCNN models, the study involved training and testing them on diverse datasets, each comprising 250 randomized samples for various parameters such as load, speed, and surface roughness. Two popular deep learning frameworks, ResNet and Inception models, were employed to assess their capability to identify these critical vehicle-bridge interaction characteristics accurately. The results reveal that the Inception model excelled in vehicle load identification, achieving an impressive validation accuracy of 99.9%. In contrast, ResNet outperformed in vehicle speed identification with a99% validation accuracy, surpassing Inception’s 97.9%. Both models exhibited remarkable resilience to noise, with road surface roughness identification demonstrating exceptional performance, including aperfect 100% training accuracy for ResNet and 99.9% for Inception. Furthermore, to validate the noise robustness of the DCNN model, the load identification is conducted under the effects of measurement noise, and the identification results show that the DCNN model can accurately identify vehicle loads with accuracies of 97.9% at 10 dB and 99.7% at 20 dB, respectively. These findings firmly establish the DCNNs’ capability to accurately identify vehicle load, speed, and road surface roughness, emphasizing their potential to significantly improve bridge safety and longevity.

Copyright of Journal of Central China Normal University is the property of Huazhong Normal University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

A library visitor would want a quiet atmosphere without noise when in the library so that he can concentrate when reading a book. However, not all visitors come to the library to read books; some want to chat and use free Wi-Fi or other, so it disturbs the concentration of other visitors who read books. Therefore, it is necessary to have a tool to detect sound pressure or sound based on the sound level and the sound produced in a library based on the noise level limit in the library, namely 45-55 dB (desible). This tool is designed based on a microcontroller where the definition of a microcontroller is a complete microprocessor system contained in a microcontroller chip which is different from the multi-purpose microprocessor used in a PC because a microcontroller generally already includes the minimum system supporting components of a microprocessor, namely memory, and programming. This tool can help officers monitor the library room for noise that can interfere with the concentration and comfort of library visitors. Based on the results of testing, the overall system is as desired, including the noise detection tool can work in an integrated system, where when the sound sensor detects a noise that exceeds the sound limit, the buzzer will sound, the red led light turns on, the sound module issues a voice message pre-recorded and also the device can be controlled or monitored from the web application.

Background radiation in the LiDAR detection field of view is complex and variable, and the background noise generated can easily cause false alarms in the receiver, which affects the effective detection of the system. Through the analysis of the influence of background radiation noise of LiDAR on the detection performance, an adaptive suppression method of LiDAR background noise is proposed. This method realizes the rapid suppression of background noise in the instantaneous field of view through an adaptive threshold adjustment of current steering architecture with a back-end digital-to-analog converter (DAC) correction based on the principle of constant false alarm rate (CFAR) control. Aiming at the problem of accurate noise detection and quantification in a very short time, a dynamic comparator is used to replace the traditional continuous comparator. While detecting the number of noise pulses, the measurement of the pulse duration of noise is realized, which improves the accuracy of short-time noise detection. In order to verify the actual effect of the adaptive method, experiments were carried out based on the team's self-developed LiDAR. The experimental results show that the measured noise ratio of the adaptive mode by using this method is the lowest. Even at 12 a.m., the noise ratio of the point cloud obtained by the adaptive mode is 0.012%, compared with 0.08% obtained by the traditional mode, which proves that this method has a good ability to suppress background noise. The proportion of noise reduction of the adaptive mode is more than 80% compared with the traditional mode. It achieves noise suppression through hardware at each detection, and each adjustment can be completed within a single period of pulse detection. Therefore, it has great advantages in real-time detection compared with the back-end software noise reduction processing method, and it is suitable for the application of LiDAR in the complex background environment. [ABSTRACT FROM AUTHOR]

