The real systems are often complex, nonlinear, and noisy in various areas including mathematics, natural science, and social science. We present the symplectic entropy (SymEn) measure as well as an analysis method based on SymEn to estimate the nonlinearity of the complex system by analyzing the given time series. The SymEn estimation is a kind of entropy based on symplectic principal component analysis (SPCA) which represent organized but unpredictable behaviors of systems. The key to SPCA is to preserve the global submanifold geometrical properties of the systems through symplectic transform in the phase space, which is a kind of the measure-preserving transforms. The capability of preserving the global geometrical characteristics makes the SymEn a test statistic to detect the nonlinear characteristics in several typical chaotic time series and the stochastic characteristic in the Gaussian white noise. The results are in agreement with findings in the approximate entropy (ApEn), the sample entropy (SampEn) and the fuzzy entropy (FuzzyEn). Moreover, the SymEn method is also used to analyze the nonlinearities of the real signals (including the EEG signals for ASD and healthy subjects, and the sound and vibration signals for the mechanical systems). The results indicate that the SymEn estimation can be taken as a measure for describing the nonlinear characteristics in the data collected from the natural complex systems.

Multimodal knowledge graph completion necessitates the integration of information from multiple modalities (such as images and text) into the structural representation of entities to improve link prediction. However, most existing studies have overlooked the interaction between different modalities. To address this issue, this paper proposed a Transformer-based knowledge graph link prediction model (MM-Transformer) that fuses multimodal features. Different modal encoders are employed to extract structural, visual and textual features, and hybrid key-value calculations are performed on features from different modalities based on the Transformer architecture. The similarities of textual tags to structural tags and visual tags are calculated and aggregated respectively, and multimodal entity representations are modeled and optimized to reduce the heterogeneity of the representations. Experimental results demonstrate that, compared to the current multimodal state-of-the-art methods, the proposed method achieves significant performance improvements in knowledge graph link prediction tasks. This proves that the proposed method effectively addresses the problem of multimodal feature fusion in knowledge graph link prediction tasks.

Color image binarization plays a pivotal role in image preprocessing work, significantly impacting subsequent tasks, particularly in text recognition. This paper concentrates on Document Image Binarization (DIB), aiming to separate a image into foreground (text) and background (non-text content). Through a thorough analysis of conventional and deep learning-based approaches, we conclude that prevailing DIB methods leverage deep learning technology. Furthermore, we explore the receptive fields pre- and post-network training to underscore the Transformer model's advantages. Subsequently, we introduce a lightweight model based on the U-Net structure, enhanced with the Mobile ViT module to better capture global information features in document images. Given its adeptness at learning both local and global features, our proposed model exhibits superior performance on two standard datasets (DIBCO2012 and DIBCO2017) compared to state-of-the-art methods. Notably, our proposed DIB method presents a straightforward end-to-end model devoid of additional image preprocessing or post-processing. Moreover, its parameter count is less than a quarter of the HIP'23 model, which achives best results on three datasets(DIBCO2012, DIBCO2017 and DIBCO2018). Finally, two sets of ablation experiments were conducted to verify the effectiveness of the proposed binarization model.

One of the most crucial elements in deeply understanding humans on a psychological level is manifested through facial expressions. The analysis of a human behavior can be informed by their facial expressions, making it essential to employ indicators such as expression (Expr), valence-arousal (VA), and action units (AU). In this paper, we introduce the method proposed in the Challenge of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW) at CVPR 2024. Our proposed method utilizes the multi-modal Aff-wild2 dataset, which is splitted into spatial and audio modalities. For the spatial data, we extract features using a SimMiM model that was pre-trained on a diverse set of facial expression data. For the audio data, we extract features using a WAV2VEC model. To fusion the extracted spatial and audio features, we employed the cascaded cross-attention mechanism of a transformer.

Systematic reviews represent a powerful instrument to summarize the existing evidence in medical literature. However, articles for a systematic review are hard to identify, and mostly require a structured search of the literature through a number of databases, using keyword-based search strategies, followed by the painstaking manual selection of pieces of evidence that are pertinent to the query. A.I. algorithms may offer solutions to reduce the workload on investigators. We applied BERTopic, a newer and much-recognized transformer-based topic-modeling algorithm, to two datasets of 6137 and 5309 articles of newly published systematic reviews in the area of peri-implantitis and bone regeneration in implant dentistry. In the two datasets, BERTopic identified 14 and 22 clusters, respectively, and it automatically created labels describing the nature of the topics for each individual cluster based on semantic interpretation of their titles. Most themes regarded the query theme, but in both conditions, BERTopic also uncovered articles related to off-themes, which composed around 30% of the dataset—with sensitivity up to 0.79 and specificities of at least 0.99. Our results suggest that adding a topic-modeling step to the screening process could potentially save working hours for researchers involved in systematic reviews of the literature.

The abilities of quantitative description of noise are restricted due to its origin and only the statistical and spectral analysis methods can be applied while an exact time evolution cannot be defined or predicted. It emphasizes the challenges faced in many applications including communication systems where noise can play, on one hand, a vital role impacting signal-to-noise ratio but possessing, on the other hand, unique properties such as infinite entropy (infinite information capacity), exponentially decaying correlation function and so on. Despite the deterministic nature of chaotic systems, the predictability of chaotic signals is limited for a short time window putting them close to random noise. In this article, we propose and experimentally verify an approach to achieve Gaussian-distributed chaotic signals by processing the outputs of chaotic systems. The mathematical criteria, on which the main idea of the study is based on, is the Central Limit Theorem which states that the sum of a large number of independent random variables with similar variances approaches a Gaussian distribution. The study involves more than 40 mostly three-dimensional continuous-time chaotic systems (Chua’s, Lorenz’s, Sprott’s, memristor-based, etc.) whose output signals are analyzed according to criteria that encompass the probability density functions of a chaotic signal itself and its envelope and phase, statistical and entropy-based metrics such as skewness, kurtosis, and entropy power. We found that two chaotic signals of Chua’s and Lorenz’s systems exhibited superior performance across the chosen metrics. Furthermore, our focus extended to determining the minimum number of independent chaotic signals necessary to yield a Gaussian-distributed combined signal. The analytic and experimental results indicate that the sum of at least three non-Gaussian chaotic signals closely approximates Gaussian distribution. It allows generation of reproducible Gaussian-distributed deterministic chaos by modeling simple chaotic systems.

Ocean exploration is crucial for utilizing its extensive resources. Images captured by underwater robots suffer from issues such as color distortion and reduced contrast. To address the issue, we propose an innovative enhancement algorithm that integrates Transformer and Convolutional Neural Network (CNN) in a parallel fusion manner. Firstly, a novel transformer model is intro-duced to capture local features, employing peak-signal-to-noise ratio (PSNR) attention and linear operations. Subsequently, to extract global features, both temporal and frequency domain features are incorporated to construct convolutional neural network. Finally, the Fourier’s high and low-frequency information of the original image are utilized to fuse different features. To demon-strate the algorithm's effectiveness, underwater images with various levels of color distortion are selected for both qualitative and quantitative analyses. The experimental results demonstrate that our approach surpasses other mainstream methods, achieving superior PSNR and structural sim-ilarity index measure (SSIM) metrics and leading to a detection performance improvement of over ten percent.

Non-toroidal shape primary pass through protection current transformers (CTs) are used to measure high currents. Their design provides them with a big airgap that allow passing several cables per phase though them, which is the main advantage versus toroidal types, as the number of CTs required to measure the whole phase current is drastically reduced. The cables pass through the transformer window can be in several positions. As the isolines of the magnetic field generated by the primary currents are centered in the cables, if these cables are not centered in the transformer window, the magnetic field will be non-uniform along the transformer core. Consequently, local saturations can appear if the cables are not properly disposed causing the malfunction of the CT. In this paper, the performance of a non-toroidal shape protection CT is studied. The research is focused on the cable position influence in possible partial saturations of the CT when it is operating near to its accuracy limit. Depending on the cable position, the ratio of the primary and secondary currents can depart from assigned ratio. The validation of this phenomenon has been carried out via Finite Element Analysis (FEA) showing that partial transformer core saturations appears in areas of the magnetic core close to the cable. Applying FEA, also the admissible accuracy region for cable positioning inside the CT is delimited. Finally, the simulation results are ratified with experimental tests performed in non-toroidal protection CTs varying the primary cables’ positions, which are subjected to currents up to 5 kA, achieving satisfactory results. From this analysis, installation recommendations are given.

Few-shot object detection (FSOD) aims to address the challenge of requiring a substantial amount of annotations for training in conventional object detection, which is very labor-intensive. However, existing few-shot methods achieve high precision with the sacrifice of time-consuming for exhaustive fine-tuning, or take poor performance in novel-class adaptation. We presume the major reason is that the valuable correlation feature among different categories is insufficiently exploited, hindering the generalization of knowledge from base to novel categories for object detection. In this paper, we propose Few-Shot object detection via Correlation-RPN and Transformer Encoder-Decoder (CRTED), a novel training network to learn object-relevant features of inter-class correlation and intra-class compactness while suppressing object-agnostic features in the background with limited annotated samples. And we also introduce a 4-way tuple-contrast training strategy to positively activate the training progress of our object detector. Experiments over two few-shot benchmarks (Pascal VOC, MS-COCO) demonstrate that, our proposed CRTED without further fine-tuning can achieve comparable performance with current state-of-the-art fine-tuned works. The codes and pre-trained models will be released.

The objective of person re-identification (ReID) tasks is to match a specific individual across different times, locations, or camera viewpoints. The prevalent issue of occlusion in real-world scenarios affects image information, rendering the affected features unreliable. The difficulty and core challenge lie in how to effectively discern and extract visual features from human images under various complex conditions, including cluttered backgrounds, diverse postures, and the presence of occlusions. Some works have employed pose estimation or human keypoint detection to construct graph-structured information to counteract the effects of occlusions. However, this approach introduces new noise due to issues such as the invisibility of keypoints. Our proposed module, in contrast, does not require the use of additional feature extractors. Our module employs multi-scale graph attention for the reweighting of feature importance. This allows features to concentrate on areas genuinely pertinent to the re-identification task, thereby enhancing the model's robustness against occlusions. To address these problems, a model that employs multi-scale graph attention to re-weight the importance of features is proposed in this study, significantly enhancing the model’s robustness against occlusions. Our experimental results demonstrate that, compared to baseline models, the method proposed herein achieves a notable improvement in mAP on occluded data sets, with increases of 0.5%, 31.5%, and 12.3% in mAP scores.

Despite significant advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), detecting and mitigating bias remains a critical challenge, particularly within social media platforms like X (formerly Twitter) and in addressing cyberbullying present on them. This research investigates the effectiveness of leading LLMs in generating synthetic biased and cyberbullying data and evaluates the proficiency of Transformer AI models in detecting bias and cyberbullying within both authentic and synthetic contexts. The study involves semantic analysis and feature engineering on a dataset of over 48,000 sentences related to cyberbullying collected from Twitter (before it became X). Leveraging state-of-the-art LLMs such as ChatGPT-4o, Pi AI, Claude 3 Opus, and Gemini-1.5, synthetic biased, cyberbullying, and neutral data were generated to deepen the understanding of bias in human-generated data. AI models including DeBERTa, Longformer, BigBird, HateBERT, MobileBERT, DistilBERT, BERT, RoBERTa, ELECTRA, and XLNet were initially trained to classify Twitter cyberbullying data and subsequently fine-tuned, optimized, and quantized for multilabel classification (detecting both biases and cyberbullying). The study's outcomes include a prototype of a hybrid application that combines a Bias Data Detector and a Bias Data Generator, validated through extensive testing.