Audio recording in classrooms is a common practice in educational research, with applications ranging from detecting classroom activities to analyzing student behavior. Previous research has employed neural networks for classroom activity detection and speaker role identification. However, these recordings are often affected by background noise that can hinder further analysis, and the literature has only sought to identify noise with general filters and not specifically designed for classrooms. Although the use of high-end microphones and environmental monitoring can mitigate this problem, these solutions can be costly and potentially disruptive to the natural classroom environment. In this context, we propose the development of a novel neural network model that specifically detects and filters out problematic audio sections in classroom recordings. This model is particularly effective in reducing transcription errors, achieving up to a 96% success rate in filtering out segments that could lead to incorrect automated transcriptions. The novelty of our work lies in its targeted approach for low-budget, aurally complex environments like classrooms, where multiple speakers are present. By allowing the use of lower-quality recordings without compromising analysis capability, our model facilitates data collection in natural educational settings and reduces the dependency on expensive recording equipment. This advancement not only demonstrates the practical application of specialized neural network filters in challenging acoustic environments but also opens new avenues for enhancing audio analysis in educational research and beyond.

Health-tracking from photoplethysmography (PPG) signals is significantly hindered by motion artifacts (MAs). Although many algorithms exist to detect MAs, the corrupted signal often remains unexploited. This work introduces a novel method able to reconstruct noisy PPGs and facilitate uninterrupted health monitoring. The algorithm starts with spectral-based MA detection, followed by signal reconstruction by using the morphological and heart-rate variability information from the clean segments adjacent to noise. The algorithm was tested on (a) 30 noisy PPGs of a maximum 20 s noise duration and (b) 28 originally clean PPGs, after noise addition (2–120 s) (1) with and (2) without cancellation of the corresponding clean segment. Sampling frequency was 250 Hz after resampling. Noise detection was evaluated by means of accuracy, sensitivity, and specificity. For the evaluation of signal reconstruction, the heart-rate (HR) was compared via Pearson correlation (PC) and absolute error (a) between ECGs and reconstructed PPGs and (b) between original and reconstructed PPGs. Bland-Altman (BA) analysis for the differences in HR estimation on original and reconstructed segments of (b) was also performed. Noise detection accuracy was 90.91% for (a) and 99.38–100% for (b). For the PPG reconstruction, HR showed 99.31% correlation in (a) and >90% for all noise lengths in (b). Mean absolute error was 1.59 bpm for (a) and 1.26–1.82 bpm for (b). BA analysis indicated that, in most cases, 90% or more of the recordings fall within the confidence interval, regardless of the noise length. Optimal performance is achieved even for signals of noise up to 2 min, allowing for the utilization and further analysis of recordings that would otherwise be discarded. Thereby, the algorithm can be implemented in monitoring devices, assisting in uninterrupted health-tracking.

Chemical Exchange Saturation Transfer (CEST) magnetic resonance imaging (MRI) provides a novel method for analyzing biomolecule concentrations in tissues without exogenous contrast agents. Despite its potential, achieving a high signal-to-noise ratio (SNR) is imperative for detecting small CEST effects. Traditional metrics such as Magnetization Transfer Ratio Asymmetry (MTRasym) and Lorentzian analyses are vulnerable to image noise, hampering their precision in quantitative concentration estimations. Recent noise-reduction algorithms like principal component analysis (PCA), nonlocal mean filtering (NLM), and block matching combined with 3D filtering (BM3D) have shown promise, as there is a burgeoning interest in the utilization of neural networks (NNs), particularly autoencoders, for imaging denoising. This study uses the Bloch–McConnell equations, which allow for the synthetic generation of CEST images and explores NNs efficacy in denoising these images. Using synthetically generated phantoms, autoencoders were created, and their performance was compared with traditional denoising methods using various datasets. The results underscored the superior performance of NNs, notably the ResUNet architectures, in noise identification and abatement compared to analytical approaches across a wide noise gamut. This superiority was particularly pronounced at elevated noise intensities in the in vitro data. Notably, the neural architectures significantly improved the PSNR values, achieving up to 35.0, while some traditional methods struggled, especially in low-noise reduction scenarios. However, the application to the in vivo data presented challenges due to varying noise profiles. This study accentuates the potential of NNs as robust denoising tools, but their translation to clinical settings warrants further investigation.

In three-dimensional (3D) airborne light detection and ranging (LiDAR) point-cloud data acquisition, noise point clusters (such as cloud, birds and incomplete scanning ground points) and isolated points are usually generated in the scanning process. Detection and elimination of these noise points directly affect the subsequent processing efficiency of the LiDAR point clouds. In this paper, a noise detection method from airborne LiDAR data based on spatial hierarchical directional relationship and region growing algorithm is proposed. First, the original airborne LiDAR points are divided into regular 3D grids, and the maximum point density unit is searched adaptively to select the initial surface seed points for region growing algorithm. Then, the spherical neighborhood is constructed with the initial seed point as the center, and fourteen main growth directions are generated based on the 3D space topology. Second, candidate seed points in each main direction are determined by the distance threshold. Finally, all LiDAR points are iteratively executed using candidate seed points as new region growing seed points. This paper selects two mountain terrain scenes with different cloud contents as the study area, and the precision, recall rates and F1-score of the proposed method reach 99.8%, 100% and 99.3%, respectively. This method can detect point-cloud clusters and isolated points, thus simplifying the LiDAR point clouds, providing basic support for the subsequent accurate data processing and analysis.

This paper presents a novel method for the detection of binary- and random-valued impulsive noise in contaminated images. The noise detector has been developed to classify the certain intensity image pixels as corrupted or uncorrupted based on their relative position. To perform such classification, we regard noise as random points and propose to use the properties of random point patterns that are formed based on a noisy image. Pixels of each image intensity are checked by what type of point pattern they form based on the Clark–Evans test. In the case of random or regular type, pixels of this intensity are classified as noise. For intensity pixels designated as a cluster, the search of isolated points is performed. In case of a homogeneity test fail, they are also classified as noise. The proposed technique can be applied to color images. Extensive simulation experiments indicate that the proposed detection approach outperforms many well-known means. [ABSTRACT FROM AUTHOR]

Label noise detection has been widely studied in Machine Learning because of its importance in improving training data quality. Satisfactory noise detection has been achieved by adopting ensembles of classifiers. In this approach, an instance is assigned as mislabeled if a high proportion of members in the pool misclassifies it. Previous authors have empirically evaluated this approach; nevertheless, they mostly assumed that label noise is generated completely at random in a dataset. This is a strong assumption since other types of label noise are feasible in practice and can influence noise detection results. This work investigates the performance of ensemble noise detection under two different noise models: the Noisy at Random (NAR), in which the probability of label noise depends on the instance class, in comparison to the Noisy Completely at Random model, in which the probability of label noise is entirely independent. In this setting, we investigate the effect of class distribution on noise detection performance since it changes the total noise level observed in a dataset under the NAR assumption. Further, an evaluation of the ensemble vote threshold is conducted to contrast with the most common approaches in the literature. In many performed experiments, choosing a noise generation model over another can lead to different results when considering aspects such as class imbalance and noise level ratio among different classes. [ABSTRACT FROM AUTHOR]

After widely studying the methods in literatures for impulse noise removal, aiming at overcoming their deficiencies and further improving the denoising performance, we propose an adaptive equidistant median filter for image restoration in the presence of impulse noise. As an improved and effective alternative to the square neighborhood, the circular neighborhood is proposed for noise detection and removal processing. A noise detector based on adaptive local statistics is proposed, followed by a noise removal technique gaining support from adaptive equidistant median proposed subsequently. Furthermore, the noise removal processing is performed adaptively so as to be robust for various noise densities. Experimental results have shown that the proposed method has substantially improved the performance in noise detection and removal, and is superior than the state-of-the-art filters with excellent capability of noise removal and structural information preservation. [ABSTRACT FROM AUTHOR]