In the area of dental healthcare services, where patients and professionals deal with multiple auditory stimuli, this cross-sectional study reports on the intricate dynamics of sound preferences, noise obstacles, and the profound impact of music on anxiety reduction within dental office set-tings. The sample comprises of 134 dental patients, primarily females (56.7%), with varying age groups, education levels, and therapy durations in the university clinics of the department of Dentistry, National and Kapodistrian University of Athens and four private dental offices at the metropolitan area of Athens, Greece. Notably, 92.5% of the participants report no hearing loss, and 56.7% exhibit some level of noise sensitivity. The study reveals a moderate to good perceived health status (M=3.84, SD=0.95) among participants, with low perceived noise disturbance in university dental clinics. Preferences for instrumental music, foreign pop, and classical music are prominent during waiting times. Potential irritations include impersonal treatment (44%) and staff behavior (41.8%). Music player usage within the settings of the dental clinic involves radios (49.3%) and headphones (41.0%). Correlations and predictors indicate associations between health status, music preferences, and noise disturbances. More specifically, visiting the university dental clinics (β = .300, p = .005) as well as younger age (β = .300, p = .034) were significant predictors of better perceived health status. Clearer perception of external sounds while using the music player (β = .190, p = .039) was a significant predictor of better perceived health status, while poorer health was predicted by the preference of Greek folk songs (β = -.200, p = .030). Also, the use of smartphones for playing music was related to poorer health (β = -.370, p < .001). Following, younger age (β = -.270, p = .015), lower education (β = -.210, p = .035), higher noise sensitivity (β = .190, p = .027), as well as feelings of anxiety and nervousness due to ambient noise from people and machines (β = .510, p = .027) were significant predictors of noise disturbance from machines. Also, visiting private clinics (β = .240, p = .018), preferences of specific playlist (β = .310, p = .012), no music (β = .280, p = .016) and use of smartphones to play music (β = .230, p = .029) were significant predictors of noise disturbance from patients or staff. Finally, the preference of listening to a specific playlist was related to better health status (r = .190, p < .05). Findings aim to optimize eco-soundscapes in dental offices, con-tributing to enhanced patient well-being. The research underscores the potential of music inter-ventions to alleviate dental anxiety and improve the overall dental experience and quality care.

Emphasizing the importance of acoustic attenuation in maintaining compliance with stringent noise regulations and enhancing workplace safety, the analysis covers the theoretical and practical aspects of sound attenuation in a turboengine testing stand. This paper presents a preliminary analysis and also an evaluation of a procedure for projecting a noise attenuator for industrial application and especially for turboengine test stands. While primarily focusing on the static acoustic behavior of the attenuator, considerations were also made regarding flow dynamics, Mach number-dependent attenuation, pressure drop, and self-generated noise aspects to provide a comprehensive perspective in selecting the optimal design configuration. The study investigates different calculation methods for assessment of the noise reduction for linear and staggered baffles, applied on a scaled reduced model of attenuator. Thus, the critical parameters and projecting requirements necessary for effective noise reduction in high-performance turboengine testing environments will be evaluated in a down-scaled model. Key factors examined include the selection of design parameters and configurations from various options. Advanced computational methods, like analytic and finite element analysis (FEM) are utilized to predict the acoustic performance and identify potential design optimizations. Experimental validation is performed to corroborate the simulation results, ensuring the reliability and efficiency of the attenuator. The findings indicate that a well-designed sound attenuator module can significantly reduce noise levels without compromising the operational performance of the turboengine inside a test cell.

In this paper, the mechanism of combined process of ion beam sputtering (IBS) and HF acid etching on the chemical structure defects of fused silica and its laser damage resistance perfor-mance were investigated. During the removal process of surface material, the sputtering effect causes lattice atoms to detach from their original positions, forming a large number of unsaturated structures on silica surface, which improves the chemical activity of Si and O atoms, accelerates the chemical reaction process between surface atoms and water molecules, increases the content of hydroxyl (OH-) groups in the shallow layer, and enhances the photothermal weak absorption intensity. However, the presence of OH- groups reduces the bonding strength of Si-O, destroys the spatial network structure of silica bulk, and reduces the mechanical strength of silica surface, resulting in a decrease in its laser damage resistance performance. The paper reveals for the first time the mechanism of IBS to change the structure characteristics of silica material, accelerate the surface hydroxylation process, and thereby reduces the laser damage resistance performance. This work provides technical guidance for effectively suppressing chemical structure defects on silica surface and improving laser damage resistance performance of optical components under high-flux laser irradiation.

This study measures the noise levels in a baseball stadium and analyzes baseball fans’ attitude of effect of recreational noise exposure on their hearing. In the baseball stadium, noise levels were measured in four seating sections using a sound level meter during the games. The LAeq average of the 16 measures produced 91.7 dBA, showing a significantly high noise level in the red and navy sections. As a function of frequency by LZeq analysis, the noise levels were significantly higher in low frequencies than other frequencies. For the survey sample, 688 randomly selected participants completed a 16-question survey on their noise exposure during the game and on the potential risk of hearing loss. Despite the very high noise levels, 70% of the respondents preferred sitting in either the red or the navy section to be closer to the cheerleaders and to obtain a good view. Most respondents reported that they did not consider wearing earplugs, and one-third experienced hearing muffled speech after the game. We conclude that the noise levels in baseball stadiums are high enough to cause hearing damage and/or tinnitus later, but expect these results to improve public education regarding safe noise exposure during popular sports activities.

A Partial discharge (PD) occurrence in high-voltage (HV) and medium-voltage (MV) power assets is a warning sign of insulation system degradation or defective manufacturing/assembly, that may cause catastrophic damage and eventually lead to the breakdown of the power equipment. Ultra-high frequency (UHF) PD measurement technology has extensively been used to monitor the insulation health of the HV or MV equipment due to its high immunity against ambient noise and conducted disturbances. This paper presents experimental validation of a new design of a UHF planar rectangular microstrip antenna that can be used for PD monitoring of HV and/or MV power equipment, such as power transformers. The designed planar rectangular microstrip antenna has a compact size of 80mmx70mmx1.6mm. Laboratory experiments were performed to validate the antenna sensitivity to PD activity caused by insulation defects created inside an oil-filled transformer tank model. PD measurement results confirm that the proposed rectangular microstrip antenna has high sensitivity and high signal-to-noise ratio (SNR), thanks to its capability to suppress external noise disturbances, especially during online PD monitoring. Thus, the proposed UHF antenna seems to be a promising and alternative PD sensor that can be employed in UHF PD monitoring systems of HV or MV power equipment.

High level of noise is a disturbance to the human environment. Noise in industries is also an occupational hazard because of its attendant effects on workers’ health. Noise presents health and social problems in industrial operations, and the source is related to the machineries used in the industries. One of the unique features of the noise associated with wood machinery is the level of exposure and duration. Equipment used in a factory can be extremely loud. They can produce noise at decibels high enough to cause environmental health and safety concerns. The mechanically driven transport and handling equipment, cutting, milling, shaping and dust extractor installations in the wood industry generate noise. The sources of noise pollution have increased due to non-compliance with basic safety practices. The increased use of locally fabricated machine in the industry has increased the level of noise and vibration. The effects of industrial noise pollution as discussed include: increase in blood pressure; increased stress; fatigue; vertigo; headaches; sleep disturbance; annoyance; speech problems; dysgraphia, which means reading/learning impairment; aggression; anxiety and withdrawal. As presented in this paper, noise control techniques include; sound insulation, sound absorption, vibration damping and Vibration isolation.

Background/Objectives: It is known that balance disorders involve occupational hazards. However, the inverse relationship (between certain occupations and an increased incidence of vertigo or dizziness) has been scarcely studied. The objective of this work was to analyze the occupation of a group of patients with vertigo, compared to economically active general population, and to evaluate the prevalence of occupational noise and/or vibration-exposure in both groups. Methods: A cross-sectional, observational, case-control study was carried out including 461 patients (220: Meniere’s disease; 73: vestibular migraine; 28: vestibular neuritis; 140: BPPV) (310 women and 151 men). These patients were compared to a control group from the general population, obtained from 6th EWCS-Spain (2015). Possible differences regarding sex, age, occupation, exposure to noise, and exposure to mechanical vibrations were analyzed. Results: Differences in distribution of occupations between patients with vertigo and general population were observed (Chi-square, p=6.142 e-30). Patients with vertigo were significantly more exposed to noise (p=8.19 e-12; OR=2,127, CI95% (1.720;2.630)) and vibrations (p=1.11 e-12; OR=2.288, CI95% (1.835;2.853)) than the control group. These differences were observed both between men and women. Conclusions: A relationship between occupational exposure to noise and/or vibrations and the presence of vertigo was observed. Protective and preventive measures could help prevent the occurrence of some diseases involving vertigo.

The present paper is aimed at presenting an updated review of prediction methods for the aerodynamic noise of ducted rotor-stator stages. Indeed, ducted rotating-blade technologies are in continuous evolution and increasingly used, for both aeronautical propulsion units, power generation and air conditioning systems. Different needs are faced, from the early design stage to the final definition of a machine. Fast-running, approximate analytical approaches and high-fidelity numerical simulations are considered as the best suited tools for each, respectively. Recent advances are discussed, with emphasis on their pros and cons.

This study introduces a sophisticated neural network structure for segmenting breast tumors. It achieves this by combining a pretrained Vision Transformer (ViT) model with a U-Net framework. The U-Net architecture, commonly employed for biomedical image segmentation, is further enhanced with Depthwise Separable Convolutional Blocks to decrease computational complexity and parameter count, resulting in better efficiency and less overfitting. The Vision Transformer, renowned for its robust feature extraction capabilities utilizing self-attention processes, efficiently captures the overall context within images, surpassing the performance of conventional convolutional networks. By using a pretrained ViT as the encoder in our U-Net model, we take advantage of its extensive feature representations acquired from extensive datasets, resulting in a major enhancement in the model’s ability to generalize and train efficiently. The suggested model has exceptional performance in segmenting breast cancers from medical images, highlighting the advantages of integrating transformer-based encoders with efficient U-Net topologies. This hybrid methodology emphasizes the capabilities of transformers in the field of medical image processing and establishes a new standard for accuracy and efficiency in activities related to tumor segmentation.

In order to solve the problem of feature extraction of underwater acoustic signals in complex ocean environment, a new method for feature extraction from ship radiated noise is presented based on empirical mode decomposition theory and permutation entropy. It analyzes the separability for permutation entropies of the intrinsic mode functions of three types of ship radiated noise signals, and discusses the permutation entropy of the intrinsic mode function with the highest energy. In this study, ship radiated noise signals measured from three types of ships are decomposed into a set of intrinsic mode functions with empirical mode decomposition method. Then, the permutation entropies of all intrinsic mode functions are calculated with appropriate parameters. The permutation entropies are obviously different in the intrinsic mode functions with the highest energy, thus, the permutation entropy of the intrinsic mode function with the highest energy is regarded as a new characteristic parameter to extract the feature of ship radiated noise. After that, the characteristic parameters, namely, the energy difference between high and low frequency, permutation entropy, and multi-scale permutation entropy, are compared with the permutation entropy of the intrinsic mode function with the highest energy. It is discovered that the four characteristic parameters are at the same level for similar ships, however, there are differences in the parameters for different types of ships. The results demonstrate that the permutation entropy of the intrinsic mode function with the highest energy is better in separability as the characteristic parameter than the other three parameters by comparing their fluctuation ranges and the average values of the four characteristic parameters. Hence, the feature of ship radiated noise can be extracted efficiently with the method.