: Automatic electrocardiogram (ECG) signal analysis for heart disease detection has gained significant attention due to busy lifestyles. However, ECG signals are susceptible to noise, which adversely affects the performance of ECG signal analysers. Traditional blind filtering methods use predefined noise frequency and filter order, but they alter ECG biomarkers. Several Deep Learning-based ECG noise detection and classification methods exist, but no study compares recurrent neural network (RNN) and convolutional neural network (CNN) architectures and their complexity. This paper introduces a knowledge-based ECG filtering system using Deep Learning to classify ECG noise types and compare popular computer vision model architectures in a practical Internet of Medical Things (IoMT) framework. Experimental results demonstrate that the CNN-based ECG noise classifier outperforms the RNN-based model in terms of performance and training time. The study shows that AlexNet, visual geometry group (VGG), and residual network (ResNet) achieved over 70% accuracy, specificity, sensitivity, and F1 score across six datasets. VGG and ResNet performances were comparable, but VGG was more complex than ResNet, with only a 4.57% less F1 score. This paper introduces a Deep Learning (DL) based ECG noise classifier for a knowledge-driven ECG filtering system, offering selective filtering to reduce signal distortion. Evaluation of various CNN and RNN-based models reveals VGG and Resnet outperform. Further, the VGG model is superior in terms of performance. But Resnet performs comparably to VGG with less model complexity. • Propose a knowledge-based filtering system to improve quality of ECG biomarkers. • Improve biomarkers used for cardiovascular detection in various environments. • Assess model's adaptability across diverse datasets to test model generalisation. [ABSTRACT FROM AUTHOR]

Background radiation in the LiDAR detection field of view is complex and variable, and the background noise generated can easily cause false alarms in the receiver, which affects the effective detection of the system. Through the analysis of the influence of background radiation noise of LiDAR on the detection performance, an adaptive suppression method of LiDAR background noise is proposed. This method realizes the rapid suppression of background noise in the instantaneous field of view through an adaptive threshold adjustment of current steering architecture with a back-end digital-to-analog converter (DAC) correction based on the principle of constant false alarm rate (CFAR) control. Aiming at the problem of accurate noise detection and quantification in a very short time, a dynamic comparator is used to replace the traditional continuous comparator. While detecting the number of noise pulses, the measurement of the pulse duration of noise is realized, which improves the accuracy of short-time noise detection. In order to verify the actual effect of the adaptive method, experiments were carried out based on the team’s self-developed LiDAR. The experimental results show that the measured noise ratio of the adaptive mode by using this method is the lowest. Even at 12 a.m., the noise ratio of the point cloud obtained by the adaptive mode is 0.012%, compared with 0.08% obtained by the traditional mode, which proves that this method has a good ability to suppress background noise. The proportion of noise reduction of the adaptive mode is more than 80% compared with the traditional mode. It achieves noise suppression through hardware at each detection, and each adjustment can be completed within a single period of pulse detection. Therefore, it has great advantages in real-time detection compared with the back-end software noise reduction processing method, and it is suitable for the application of LiDAR in the complex background environment.

The present study undertakes the development and implementation of an algorithm for an automatic separation of acoustic events related to aircraft flights. The data are provided by noise monitoring stations operating as part of multi-point continuous noise measurement systems around small and medium-sized airports and helicopter landing sites in Poland. The article presents initial assumptions of the developed method based on the conclusions of the research. For this purpose, two different methods of airborne noise signal detection will be discussed. The first method is based on the analysis of the value of the changing rate of the signal being the difference between the value of the analysed sample and the value of the h-th previous sample of the recorded sound level time history. The second method uses a convolutional neural network operating on values recorded in 1/3-octave bands. The objective of the study is to examine the effectiveness and limitations of the selected methods on the collected representative input data. [ABSTRACT FROM AUTHOR]

Removing salt and pepper noise is an active research area in image processing. In this paper, a two-phase method is proposed for removing salt and pepper noise while preserving edges and fine details. In the first phase, noise candidate pixels are detected which are likely to be contaminated by noise. In the second phase, only noise candidate pixels are restored using adaptive median filter. In terms of noise detection, a two-stage method is utilized. At first, a thresholding is applied on the image to initial estimation of the noise candidate pixels. Since some pixels in the image may be similar to the salt and pepper noise, these pixels are mistakenly identified as noise. Hence, in the second step of the noise detection, the pixon-based segmentation is used to identify the salt and pepper noise pixels more accurately. Pixon is the neighboring pixels with similar gray levels. The proposed method was evaluated on several noisy images, and the results show the accuracy of the proposed method in salt and pepper noise removal and outperforms to several existing methods.

Knowledge graphs are widely used in a variety of knowledge-driven applications. Due to the inefficiency of manual construction of knowledge graphs, automatic construction mechanism has become the dominant method, which introduces noise. However, most knowledge representation learning approaches assume that there is no noise in the knowledge graph and hence ignore noise detection. In this paper, we propose a dissimilarity-support-aware knowledge representation learning framework, which accomplishes knowledge representation learning and noise detection simultaneously. Specifically, we introduce triple dissimilarity and triple support to construct the model energy function which is based on translation-based methods. The triple dissimilarity measures the matching extent of entities and relations in triples and the triple support measures the credibility of the matching extent. In order to make triple dissimilarity and triple support estimation effective and comprehensive, we synthesize structural information and auxiliary information (entity hierarchical type and relation path information) in triple dissimilarity and triple support. We conduct experiments on three datasets for the knowledge graph noise detection task and the knowledge graph completion task. The experimental results show that our model achieves significant and consistent improvements compared to all baseline methods. [ABSTRACT FROM AUTHOR]

The automatic construction of knowledge graphs (KGs) from multiple data sources has received increasing attention. The automatic construction process inevitably brings considerable noise, especially in the construction of KGs from unstructured text. The noise in a KG can be divided into two categories: factual noise and low-quality noise. Factual noise refers to plausible triples that meet the requirements of ontology constraints. For example, the plausible triple satisfies the constraints that the head entity "New_York" is a city and the tail entity "America" belongs to a country. Low-quality noise denotes the obvious errors commonly created in information extraction processes. This study focuses on entity type errors. Most existing approaches concentrate on refining an existing KG, assuming that the type information of most entities or the ontology information in the KG is known in advance. However, such methods may not be suitable at the start of a KG's construction. Therefore, the authors propose an effective framework to eliminate entity type errors. The experimental results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

A noise detection system (INDS) composed of an acoustic triboelectric nano-generator (TENG) and an electrical bilayer synaptic transistor (EDLT) is proposed. As a self-powered sound sensor, TENG converts the sound signal directly into a voltage signal output. EDLT is used as a neuromorphic device to simulate synaptic behavior in organisms and has the ability to store and process signals simultaneously. In this letter, a kind of intelligent, simple structure and humanized noise detection system is developed. [ABSTRACT FROM AUTHOR]

The snapping shrimp sound is known to be a major biological noise source of ocean soundscapes in coastal shallow waters of low and mid-latitudes where sunlight reaches. Several studies have been conducted to understand the activity of snapping shrimp through comparison with surrounding environmental factors. In this paper, we report the analysis of the sound produced by snapping shrimp inhabiting an area where sunlight rarely reaches. The acoustic measurements were taken in May 2015 using two 16-channel vertical line arrays (VLAs) moored at a depth of about 100 m, located ∼100 km southwest of Jeju Island, South Korea, as part of the Shallow-water Acoustic Variability Experiment (SAVEX-15). During the experiment, the underwater soundscape was dominated by the broadband impulsive snapping shrimp noise, which is notable considering that snapping shrimp are commonly observed at very shallow depths of tens of meters or less where sunlight can easily reach. To extract snapping events in the ambient noise data, an envelope correlation combined with an amplitude threshold detection algorithm were applied, and then the sea surface-bounced path was filtered out using a kurtosis value of the waveform to avoid double-counting in snap rate estimates. The analysis of the ambient noise data received for 5 consecutive days indicated that the snap rate fluctuated with a strong one-quarter-diurnal variation between 200 and 1,200 snaps per minute, which is distinguished from the periodicity of the snap rate reported in the euphotic zone. The temporal variation in the snap rate is compared with several environmental factors such as water temperature, tidal level, and current speed. It is found that the snap rate has a significant correlation with the current speed, suggesting that snapping shrimp living in the area with little sunlight might change their snapping behavior in response to changes in current speed.