The uncertainty in the secondary path of an Active Noise Control (ANC) headphone affects the waterbed effect and stability of the feedback system. This study focuses on the uncertainty of the secondary path when real users wear headphones, and proposes a new uncertainty constraint based on the measured results of the secondary path transfer function under different wearing conditions of dummy head and limited subjects. This constraint and a cascaded second-order infinite impulse response filter with fixed coefficients are used to formulate a control strategic function, which is optimized by the Improved Grey Wolf Optimizer (IGWO) algorithm to obtain the optimal controller with better noise reduction performance. The proposed method and simulation model are validated based on the experimental test results. The results demonstrate that the safety factor and waterbed suppressing factor contained in the proposed uncertainty constraint ensures more stable noise reduction and effective suppression of the waterbed effect for new subjects without a priori data.

The architectural configuration of the space plays a crucial role in the acoustics of Neonatal Intensive Care Units (NICUs). The design of the environment, the materials used in construction, and the organisation of noise sources within the room significantly influence the noise levels present in these critical areas. For this research, noise levels found in two hospitals, with different architectural configurations and sizes but similar construction materials, have been analyzed. Data were recorded at 1-second intervals over a period of more than 24 hours. The data collected in these hospitals confirm the magnitude of the noise problem in NICUs, highlighting the urgent need to address it effectively to ensure an appropriate and safe environment for the recovery of neonates. Good architectural planning can help mitigate noise, while poor configuration can exacerbate acoustic problems, negatively affecting both patients and healthcare staff. It is crucial to involve architects, acoustic engineers, and healthcare staff in the design and renovation of NICUs to create spaces that not only meet medical needs but also consider the auditory well-being of neonates.

Neural decoding from spiking activity is an essential tool for understanding the information encoded in population neurons, especially in applications like brain-computer interface (BCI). Various quantitative methods have been proposed and have shown superiorities under different scenarios respectively. From the machine learning perspective, the decoding task is to map the high-dimensional spatial &amp; temporal neuronal activity to the low-dimensional physical quantities (e.g., velocity, position). Because of the complex interactions and the abundant dynamics among neural circuits, good decoding algorithms usually have the capability of capturing flexible spatiotemporal structures embedded in the input feature space. Recently, the Transformer-based models are widely used in processing natural languages and images due to its superior performances in handling long-range and global dependencies. Hence, in this work we examine the potential applications of Transformers in neural decoding and introduce two Transformer-based models. Besides adapting the Transformer to neuronal data, we also propose a data augmentation method for overcoming the data shortage issue. We test our models on three experimental datasets and their performances are comparable to the previous state-of-the-art (SOTA) RNN-based methods. In addition, Transformer-based models show increased decoding performances when the input sequences are longer, while LSTM-based models deteriorate quickly. Our research suggests that Transformer-based models are important additions to the existing neural decoding solutions, especially for large datasets with long temporal dependencies.

As split learning (SL) becomes popular for addressing data privacy and resource limitation issues in edge model training process, it is crucial to pre-validate whether the extensive use of wireless and computing resources in SL can achieve the expected training latency and convergence. While digital twin network (DTN) can potentially estimate network strategy performance in pre-validation environments, they are still in their infancy for SL tasks, facing challenges like unknown non-i.i.d. data distributions, inaccurate channel states, and misreport resource availability across devices. To address these challenges, this paper proposes a TransNeural algorithm for DTN pre-validation environment to estimate SL latency and convergence. First, the TransNeural algorithm integrates transformers to efficiently model data similarities between different devices, considering different data distributions and device participate sequence greatly influence SL training convergence. Second, it leverages neural network to automatically establish the complex relationships between SL latency and convergence with data distributions, wireless and computing resources, dataset sizes, and training iterations. Deviations in user reports are also accounted for in the estimation process. Simulations show that the TransNeural algorithm improves latency estimation accuracy by 13.44% and convergence estimation accuracy by 116.74% compared to traditional equation-based methods.

Understanding speech in noise is particularly difficult for individuals occupationally exposed to noise due to a to a mix between noise-induced auditory lesions and energetic masking of speech signal. For years, the monitoring of conventional audiometric thresholds has been the usual way to check and preserve the auditory function. But the highlighting of supra-threshold deficits, notably speech in noise understanding difficulties, has pointed out the need for new monitoring tools. The present study aims to identify the most important variables that predict speech in noise under-standing in order to suggest a new way of regular monitoring. Physiological (distortion products of otoacoustic emissions, electrocochleography) and behavioral (amplitude and frequency modula-tion detection thresholds, conventional and extended high frequency audiometric thresholds) variables were collected in a population of individuals presenting a relative homogeneous occu-pational noise exposure. Those variables were used as predictors in a statistical model (random forest) to predict scores of three different speech in noise tests and a self-report of speech in noise ability. The extended high frequency threshold appears to be the best predictor and therefore an interesting candidate for a new way of monitoring noise exposed professionals.

Intelligent fault diagnosis techniques have replaced the time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning model can improve the accuracy of intelligent fault diagnosis with the help of its multilayer nonlinear mapping ability. This paper has proposed a novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN). The proposed method uses raw vibration signals as input (data augmentation is used to generate more inputs), and uses the wide kernels in first convolutional layer for extracting feature and suppressing high frequency noise. Small convolutional kernels in the preceding layers are used for multilayer nonlinear mapping. AdaBN is implemented to improve the domain adaptation ability of the model. The proposed model addresses the problem that currently, the accuracy of CNN applied to fault diagnosis is not very high. WDCNN can not only achieve 100% classification accuracy on normal signals, but also outperform state of the art DNN model which is based on frequency features under different working load and noisy environment.

Highly-doped graphene samples show the conductance reduced and the shot-noise power enhanced compared to standard ballistic systems in two-dimensional electron gas. These features can be understood within a model assuming incoherent scattering of Dirac electrons between two interfaces separating the sample and the leads. Here we find, by adopting the above-mentioned model for the edge-free (Corbino) geometry and by means of the computer simulation of quantum transport, that another graphene-specific feature should be observable when the current flow through a doped disk is blocked by high magnetic field. In case the conductance drops to zero, the Fano factor approaches the value of $F\approx{}0.56$, with a very weak dependence on the disk radii ratio. The role of finite source-drain voltages and the system behavior upon tuning the electrostatic potential barrier from a rectangular to parabolic shape are also discussed.

In this paper, we introduce Syntax-Enhanced Transformer Model (SET), a groundbreaking approach in the realm of Transformer-based language modeling that seeks to redefine the boundaries of linguistic analysis and comprehension. SET innovatively combine (i) the well-established high-level performance, scalability, and adaptability of traditional Transformers with (ii) a sophisticated analysis of syntactic structures. This synergy is enabled by a novel attention mechanism tailored to parse syntactic nuances and a deterministic process adept at transforming linearized parse trees into meaningful linguistic representations. Our comprehensive experiments reveal that SET significantly advance the field by surpassing existing benchmarks in sentence-level language modeling perplexity. They exhibit exceptional proficiency in tasks that require an acute awareness of syntax, setting new standards for language models in understanding complex linguistic structures. Furthermore, SET demonstrate an enhanced capability to grasp nuanced linguistic patterns that have traditionally been challenging for standard Transformer models. However, our studies also uncover a unique aspect of SET: while they excel in sentence-level tasks, their representation of sentences as singular vectors—owing to the syntactic composition constraints intrinsic to their design—introduces certain limitations in document-level language modeling. This observation points to an intriguing area for future exploration; it suggests the potential need for an alternative or complementary memory mechanism within Transformer models, one that functions independently from, yet in harmony with, syntactic structures. Such a mechanism could be pivotal in enhancing the model's ability to comprehend and process long-form texts effectively. In conclusion, SET mark a significant stride in the journey towards more sophisticated, syntax-aware language models. They offer promising insights into the integration of deep linguistic knowledge with cutting-edge machine learning techniques, potentially opening doors to a new era of natural language understanding and processing.

The evolution of sentence representation learning, especially with parse tree encoders, has shown remarkable progress. Traditional approaches predominantly rely on recursive encoding of tree structures, which impedes parallel processing capabilities. Additionally, these methods often overlook the significance of dependency tree arc labels. To overcome these limitations, we introduce the Syntax-Enhanced Transformer (SET), incorporating a novel dual-attention mechanism that integrates relation-focused attention alongside traditional self-attention. This design effectively encodes both dependency and spatial positional relationships within sentence dependency trees. Our approach innovatively incorporates syntactic information into the Transformer framework without compromising its inherent parallelizability. The SET demonstrates superior or comparable performance to contemporary methods across various sentence representation tasks, significantly enhancing computational efficiency.

Recent advancements in neural language models, particularly attention-based architectures like the Transformer, have substantially surpassed traditional methods in various natural language processing tasks. These models adeptly generate nuanced token representations by considering contextual relations within a sequence. However, augmenting these models with explicit syntactic knowledge, such as part of speech tags, has been found to remarkably bolster their effectiveness, especially under constrained data scenarios. This study introduces the Linguistic Enhanced Transformer (LET), which integrates multiple syntactic features, showing a notable increase in translation accuracy, evidenced by an improvement of up to 1.99 BLEU points on subsets of the WMT '14 English-German dataset. Furthermore, this paper demonstrates that enriching BERT models with syntax-aware embeddings enhances their performance on several GLUE benchmark tasks.

In recent years, there has been an increasing interest in adopting novel sensing technologies for the continuous monitoring of structural systems. In this respect, Micro-Electro-Mechanical System (MEMS) sensors are widely used in several applications, including Structural Health Monitoring (SHM). Thanks to their significantly lower cost, ease of installation on the structure, and lower power consumption, they enable extensive, pervasive, and battery-less monitoring systems. This paper presents an innovative high-performance device for SHM applications, based on a low-noise triaxial MEMS accelerometer, providing a guideline and insightful results about the opportunities and capabilities of these devices. Sensor nodes have been designed, developed, and calibrated to meet structural vibration monitoring and modal identification requirements. These components include a protocol for reliable command dissemination through the network and data collection, and improvements to software components for data pipelining, jitter control, and high-frequency sampling. Devices were tested in the lab using shaker excitation. Results demonstrate that MEMS-based accelerometers are a feasible solution to replace expensive piezo-based accelerometers. Deploying MEMS is promising to minimize sensor node energy consumption. Time and frequency domain analysis show that MEMS can correctly detect modal frequencies, useful parameters for damage detection. The acquired data from the test bed were used to examine the functioning of the network, data transmission, and data quality. The proposed architecture has been successfully deployed in a real case study to monitor the structural health of the Marcus Aurelius Exedra Hall within the Capitoline Museum of Rome. The performance robustness was demonstrated and the results showed that the wired sensor network provides dense and accurate vibration data for structural continuous monitoring.

In this work, an analog front-end (AFE) circuit for Electrocardiogram (ECG) detection system has been designed, implemented, and investigated in an industry-standard Cadence simulation framework using advanced technology node of 45 nm. The AFE consists of an instrumentation amplifier, a Butterworth band-pass filter (with fifth-order low-pass and second-order high-pass sections), and a second-order notch filter- all are based on two-stage, Miller-compensated operational transconductance amplifiers (OTA). The OTAs have been designed employing the $g_m/I_D$ methodology. Both the pre-layout and post-layout simulation were carried out. The layout consumes an area of 0.0058 mm$^2$ without the resistors and capacitors. Analysis of various simulation results were carried out for the proposed AFE. The circuit demonstrates a post-layout bandwidth of 239 Hz with a variable gain between 44 to 58 dB, a notch depth of -56.4 dB at 50.1 Hz, a total harmonic distortion (THD) of -59.65 dB (less than 1\%), an input referred noise spectral density of $

Time series forecasting has been a challenging area in the field of Artificial Intel-ligence. Various approaches such as linear Neural Networks, Recurrent Linear Neural Networks, Convolutional Neural Networks and recently Transformers have been attempted for the time series forecasting domain. Although, Trans-former-based architectures have been outstanding in the Natural Language Pro-cessing domain, especially in autoregressive language modeling, the initial at-tempts to use transformers in the time series arena have met with mixed success. One of the recent papers demonstrated that modeling the multi-variate time se-ries problem as independent channels on a transformer architecture produced lower mean square and mean absolute errors on benchmarks, however, another recent paper claimed that a simple linear neural network out-performs previous approaches including transformer-based designs. We investigate this paradox in detail comparing the linear Neural Network and Transformer based designs, provide insights to why a certain approach may be better for a particular type of problem. We also improve upon the recently proposed simple linear Neural Network based architecture by using dual pipelines with batch normalization and reversible instance normalization. Our enhanced architecture outperforms all existing architectures for time series forecasting on majority of the popular benchmarks.

Multispectral image (MSI) and hyperspectral image (HSI) fusion (MHIF) aims to address the challenge of acquiring high-resolution (HR) HSI images. This field combines a low-resolution (LR) HSI with an HR-MSI to reconstruct HR-HSI. Existing methods directly utilize transformers to perform feature extraction and fusion. Despite the demonstrated success, there exist two limitations: 1) Employing the entire transformer model for feature extraction and fusion fails to fully harness the transformer’s potential in integrating the spectral of the HSI and spatial information of the MSI. 2) HSI has a strong spectral correlation and exhibits sparsity in the spatial domain. Existing transformer-based models do not optimize this physical property, which makes their methods prone to spectral distortion. To accomplish these issues, this paper introduces a novel framework for MHIF called Sparse Mix-Attention Transformer (SAMformer). Specifically, to fully harness the advantages of the Transformer architecture, we propose a Spectral Mix Attention Block (SMAB), which concatenates the keys and values extracted from LR-HSI and HR-MSI to create a new multi-head attention module. This design facilitates the extraction of detailed long-range information across spatial and spectral dimensions. Besides, to address the spatial sparsity inherent in HSI, we incorporated a sparse mechanism within the core of SMAB called Sparse Spectral Mix Attention Block (SSMAB). In the SSMAB, we compute attention maps from queries and keys and select the K highly correlated values as the sparse attention map. This approach enables us to achieve a sparse representation of spatial information while eliminating spatially disruptive noise. Extensive experiments conducted on three benchmark datasets, namely Cave, Harvard, and Pavia Center, demonstrate the SMAformer method outperforms state-of-the-art methods.

Heat transfer fluids are used in various industrial systems to maintain them in perfect operating conditions. Extensive research efforts have been dedicated to enhance the thermal properties of these heat transfer fluids to improve their efficiency. Developing nanofluids is a potential candidate for such enhancements. This study investigates the impact of incorporating TiO2 nanoparticles into two types of oils: transformer oil (NYTRO LIBRA) and virgin coconut oil (manufactured by Govi Aruna Pvt. Ltd.) at different temperatures and with varying volume fractions. The nanofluids were prepared using a two-step method by adding CTAB (Cetyltrimethylammonium bromide) surfactant. To minimize nanoparticle agglomeration, this study employed relatively low-volume fractions. Thermal properties by means of thermal conductivity, thermal diffusivity, and volumetric heat capacity were measured in accordance with ASTM (American Society for Testing and Materials) standard methods, using a multifunctional thermal conductivity meter (LAMBDA thermal conductivity meter). The measured thermal conductivity values were compared with theoretical models and previous research findings. It was confirmed that the modification of thermal properties was enhanced by doping TiO2 nanoparticles with different volume fraction.

Identification of plants is a challenging task which aims to identify the family, genus, and species level according to morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users to narrow down the possibilities. However, numerous morphological similarities between and within species make the classification difficult. In this paper, we tested a custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88K and 16K images for classifying plants at genus and species levels respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. The ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. ViT models also perform better for classifying plants at the species level compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success.

Guided image filter implicitly balances noise and details based on local variance, achieving noise suppression while preserving prominent edges. However, we have observed limitations in using variance to distinguish between noise and image details, resulting in the suppression of fine structures alongside noise. Furthermore, the goal of enhancing image details, which is crucial in image filtering, has not been adequately addressed in edge-preserving filter design. In this paper, we approach image filtering as a problem of spectral energy reconfiguration, where the gain of each spectral band is adaptively regulated to achieve simultaneous noise suppression and detail enhancement. Instead of relying on variance, we employ a linear noise estimator to obtain the Signal-to-Noise Ratio (SNR) measurement necessary for dynamic gain regulation. Similar to the guided image filter, we determine the filter coefficients by solving the closed-form solution of the optimizer. We demonstrate that the proposed extended guided filter effectively integrates information from multiple spectral bands locally, allowing for the joint enhancement of meaningful details while simultaneously smoothing noise.

Noise reduction is the major issue in the loudspeaker for the application of the musical instruments and related areas. In this paper, a noise disturbance control of a loudspeaker with optimal and robust controllers has been done successfully. The noise of the loudspeaker has been analyzed by simply track a reference cone displacement with the actual cone displacement. Static output feedback and H infinity optimal loop shaping controllers have been used to compare the actual and reference cone displacements by using a sine wave and random cone displacement signals and a promising results have been analyzed.

This paper describes the successful application of the Transformer model used in the natural language processing and vision tasks as a means of processing the time series of signals from gyroscope and accelerometer sensors for the classification of human activities. The Transformer model is based on deep neural networks with many layers which can generalize well on signals. All measured signals come from a smartphone placed in a waist bag. Activity prediction is sequence-to-sequence, each time step of the signal is assigned a designation of the performed activity. Emphasis is placed on attention mechanisms, which express individual dependencies between signal values within a time series. In comparison with another recent result, the recognition precision was improved from 89.67 percent to 99.2 percent. The transformer model should in the future be included among the top options in machine learning methods for human activity recognition.

The main sources of intrinsic noise in excitable cells at the microcircuit and network levels are the stochastic characteristics of ion channel gating and activation of the synaptic conductance. Studies using in vivo, in vitro, and in silico methods to examine the effects of synaptic background activity were not adequately investigated in non-neuronal excitatory cells, where neurotransmitter-based innervation also occurs. We created a mathematical model to replicate the background synaptic noise dynamics in a non-neuronal cell. We utilized the stochastic Ornstein-Uhlenbeck process to represent excitatory synaptic conductance, which was incorporated into a whole-cell model to produce spontaneous and evoked cellular electrical activities. The single-cell model includes many biophysically detailed ion channels represented by a set of ordinary differential equations in Hodgkin-Huxley and Markov formalisms. This paradigm effectively induced irregular spontaneous depolarizations (SDs) and spontaneous action potential (sAP) resembling in vitro-like electrical activity in the cells. The input resistance decreased by multiple factors, and the spontaneous action potential firing rate elevated. The potential to reach the action potential threshold is altered. Background synaptic activity can alter the input/output characteristics of non-neuronal excitatory cells. Suppressing these baseline activities would facilitate the discovery of new pharmaceutical targets for different clinical diseases.

Agriculture is pivotal in national economies, with pest detection significantly influencing food quality and quantity. Pest classification remains challenging in automated agriculture monitoring systems, exacerbated by the non-uniform pest scales and the scarcity of high-quality datasets. In this study, we constructed a pest dataset by acquiring domain-agnostic images from the Internet and resizing them to a standardized 299x299 pixel format. Additionally, we employed diffusion models to generate supplementary data. While Convolutional Neural Networks (CNNs) are prevalent for prediction and classification, they often lack effective global information integration and discriminative feature representation. To address these limitations, we propose the RS Transformer, an innovative model that combines elements like the Region Proposal Network, Swin Transformer, and ROI Align. Additionally, we introduce the Randomly Generated Stable Diffusion Dataset (RGSDD) to augment the availability of high-quality pest datasets. Extensive experimental evaluations demonstrate the superiority of our approach compared to both two-stage models (SSD and Faster R-CNN) and one-stage models (YOLOv3, YOLOv4, YOLOv5m, YOLOv8, and DETR). We rigorously assess performance using metrics such as mean Average Precision (mAP), F1Score, Recall, and mean Detection Time (mDT). Our research contributes to advancing pest detection methodologies in automated agriculture systems, promising improved food production and quality.

Synthetic Aperture Radar has been extensively used in numerous fields and can gather a wealth of information about the area of interest. This large-scene data-intensive technology puts a high value on automatic target recognition (ATR) which can free the utilizers and boost the efficiency. Recent advances in artificial intelligence have made it possible to create a deep learning-based SAR ATR that can automatically identify target features from massive input data. In the last 6 years, intensive research has been conducted in this area, however, most papers in the current SAR ATR field used recurrent neural network (RNN) and convolutional neural network (CNN)-varied models to deepen the regime’s understanding of the SAR images. To equip SAR ATR with updated deep learning technology, this paper tries to apply a lightweight vision transformer (LViT)-based model to classify SAR images. The entire structure was verified by an open- accessed SAR data set and recognition results show that the final classification outcomes are robust and more accurate in comparison with referred traditional network structures without even using any convolutional layers.

In this study, the degradation characteristics of radio-frequency (RF) low-noise amplifier (LNA) based on silicon-germanium (SiGe) heterojunction bipolar transistors (HBTs) due to total ionizing dose (TID) are investigated. The small-signal equivalent model of a SiGe HBT is utilized to analyze circuit-level performance including the input and the output matching and noise figure (NF). As a target circuit, an LNA with a cascode common-emitter stage with emitter degeneration is studied and the equation of each performance parameter is derived. The RF LNA fabricated using commercial 350 nm SiGe technology was exposed to X-ray irradiation with the total dose up to 3 Mrad (SiO2). The experimental results exhibit that modeled device parameters estimate the degraded circuit performance. In addition, the relative impact of each parameter on the circuit metrics is revealed, which is expected from the derived design equations. The key device parameters for modeling TID-induced circuit degradations include the base resistance, the transconductance, and the base-to-emitter capacitance.