Abnormal noise originating from within faulty products often irritates customers, which may lead to expensive warranty claims. Therefore, it is important to identify these faulty products proactively in the manufacturing process. However, noise detection in a loud shop-floor is not straightforward because inspection in an anechoic chamber is very costly, and some prerequisites for conventional noise reduction and source separation methods, such as stationary and independent signals and prior knowledge about the signal of interest, are sometimes not feasible in practice. Therefore, we developed an in-process noise inspection system that supports dual-channel acoustic data collection during the inspection process. By using two different groups of acoustic signals, abnormal sound separation and noise detection are made possible through three main steps: in-process background noise training, abnormal noise separation, and significance evaluation. The efficiency of the proposed procedure is demonstrated with two case studies: car door trim panels and dual-channel sound generator and collector. [ABSTRACT FROM AUTHOR]

Salt-and-pepper noise suppression for vector-valued images usually employs vector median filtering, total variation L1 model, diffusion methods and variants. These approaches, however, often introduce excessive smoothing and can result in extensive visual feature blurring and are suitable only for images with low intensity noise. In this paper, a new method, as an important preprocessing step in cyber-physical systems, is presented to suppress salt-and-pepper noise that can overcomes this limitation. This method first detects the corrupted pixels and then restores them using channel-wise anisotropic diffusion. The means is twofold. On the one hand, the marginal approach is used to perform noise suppression separately in each channel because the contaminative pixel components are of independent distribution. On the other hand, a decision-based anisotropic diffusion method is applied to each channel to restores them. The anisotropic diffusion is an energy-dissipating process with time, and dependent on geometric analysis of shape of the energy surface. Simulation results indicate that the proposed method for impulsive noise removal achieves the state-of-the-arts results. [ABSTRACT FROM AUTHOR]

To tackle the difficulties in the detection and removal of impulse noise faced by the existing filters, and to further improve the denoising performance, we propose an adaptive sequentially weighted median filter for image corrupted by impulse noise. In the proposed method, a noise detector employing the 3σ principle of normal distribution and the local intensity statistics, is proposed; and a sequentially weighted median filter with a neighborhood of adaptive size, is proposed for noise removal, in which the weighted operator is derived in reference to the spatial distances from central noisy pixel, i.e., the weighting coefficients are sequentially inversely proportional to the spatial distances. The experimental results confirm that the proposed method outperforms the existing filters, excelling in the capability of noise removal, structure and edge information preservation.

Distant supervised relation extraction (DSRE) is widely used to extract novel relational facts from plain text, so as to improve the knowledge graph. However, distant supervision inevitably suffers from the noisy labeling problem that will severely damage the performance of relation extraction. Currently, most DSRE methods are mainly focused on reducing the weights of noisy sentences, ignoring the bag-level noise where all sentences in a bag are wrongly labeled. In this paper, we present a novel noise detection-based relation extraction approach (NDRE) to automatically detect noisy labels with entity information and dynamically correct them, which can alleviate both instance-level and bag-level noisy problems. By this means, we can extend the dataset from the Web tables without introducing more noise. In this approach, to embed the semantics of sentences from corpus and web tables, we firstly propose a powerful sentence coder that employs an internal multi-head self-attention mechanism between the piecewise max-pooling convolutional neural network. Second, we adopt a noise detection strategy, which is expected to dynamically detect and correct the original noisy label according to the similarity between sentence representation and entity-aware embeddings. Then, we aggregate the information from corpus and web tables to make the final relation prediction. Experimental results on a public benchmark dataset demonstrate that our proposed approach achieves significant improvements over the state-of-the-art baselines and can effectively reduce the noisy labeling problem. [ABSTRACT FROM AUTHOR]