Blood cell analysis is a crucial diagnostic process in medical practice. In particular, detecting white blood cells (WBCs) is essential for diagnosing of many diseases. The manual screening of blood films is a time-consuming and subjective process, which can lead to inconsistencies and errors. Therefore, automated detection of blood cells can improve the accuracy and efficiency of the screening process. In this study, an explainable Vision Transformer (ViT) model was proposed for the automatic detection of WBCs from blood films. The proposed model utilizes the self-attention mechanism to extract relevant features from the input images and leverages transfer learning by incorporating pre-trained model weights to improve its performance. The proposed model achieved a classification accuracy of 99.40% for five distinct types of WBCs and exhibited potential in reducing the time required for manual screening of blood films by pathologists. Upon examination of the misclassified test samples, it was observed that incorrect predictions were correlated with the presence or absence of granules in the cell samples. To validate this observation, the dataset was divided into two classes, namely Granulocytes and Agranulocytes, and a secondary training process was conducted. The resulting ViT model trained for binary classification achieved an accuracy of 99.70%, recall of 99.54%, precision of 99.32%, and F-1 score of 99.43% during the test phase. To ensure the reliability of the ViT model's multi-class classification of WBCs, the pixel areas that the model focuses on in its predictions are visualized through the Score-CAM algorithm.

We present a high-throughput nanoindentation study of in-situ bending effects on incipient plastic deformation behavior of polycrystalline and single-crystalline pure aluminum and pure copper at ultra-nano depths (<200nm). We find that hardness displays a statistically inverse dependence on in-plane stress for indentation depths smaller than 10nm, and the dependence disappears for larger indentation depths. In addition, plastic noise in the nanoindentation force and displacement displays statistically robust noise features, independently of applied stresses. Our experimental results suggest the existence of a regime in FCC crystals where ultra-nano hardness is sensitive to residual applied stresses, but plasticity pop-in noise is insensitive to it.

We derive the thermal noise spectrum of the Fourier transform of the electric field operator of a given wave vector starting from the quantum-statistical definitions and relate it to the complex frequency and wave vector dependent complex conductivity in a homogeneous, isotropic system of electromagnetic interacting electrons. We analyze separately the longitudinal and transverse case with their peculiarities. The Nyquist formula for vanishing frequency and wave vector, as well as its modification for non-vanishing frequencies and wave vectors follow immediately. Furthermore we discuss also the noise of the photon occupation numbers. It is important to stress that no additional assumptions at all were used in this straightforward proof.

Estimating the Remaining Useful Life (RUL) of aircraft engines holds a pivotal role in enhancing safety, optimizing operations, and promoting sustainability, thus being a crucial component of modern aviation management. Precise RUL predictions offer valuable insights into an engine’s condition, enabling informed decisions regarding maintenance and crew scheduling. In this context, we propose a novel RUL prediction approach in this paper, harnessing the power of Bi-directional LSTM and Transformer architectures, known for their success in sequence modeling, such as natural languages. We adopt the encoder part of the full Transformer as the backbone of our framework, integrating it with a self-supervised denoising autoencoder that utilizes Bidirectional LSTM for improved feature extraction. Within our framework, a sequence of multivariate time series sensor measurements serves as the input, initially processed by the Bidirectional LSTM autoencoder to extract essential features. Subsequently, these feature values are fed into our Transformer encoder backbone for RUL prediction. Notably, our approach simultaneously trains the autoencoder and Transformer encoder, different from the naive sequential training method. Through a series of numerical experiments carried out on the C-MAPSS datasets, we demonstrate that the efficacy of our proposed models either surpasses or stands on par with that of other existing methods.

Indoor localization is an active area of research dominated by traditional machine-learning techniques. Deep learning-based systems have shown unprecedented improvements and have accomplished exceptional results over the past decade, especially the Transformer network within natural language processing (NLP) and computer vision domains. We propose the hyper-class Transformer (HyTra), an encoder-only Transformer with multiple classification heads (one per class) and learnable embeddings, to investigate the effectiveness of Transformer-based models for received signal strength (RSS) based WiFi fingerprinting. HyTra leverages learnable embeddings and the self-attention mechanism to determine the relative position of the wireless access points (WAPs) within the high-dimensional embedding space, improving the prediction of user location. From an NLP perspective, we consider a fixed order sequence of all observed WAPs as a sentence and the captured RSS value(s) for every given WAP at a given reference point from a given user as words. We test our proposed network on public and private datasets of different sizes, proving that the quality of the learned embeddings and overall accuracy improves with increments in samples.

In this research paper, a high gain transformer less inverter modeling which is used for the smart grid technology or as the stand alone for home appliances is proposed. The proposed transformer less topology provides a higher voltage gain, low cost, small size and simple control stand alone transformer less inverter for home appliances. The above inverter is modeled by using software which is known as MATLAB/ Simulimk.

Visual object tracking is an important technology in camera based sensor networks, which has a wide range of practicability in auto drive system. A transformer is a deep learning model that adopts the mechanism of self-attention, and it differentially weights the significance of each part of the input data. It has been widely applied in the field of visual tracking. Unfortunately, the security of the transformer model is unclear. It makes such transformer-based applications be exposed to security threats. In this work, the security of the transformer model is investigated with the important component of autonomous driving, visual tracking. Such deep-learning-based visual tracking is vulnerable to adversarial attacks, so adversarial attacks are implemented as the security threats to conduct the investigation. First, adversarial examples are generated on top of video sequences to degrade tracking performance, and the frame-by-frame temporal motion is taken into consideration when generating perturbations over the predicted tracking results. Then, the influence of perturbations on performance is sequentially investigated and analyzed. Finally, numerous experiments on OTB100, VOT2018, and GOT-10k data sets demonstrate that the executed adversarial examples are effective on the performance drops of the transformer-based visual tracking.

Autoencoders are neural networks that have applications in denoising processes. Their use is widely reported in imaging (2D), though 1D series can also benefit from this function. Here, three canonical waveforms are used to train a neural network and achieve a signal-to-noise reduction with curves whose noise energy was above that of the signals. A real-world test is carried out with the same autoencoder subjected to a set of time series corrupted by noise generated by a zener diode, biased on the avalanche region. Results showed that, observed some guidelines, the autoencoder can indeed denoise 1D waveforms usually observed in electronics, particularly square waves found in digital circuits.

The correlations of seismic noise, recorded during 1997-2022 at 229 stations around the world are investigated. The property of waveforms, known as the Donoho-Johnston threshold, is analyzed, which separates the absolute values of the orthogonal wavelet coefficients into "small" and "large". Network of 50 reference points is considered. For each reference point, a time series with a time step of 1 day is calculated as the median of the values of the DJ index from the 5 nearest stations. For each reference point, the correlations between the values of the DJ index at other reference points are calculated in a sliding time window of 365 days. Average values of the DJ index decrease, which is interpreted as indicators of global seismic hazard increasing. The maximum distances between reference points with strong correlations show an explosive increase after 2011. Bursts in the mean coherences between the length of day (LOD) and the values of the DJ index at the reference points precede the release of seismic energy with a delay of about 530 days. High amplitude of the DJ index response to LOD for the times 2020-2022 was identified, which may forecast a strong earthquake in the second half of 2023.

Electrification of society, increasing renewable energy sources and mobility charging lead to new loading patterns for power transformers. Dynamic load conditions induce enhanced mechanical stress on the transformers’ windings, potentially causing degradation of the solid insulation over time and compromising the transformer's short-circuit withstand capability. Thermal expansion of the windings, caused by losses in the copper conductors, occurring as the transformer is load-ed, increases the stress. Conversely, magnetic losses in the core and tie plate expansion contribute to a reduction in stress. This paper presents the effect of step changes in core losses and copper losses by on-line measurements of the clamping pressure, to better understand the mechanical stresses acting upon the solid insulation cellulose materials.

Detection of partial discharge (PD) activities in high-voltage equipment can be done according to the several mechanisms of signal detection, which are electromagnetic wave signal detection, acoustic signal detection, chemical reactions, electrical signal detection, or optical emission detection. Recently, multiple methods of detection and localization of partial discharge activities occurred in power transformers and gas-insulated switchgear (GIS) have been proposed to monitor the health condition of high-voltage equipment, especially when the awareness regarding preventive maintenance has been emphasized at the industrial level and electrical providers. In aligning the needs of industrial and the improvement of PD detection methods, this manuscript focused on reviewing the current practice methods for the detection and localization of PD signals in high-voltage equipment and comparing their efficacy, in summarizing the future direction of research work-related methods of PD detection. The comparative reviews are discussed in terms of the mechanism of PD signal detection, indication parameters, calibration technique, advantages, and limitations of each method of PD measurement in detail.

The limits for recording weak signals for electrochemical seismic sensors are determined by their self-noise. At the same time, the noise nature is complex and not fully understood. In this work, for the first time, in addition to the frequency dependences of the noise amplitude, the difference in the phases of the noise currents of the cathodes of an electrochemical sensor has been studied. It has been established that at low frequencies the cathode currents change in an-tiphase. As the frequency increases, the phase difference becomes random. At the same time, the frequency at which the phase difference changes depend on the interelectrode distance; the clos-er the electrodes are located to each other, the greater it is. Physically, this effect is explained by the transition from noise caused by the integral flow of the working fluid to noise associated with vortex flows, the size of which depends on frequency. Thus, a new way of studying noise makes it possible to identify its physical nature and develop new methods of reduction.

Analyzing the records of Advanced LIGO and Virgo gravitational observatories, we found a specific time-domain asymmetry inherent only to the signals of their gravitational detectors. Experiments with different periodic signals, Gaussian and non-Gaussian noises, made it possible to conclude that the noise of gravitational detectors is an unusual mixture of signals. We also developed a specialized Pearson correlation analyzer to recognize the gravitational-wave events. It turned out that the LIGO detectors’ output signals include a significant (– 6 dB) component, which has the properties of records of reliably recognized gravitational waves. It allows us to argue that the gravitational background noise is largely due to the processes of merging astronomical objects. Since the specific signal is registered by the detectors continuously, we can consider the sub-kilohertz band gravitational oscillations field as detected. Our analysis method also allows us to estimate the contribution of the gravitational background component to the total signal energy. With its help, it will be possible not only to provide the radio-frequency estimation of the magnitude of gravitational disturbances but also, possibly, to construct a map of the gravitational noise of the sky.

Recommendation systems are crucial in navigating the vast digital market. However, user data’s dynamic and non-stationary nature often hinders their efficacy. Traditional models struggle to adapt to the evolving preferences and behaviours inherent in user interaction data, posing a significant challenge for accurate prediction and personalisation. Addressing this, we propose a novel theoretical framework, the Non-stationary Transformer, designed to capture and leverage the temporal dynamics within data effectively. This approach enhances the traditional transformer architecture by introducing mechanisms accounting for non-stationary elements, offering a robust and adaptable solution for recommendation systems. Our experimental analysis, encompassing deep learning and reinforcement learning paradigms, demonstrates the framework’s superiority over benchmark models. The empirical results confirm the efficacy of our proposed framework, which not only provides significant performance enhancements, approximately 8% in Logloss reduction and up to 2% increase in F1 score but also underscores its potential applicability across accumulative reward scenarios. These findings advocate adopting Non-stationary Transformer models to tackle the complexities of today’s recommendation tasks.

We propose Context-aware Feature Transformer Network (CaFTNet), a novel network for human pose estimation. To address the issue of limited modeling of global dependencies in convolutional neural networks, we design Transformerneck to strengthen the expressive power of features. Transformerneck directly substitutes the 3×3 convolution in bottleneck of HRNet with Contextual Transformer (CoT) block, while reducing the complexity of the network. Specifically, CoT first produces keys with static contextual information through 3×3 convolution. Then, relying on the query and contextualization keys, the dynamic contexts are generated through two concatenated 1×1 convolutions. Static and dynamic contexts are eventually fused as an output. Additionally, for the multi-scale networks, in order to further refine the features of the fusion output, we propose an Attention Feature Aggregation Module(AFAM). Technically, given an intermediate input, AFAM successively deduces attention maps along channel and spatial dimensions. Then, Adaptive refinement module(ARM) is exploited to activate the obtained attention maps. Finally, the input undergoes adaptive feature refinement through multiplication with the activated attention maps. Through the above studies, our lightweight network provides a powerful clue for detection of keypoints. Experiments are implemented on the COCO and MPII datasets. The model achieves 76.2 AP on the COCO val2017. Compared to other methods with the CNN as the backbone, CaFTNet reduces the number of parameters by 72.9 %. On the MPII, our method uses only 60.7% of the number of parameters, acquiring semblable results to other methods with the CNN as the backbone.

Due to the influence of background conditions, lighting conditions, occlusion issues and the image resolution, how to extract robust person features is one of the difficulties in ReID research. Vision in Transformers (ViT) has achieved significant results in the field of computer vision. However, the existing problems still limit its application in ReID due to slow extraction of person features and difficulty in utilizing local features of people. To solve the mentioned problems, we utilize Pyramid Vision Transformer (PVT) as the backbone of feature extraction and propose a PVT-based ReID method in conjunction with other studies. Firstly, some improvements suitable for ReID are used on the PVT backbone, and we establish a basic model by using powerful methods verified on CNN-based ReID. Secondly, in an effort to further promote the robustness of the person features extracted by the PVT backbone, two new modules are designed. (1) The local feature clustering (LFC) is recommend to enhance the robustness of person features by calculating the distance between local features and global feature to select the most discrete local features and clustering them. (2) The side information embeddings (SIE) are used to encode non-visual information and send it into the network for training to reduce its impact on person features. Finally, the experiments show that PVTReID has achieved excellent results in ReID datasets and are 20% faster on average than CNN-based ReID methods.

Structural magnetic resonance imaging (sMRI) is widely used in the clinical diagnosis of diseases due to its advantages: high definition and noninvasive. Therefore, computer-aided diagnosis based on sMRI images is broadly applied in classifying Alzheimer’s disease (AD). Due to the excellent performance of Transformer in computer vision, Vision Transformer (ViT) has been employed for AD classification in recent years. ViT relies on access to large datasets, while the sample size of brain imaging datasets is relatively insufficient. Moreover, the pre-processing procedures of brain sMRI images are complex and labor-intensive. To overcome the limitations mentioned above, we propose Resizer Swin Transformer (RST), a deep learning model that can extract information from brain sMRI images that are only briefly processed to achieve multi-scale and cross-channel features. In addition, we pre-trained our RST on a natural image dataset and obtained better performance. The experimental results of ADNI and AIBL datasets prove that RST can achieve better classification performance in AD prediction compared with CNN-based and Transformer models.

Long unpunctuated texts containing complex linguistic sentences are a stumbling block to processing any low-resource languages. Thus, approaches that attempt to segment lengthy texts with no proper punctuation into simple candidate sentences are a vitally important preprocessing task in many hard-to-solve NLP applications. In this paper, we propose (PDTS) a punctuation detection approach for segmenting Arabic text, built on top of a multilingual BERT-based model and some generic linguistic rules. Furthermore, we showcase how PDTS can be effectively employed as a text tokenizer for unpunctuated documents (i.e., mimicking the transcribed audio-to-text documents). Experimental findings across two evaluation protocols (involving an ablation study and a human-based judgment) demonstrate that PDTS is practically effective in both performance quality and computational cost.

Robots in space are necessarily extremely light and lack structural stiffness resulting in natural frequencies of resonance so low as to reside inside the attitude controller’s bandwidth. A variety of input trajectories can be used to drive a controller’s attempt to ameliorate the control-structural interactions where feedback is provided by low-quality, noisy sensors. Traditionally, step functions are used as the ideal input trajectory. However, step functions are not ideal in many applications, as they are discontinuous. Alternative input trajectories are explored in this manuscript and applied to an example system that includes a flexible appendage attached to a rigid main body. The main body is controlled by a reaction wheel. The equations of motion of the flexible appendage, rigid body, and reaction wheel are derived. A feedback controller is developed to account for the rigid body modes. Additional filters are added to compensate for the system’s flexible modes. Sinusoidal trajectories are autonomously generated to feed the controller. Whiplash compensation is additionally implemented for comparison. The control method without random errors with the smallest error is the sinusoidal trajectory method, which showed a 97.39% improvement when compared to the baseline response when step trajectories were commanded, while the sinusoidal method was inferior to traditional step trajectories when sensor noise and random errors were present.

This study was undertaken to investigate and analyze noise pollution in a large Chinese governmental hospital’s medical intensive care unit and compare to the WHO guidelines.This cross-sectional study was conducted in a MICU at a public governmental teaching hospital in Fujian province between July and August of 2017. A WENSN® WS1361 Integrated Sound Level Meter (China) was used for continuous every five seconds one week noise levels recording. After this measurement, the decibel meter was used for recording different location of isolation rooms and open bays, including occupied and unoccupied patient, and recording sound events occurs in the ICU to identify sources of noise. Peak and average noise levels were obtained from the meter, and data were downloaded from the WS1361 into a laptop computer. The measured mean equivalent sound pressure levels (L) and standard Aeq deviation over one week period were 66.64±7.57 dB(A), with acute spikes reaching 119.7 dB(A), the average sound level for a 24 hour period in a work day was 68.03±5.07 dB(A). These are higher than the current daytime environmental noise limit of 40-45 decibels in China and WHO. Mean work day noise was significantly louder than weekend time, there was a significant difference in work days and weekend (t=16.85;P=0.000).There was a statistical difference between the day time and night time shifts (t=34.67;P=0.000). The isolation rooms were significantly quieter than the open-bay rooms(t=46.15; p=0.00), sound levels in the occupied and unoccupied rooms also had significant difference(t=17.26; P=0.000).Two types of noise resources, including twenty kinds sources were identified and measured, mean noise levels ranged from of 61.33 to 79.21 dB(A). This study shows noise levels in intensive care units were exceeded the recommended. The study of the influence of noise on patient and staff is needed, and noise reduction strategies must be conduct in ICU.

Currently, narrowband Power line communication (PLC) is considered as an attractive communication system in smart grid environments for applications such as advanced metering infrastructure (AMI). In this paper, we will present a comprehensive comparison and analysis in time and frequency domain of noise measured in China and Italy. In addition, impulsive noise in these two countries are mainly analyzed and modeled using two probability based models, Middleton Class A (MCA) model and \(\alpha\) stable distribution model. The results prove that noise measured in China is rich in impulsive noise, and can be modeled well by \(\alpha\) stable distribution model, while noise measured in Italy has less impulsive noise, and can be better modeled by MCA model.

In a densely populated country like Bangladesh, universities grapple with the challenge of efficiently addressing myriad queries from a large student body, leading to a heightened workload for university stakeholders. To tackle these challenges, we introduce PixieGPT, a tailor-made Generative Pre-Trained Transformer for Bangladeshi universities. PixieGPT significantly mitigates workload by adeptly handling common university-related queries, thereby enhancing user experience. The hierarchical structure plays a crucial role in managing diverse queries from thousands of students about the university system. The solution introduces a modular hierarchical knowledge base (KB) with simpler complexities, addressing the intricacies of efficiently managing large volumes of queries. PixieGPT is designed in a modular way so that the solution is also adaptable for the implementation of other universities worldwide based on the requirements of a particular administrative system. The modular nature facilitates easy adaptation with minor changes based on specific university requirements, ensuring a seamless integration process. This paper delves into the intricacies of PixieGPT's design, emphasizing its pivotal role in mitigating workload challenges for university stakeholders in Bangladesh. The incorporation of BERT for Natural Language Understanding(NLU) and GPT models for Natural Language Generation(NLG) enhances PixieGPT's capabilities, contributing to the scalability and efficiency of the system. The presented use case underscores the practical benefits of PixieGPT, positioning it as a promising solution for universities globally with similar operational frameworks.

The purpose of this study is to ​​explore the use of a custom Transformer model in brain-computer interfaces (BCIs) that translate the neural activity present when an individual with limited verbal and fine-motor skills attempts to handwrite. As found in previous studies, Transformers have performed better than recurrent neural networks (RNNs) in translation tasks which are similar to its usage here in decoding neural signals into intended handwritten text. Due to the known benefits of a Transformer, the hypothesis was that the Transformer would show promise in the context of a BCI through the recorded metrics. The neural signals of a tetraplegic individual, when they attempted to handwrite, were provided by existing research. Four trials were conducted using data with or without augmentation which the model used when training to separately minimize training loss and validation loss. When comparing the results of a BCI with the implementation of a Transformer model with the original RNN BCI (the original data source), the Transformer model performed less favorably across all four trials. Although the results do not indicate that the Transformer model currently outperforms an RNN BCI, it is important to note that further testing of the model's capabilities (such as training it with a larger and more preferable dataset and/or for longer, comparing training times between the RNN and Transformer, and/or seeing how the Transformer is improved with an offline autocorrect feature) is necessary before determining whether Transformers can enhance communication in this manner.

Deep Learning (DL) has made significant advances in computer vision with the advent of Vision Transformers (ViT). Unlike Convolutional Neural Networks (CNNs), ViTs use self-attention to extract both local and global features from image data, and then use residual connections to feed these features directly into a fully networked multilayer perceptron head. In hospitals, hematologists prepare peripheral blood smears (PBSs) and read them under a medical microscope to detect abnormalities in blood counts such as leukemia. However, this task is time-consuming and prone to human error. This study investigates the transfer learning process of Google ViT and ImageNet CNNs to automate the reading of PBSs. The study used two online PBS datasets, PBC and BCCD, and transferred them into balanced datasets to investigate the influence of data amount and noise immunity on both neural networks. The PBC results show that Google ViT is an excellent DL neural solution for data scarcity. The BCCD results show that Google ViT is superior to ImageNet CNNs in dealing with unclean, noisy image data because it is able to extract both global and local features and use residual connections, despite the additional time and computational overhead.

Safe, high-quality and economical electric energy transportation is the basic requirements of modern power system operation. Transformer, as one of the core equipment of power system and national grid system, has the characteristics of diverse types, variable models and wide deployment. It is the basic equipment for power system to realize voltage change and electric energy distribution. Because the power system transformer needs to operate with load for a long time, the probability of failure is usually higher than that of other power equipment in general. This paper starts from the transformer fault and fault diagnosis. Firstly, the transformer fault types, traditional transformer fault diagnosis techniques and the advantages of machine learning in transformer fault diagnosis are reviewed. Secondly, the application of information system theory and information entropy in transformer fault diagnosis is introduced. Then it introduces machine learning technology, feature selection and extraction technology in transformer fault diagnosis, and machine learning algorithms such as support vector machine and extreme learning machine for transformer fault diagnosis. Finally, the potential development trend of information system theory, information entropy and machine learning in transformer fault diagnosis is forecasted. The combination of transformer fault prediction and machine learning algorithm is helpful for power system maintenance personnel to accurately predict the running state of power equipment, and also provides a new method and technology for the safe and reliable operation and regular maintenance of power system.

Wolfenden and his coworkers observed the astronomical numbers for the catalytic proficiency of some enzymes. We connected that pinnacle of biological evolution to the universal thermodynamic evolution. We added or multiplied a random noise with chosen rate constants to explore the correlation between dissipation and enzyme efficiency for ten enzymes: beta-galactosidase, glucose isomerase, β-lactamases from three bacterial strains, ketosteroid isomerase, triosephosphate isomerase, and carbonic anhydrase I, II, and T200H. The turnover number kcat and catalytic efficiency kcat/KM are proportional to the overall entropy production – the main parameter from irreversible thermodynamics. For most enzymes with the Michaelis-Menten type cycle kinetics, the best increase in the forward kcat/KM follows after increasing the equilibrium constant of substrate-enzyme association. The Discussion section emphasizes the role of biological evolution in harvesting order (high enzyme efficiency) from disorder (high noise and dissipation). It also connects the applications of the maximum partial entropy production theorem in optimizing enzyme kinetics (D. Juretić "Bioenergetics - A Bridge across Life and Universe") with the present total entropy production role analysis. De novo enzyme design and various attempts to speed up the rate-limiting catalytic steps may profit from our theoretical insights.

This paper explores the use of different deep learning models for predicting precipitation in 56 meteorological stations in Jilin Province, China. The models used include Stacked-LSTM, Transformer, and SVR, and Gaussian noise is added to the data to improve their robustness. Results show that the Stacked-LSTM model performs the best, achieving high prediction accuracy and stability. The study also conducts variable attribution analysis using LightGBM and finds that temperature, dew point, precipitation in previous days, and air pressure are the most important factors affecting precipitation prediction, which is consistent with traditional meteorological theory. The paper provides detailed information on the data processing, model training, and parameter settings, which can serve as a reference for future precipitation prediction tasks. The findings suggest that adding Gaussian noise to the dataset can improve the model's generalization ability, especially for predicting days with zero precipitation. Overall, this study provides useful insights into the application of deep learning models in precipitation prediction and can contribute to the development of meteorological forecasting and applications.

EMG analysis is becoming increasingly important in many research and clinical applications, including muscle fatigue detection, control of robotic mechanisms and prostheses, clinical diagnosis of neuromuscular diseases and quantification of force. However, electromyographic signals can be contaminated by various types of noise, interference and artifacts, which can lead to misinterpretation of the data acquired using this method. Even assuming best practices, the collected signal may still be altered by such contaminants. The aim of this paper is to review methods employed to reduce contamination of single channel EMG signals. This review is limited to methods performed directly on the measured EMG signal and those that allow total reconstruction of the EMG signal. Subtraction methods used in the time domain, denoising methods performed after signal decomposition and hybrid methods are assessed. It is defended that individual methods may be more or less suitable for a particular application depending on contaminant(s) present in the signal and on the specific requirements of the application.

This study aims to assess using a smartphone app (DecibelX), as a noise measuring alternative to the more costly traditional use of measuring noise levels with a Sound Level Meter (SLM). The study compares the accuracy of the app to readings taken with a SLM and dosimeter, and also evaluates the app’s performance for pure tone and narrow band noise. And a usability study identifies strengths and weaknesses related to usability of the app.

A recently published article posited the use of polymer matrix composites (PMCs) as a replacement material for low-carbon steel (LCS) in large power transformer (LPT) tanks [1]. PMCs offer potential advantages such as weight reduction, corrosion prevention, and self-healing of the tank material which may not be achievable with traditional LCS. LCS can arrest ballistic projectiles at relatively low velocities, but at higher velocities, penetration can occur leading to a potential major transformer failure. Numerical simulations of steel projectile impacts upon LCS plates and glass and/or carbon fiber polymer composite laminates showed that with sufficient thickness both could prevent projectile penetration. This prevention was especially efficient when the plates were coated with a high strain rate sensitive material such as polyurea (PU). Our simulations show that the addition of a 3 mm coating of PU to a standard 10 mm thick LCS plate used in LPT tanks could prevent penetration of a 400 m/s steel projectile. For PMC plates, the simulations with the same projectile velocity showed three times faster deceleration with a 3 mm PU coating than without the coating. Thus, two realistic approaches to improving the ballistic protection of LPTs are presented. In addition to their other advantages, this research clearly shows that PMCs with the coating could provide significant ballistic protection for the next generation of LPT tanks.

In the realm of the five-category classification endeavor, there has been limited exploration into applied techniques for classifying Arabic text. These methods have primarily leaned on singletask learning, incorporating manually crafted features that lack robust sentence representations. Recently, the Transformer paradigm has emerged as a highly promising alternative. However, when these models are trained using single-task learning, they often face challenges in achieving outstanding performance and generating robust latent feature representations, especially when dealing with small datasets. This issue is particularly pronounced in the context of the Arabic dialect, which has a scarcity of available resources. Given these constraints, this study introduces an innovative approach to dissecting sentiment in Arabic text. This approach combines Inductive Transfer (INT) with the Transformer paradigm to augment the adaptability of the model and refine the representation of sentences. By employing self-attention SE-A and feed-forward sub-layers as a shared Transformer encoder for both the five-category and three-category Arabic text classification tasks, this proposed model adeptly discerns sentiment in Arabic dialect sentences. The empirical findings underscore the commendable performance of the proposed model, as demonstrated in assessments of the Hotel Arabic-Reviews Dataset, the Book Reviews Arabic Dataset, and the LARB dataset.

Although wireless capsule endoscopy (WCE) detects small bowel diseases effectively, it has some limitations. For example, the reading process can be time-consuming due to the numerous images generated per case, and lesion detection accuracy may rely on the operators' skills and experiences. Hence, many researchers have recently developed deep learning-based methods to address these limitations. However, they tend to select only a portion of the images from a given WCE video and analyze each image individually. In this study, we note that more information can be extracted from the unused frames and temporal relations of sequential frames. Specifically, to increase the accuracy of lesion detection without depending on experts' frame selection skills, we suggest using whole video frames as the input to the deep-learning system. Thus, we propose a new Transformer-based neural encoder that takes the entire video as the input, exploiting the power of the Transformer to extract long-term global correlation within and between the input frames. Subsequently, we can capture the temporal context of the input frames and the attentional features within a frame. Tests on benchmark datasets of four WCE videos showed 95.1% sensitivity and 83.4% sensitivity. These results may significantly advance automated lesion detection techniques for WCE images. Our code is available at https://github.com/syupoh/VWCE-Net.git.

We introduce a novel hybrid Transformer-CNN architecture for robotic grasp detection, designed to enhance the accuracy of grasping unknown objects. Our proposed architecture has two key designs. Firstly, we develop a hierarchical transformer as the encoder, incorporating the external attention to effectively capture the correlation features across the data. Secondly, the decoder is constructed with cross-layer connections to efficiently fuse multi-scale features. Channel attention is introduced in the decoder to model the correlation between channels and to adaptively recalibrate the channel correlation feature response, thereby increasing the weight of the effective channels. Our method is evaluated on the Cornell and Jacquard public datasets, achieving an image-wise detection accuracy of 98.3% and 95.8% on each dataset, respectively. Additionally, we achieve object-wise detection accuracy of 96.9% and 92.4% on the same datasets. A physical experiment is also performed using the Elite 6Dof robot, with a grasping accuracy rate of 93.3%, demonstrating the proposed method's ability to grasp unknown objects in real-world scenarios. The results of this study show that our proposed method outperforms other state-of-the-art methods.

Incorporating source-side linguistic knowledge into the neural machine translation (NMT) model has recently achieved impressive performance on machine translation tasks. One popular method is to generalize the word embedding layer of the encoder to encode each word and its linguistic features. The other method is to change the architecture of the encoder to encode syntactic information. However, the former cannot explicitly balance the contribution from the word and its linguistic features. The latter cannot flexibly utilize various types of linguistic information. Focusing on the above issues, this paper proposes a novel NMT approach that models the words in parallel to the linguistic knowledge by using two separate encoders. Compared with the single encoder based NMT model, the proposed approach additionally employs the knowledge-based encoder to specially encode linguistic features. Moreover, it shares parameters across encoders to enhance the model representation ability of the source-side language. Extensive experiments show that the approach achieves significant improvements of up to 2.4 and 1.1 BLEU points on Turkish→English and English→Turkish machine translation tasks, respectively, which indicates that it is capable of better utilizing the external linguistic knowledge and effective improving the machine translation quality.

Standard ANNs lack flexibility when handling corrupted input due to their fixed structure. Spiking Neural Networks (SNNs) can utilize biological temporal coding features, such as noise-induced stochastic resonance and dynamical synapses to increase a model’s performance when its parameters are not optimized for a given input. Using the analog XOR task as a simplified Convolutional Neural Network analog, this paper demonstrates two key results: (1) SNNs solve the problem linearly inseparable in ANN with over 10% improvement in the optimal setting, and (2) in SNNs, the synaptic noise and dynamical synapses compensate for non-optimal parameters, achieving near-optimal results.

A crucial component for developing an automated speaker or speech recognition system is voice preprocessing, which filters unwanted noise and detects the speech part. This study aimed to develop a computerized model to remove background noise and improve signal quality for future applications. This model was developed on a large longitudinal dataset containing varying real-world noise and validated on both a public dataset and a locally collected test dataset in different environments. An overall voice pre-processing pipeline is presented in this study, including denoising, segmentation, feature extraction, and ease of storage. The backbone of the denoising model is a Kalman filter, where the parameters were obtained from a grid search method; the signal-to-noise ratio (SNR) was used as the performance metric. Also, the segmentation was done to remove the pauses from the audio signal before the feature extraction. Finally, the data was stored as a template with the most common features. The SNR result suggested that the Kalman filter-based proposed method performed successfully across diverse datasets. Thus, this model provides a robust and adaptable solution for real-world scenarios and also ensures the data storing quality for future applications.

Wind energy in Europe is aimed to grow at a steady, high pace, but opposition from residents to local wind farm plans is one of the obstacles to further growth. A large body of evidence shows that local populations want to be involved and respected for their concerns, but in practice this is a complex process that cannot be solved with simple measures such as financial compensation. The visual presence and the acoustic impact of a wind farm is an important concern for residents. Generally environmental noise management aims to reduce the exposure of the population, usually based on acoustics and restricted to a limited number of sources (such as transportation or industry) and sound descriptors (such as Lden). Individual perceptions are taken into account only at an aggregate, statistical level (such as percentage of exposed, annoyed or sleep-disturbed persons in the population). Individual perceptions and reactions to sound vary in intensity and over different dimensions (such as pleasure/fear or distraction). Sound level is in fact a weak predictor of the perceived health effects of sound. The positive or negative perception of and attitude to the source of the sound is a better predictor of its effects. This article aims to show how the two perspectives (based on acoustics and on perception) can lead to a combined approach in the management of a wind farm aimed to reduce annoyance, not primarily of sound level. An important aspect in this approach is what the sound means to people: is it associated with the experience of having no say in plans, does it lead to anxiety or worry, is it appropriate? The available knowledge will be applied to wind farm management: planning as well as operation.

Chronic exposure to noise can cause several extraordinary effects and involve all the systems of the human organism. In addition to cardiovascular, gastrointestinal and immune effects, the data in the literature show alterations in behavioral disturbances, in memory capacity and cognitive performance. Through this systematic review, the authors try to find out which are the main neurobehavioral alterations, in case of occupational exposure to noise. Literature review included articles published in the major databases (PubMed, Cochrane Library, Scopus), using a combina-tion of some relevant keywords. This online search yielded 4434 references; after selection, the authors analyzed 41 articles (4 narrative reviews and 37 original articles). From this analysis, it appears that main symptoms are related to psychological distress, annoyance, sleep disturbances, cognitive performance. Regarding tasks, the most frequent employments concern school staff, followed by employees from various industrial sectors and office workers. Although the causes are still widely debated, it is essential to protect these workers against chronic exposure to noise. In fact, in addition to a hearing loss, they can manifest many other related discomforts over time and compromise their full working capacity, as well as expose them to a greater risk of accidents or absences from work.

Software fault prediction is the very consequent research topic for software quality assurance. Data driven approaches provide robust mechanisms to deal with software fault prediction. However, the prediction performance of the model highly depends on the quality of dataset. Many software datasets suffers from the problem of class imbalance. In this regard, under-sampling is a popular data pre-processing method in dealing with class imbalance problem, Easy Ensemble (EE) present a robust approach to achieve a high classification rate and address the biasness towards majority class samples. However, imbalance class is not the only issue that harms performance of classifiers. Some noisy examples and irrelevant features may additionally reduce the rate of predictive accuracy of the classifier. In this paper, we proposed two-stage data pre-processing which incorporates feature selection and a new Rough set Easy Ensemble scheme. In feature selection stage, we eliminate the irrelevant features by feature ranking algorithm. In the second stage of a new Rough set Easy Ensemble by incorporating Rough K nearest neighbor rule filter (RK) afore executing Easy Ensemble (EE), named RKEE for short. RK can remove noisy examples from both minority and majority class. Experimental evaluation on real-world software projects, such as NASA and Eclipse dataset, is performed in order to demonstrate the effectiveness of our proposed approach. Furthermore, this paper comprehensively investigates the influencing factor in our approach. Such as, the impact of Rough set theory on noise-filter, the relationship between model performance and imbalance ratio etc. comprehensive experiments indicate that the proposed approach shows outstanding performance with significance in terms of area-under-the-curve (AUC).

This paper exposes the initial part of a larger research on the impact of the automotive on human health and the quality of life and environment. After a brief introduction on the need for responsible and sustainable approaches and few questions on the subject, some considerations and statistical data are presented, based on a study of the literature on the impact of road traffic and vehicles noise and vibration on people's comfort and health and their quality of life. The research results show, based on official statistics, the significant harmful impact of noise and vibration from motor vehicles and road transport on people's health and quality of life, especially in urban areas during the day. Also, the significant increase in the number of electric and hybrid vehicles from one year to another, a reality and a necessity nowadays, and the awareness that electric vehicles are not perfectly quiet and comfortable, open new research opportunities and require the development of new standards, materials, tools, equipment and test methods in the field of NVH, in a sustained synergistic approach from all stakeholders, to meet the needs and demands of today's consumers, and to comply with existing regulations and standards on environmental protection and sustainable development.

In forensic acoustics, a possible area of analysis is represented by unwanted sound that 1 is perceived as a source of intrusion or disturbance within a certain auditory context. This context 2 is defined as the "auditory scene" and refers to the set of sounds present in a specific environment. 3 The presence of unwanted sounds in the auditory scene can cause a wide range of negative effects, 4 including disturbance, discomfort, moral or immoral harm, and other types of negative impact on the 5 health and well-being of individuals exposed to noise. In 2022, the technical specification UNI/TS 6 11844:2022 dedicated to the measurement and analysis of intrusive noise was published. The standard 7 introduces the concept of intrusive noise and defines its calculation methods based on environmental 8 measurements. The purposes of this technical specification is to provide an objective support to 9 methods already in used in acoustic disputes, where the assessment of the annoyance of a noise is 10 often a subjective evaluation of the technician. This work delves into the application to some real 11 cases, identifying the potentiality and the limits of the standardized method.

To enhance the overall reliability of the power system, engineers have redirected their focus toward health monitoring and early detection of faults in transformers. Among these faults, transformer core defects demand particular attention. While fault simulation using software has traditionally been the preferred approach, these methods suffer from data inaccuracies in real-world conditions. Consequently, conducting actual experimental setups with induced faults is imperative to investigate core issues. This study uses Hilbert Transform (HT) as a signal processing technique to extract crucial data characteristics, thereby enhancing the performance of the classifier model. The research involves analyzing electric current signals from a single-phase 1kVA transformer. A comparative assessment of our proposed model was conducted using raw data and Fast Fourier Transform (FFT), evaluating accuracy, precision, recall, F1-score, and computational time. The results demonstrate a significant improvement in all metrics for the classifier models, particularly the k-nearest neighbor (KNN) algorithm, which exhibited values of 83.89%, 84.39%, 83.89%, 83.79%, and 0.0156 seconds, respectively. Future work aims to extend this analysis under different loading conditions.

The question of molecular similarity is core in cheminformatics, and is usually assessed via a pairwise comparison based on vectors of properties or molecular fingerprints. We recently exploited variational autoencoders to embed 6M molecules in a chemical space, such that their (Euclidean) distance within the latent space so formed could be assessed within the framework of the entire molecular set. However, the standard objective function used did not seek to manipulate the latent space so as to cluster the molecules based on any perceived similarity. Using a set of some 160,000 molecules of biological relevance, we here bring together three modern elements of deep learning to create a novel and disentangled latent space, viz transformers, contrastive learning, and an embedded autoencoder. The effective dimensionality of the latent space was varied such that clear separation of individual types of molecules could be observed within individual dimensions of the latent space. The capacity of the network was such that many dimensions were not populated at all. As before, we assessed the utility of the representation by comparing clozapine with its near neighbours, and did the same for various antibiotics related to flucloxacillin. Transformers, especially when as here coupled with contrastive learning, effectively provide one-shot learning, and lead to a successful and disentangled representation of molecular latent spaces that at once uses the entire training set in their construction while allowing ‘similar’ molecules to cluster together in an effective and interpretable way.

Interleaved power factor correction (PFC) is widely used circuit topology due to good efficiency and power density for single-switch boost PFC. As the differential mode (DM) electromagnetic interference (EMI) noise magnitude depends upon the input current ripple, this research details a comprehensive study of DM EMI filter design for interleaved boost PFC with the aim of minimizing the component size. It is also demonstrated that the different numbers of interleaved stages and switching frequency influence the filter attenuation requirement and, thus, the EMI filter size. First, an analytical model is derived on the basis of the Norton equivalent circuit model for the differential mode noises of interleaved boost PFC within the frequency range of 9-500 kHz. The derived model can help identify the optimal phase shifting among the interleaved boost converters in order to minimize the considered differential mode noises at the filter design frequency. So, a novel phase-shift method is developed to get a minimized attenuation required by a filter in Band B. Further, a volume optimization of the required DM filter was introduced based on the calculated filter attenuation and volumetric component parameters. Based on the obtained results, unconventional and conventional phase shifts have demonstrated a good performance in decreasing the EMI filter volume in Band B and Band A, respectively. A 2-kW interleaved PFC case study is presented to verify the theoretical analyses and the impact of phase-shifting on EMI filter size.

Noise reduction in medical images is a perplexing undertaking for the researchers in digital image processing. Noise generates maximum critical disturbances as well as touches the medical images quality, ultrasound images in the field of biomedical imaging. The image is normally considered as gathering of data and existence of noises degradation the image quality. It ought to be vital to reestablish the original image noises for accomplishing maximum data from images. Medical images are debased through noise through its transmission and procurement. Image with noise reduce the image contrast and resolution, thereby decreasing the diagnostic values of the medical image. This paper mainly focuses on Gaussian noise, Pepper noise, Uniform noise, Salt and Speckle noise. Different filtering techniques can be adapted for noise declining to improve the visual quality as well as reorganization of images. Here four types of noises have been undertaken and applied on medical images. Besides numerous filtering methods like Gaussian, median, mean and Weiner applied for noise reduction as well as estimate the performance of filter through the parameters like mean square error (MSE), peak signal to noise ratio (PSNR), Average difference value (AD) and Maximum difference value (MD) to diminish the noises without corrupting the medical image data.

In Brain-Computer Interface Motor Imagery (BCI-MI) systems, Convolutional Neural Networks (CNNs) have traditionally dominated as the deep learning method of choice, demonstrating significant advancements in state-of-the-art studies. Recently, Transformer models with attention mechanisms have emerged as a sophisticated technique, enhancing the capture of long-term dependencies and intricate feature relationships in BCI-MI. This research investigates the performance of EEG-TCNet and EEG-Conformer models, which are trained and validated using various hyperparameters and bandpass filters during preprocessing to assess improvements in model accuracy. Additionally, this study introduces the EEG-TCNTransformer, a novel model that integrates the convolutional architecture of EEG-TCNet with a series of self-attention blocks employing a multi-head structure. The EEG-TCNTransformer achieves an accuracy of 82.97% without the application of bandpass filtering. The source code of EEG-TCNTransformer is available on GitHub.

Accurate estimation of Remaining Useful Life (RUL) for aircraft engines is essential for ensuring safety and uninterrupted operations in the aviation industry. Numerous investigations have leveraged the success of attention-based Transformer architecture in sequence modeling tasks, particularly in its application to RUL prediction. These studies primarily focus on utilizing onboard sensor readings as input predictors. While various Transformer-based approaches have demonstrated improvement in RUL predictions, their exclusive focus on temporal attention within multivariate time series sensor readings, without considering sensor-wise attention, raises concerns about potential inaccuracies in RUL predictions. To address this concern, our paper proposes a novel solution in the form of a two-stage attention based hierarchical transformer (STAR) frame-work. This approach incorporates a two-stage attention mechanism, systematically addressing both temporal and sensor-wise attentions. Furthermore, we enhance the STAR RUL prediction framework by integrate hierarchical encoder-decoder structures to capture valuable information across different time scales. By conducting extensive numerical experiments with the CMAPSS datasets, we demonstrate that our proposed STAR framework significantly outperforms current state-of-the-art models for RUL prediction.

Social media platforms are increasingly enabling the propagation of content from groups related to drug use, thus posing risks for the wider population and, in particular, individuals who are amenable to drug use and drug addiction. The detection of drug use content on social media platforms is a priority for governments, technology companies, and drug law enforcement organizations. To counter this issue, various techniques have been developed to identify and promptly remove drug use content, while also blocking its creators from network access. In this paper, we introduce a manually annotated Twitter dataset, comprising 156,521 tweets published between 2008 and 2022, specifically compiled for the purpose of drug use detection. The dataset underwent annotation by several group of expert annotators who classified the tweets as either drug use or non-drug use. Exploratory data analysis was conducted to comprehend the dataset's characteristics. Various classification algorithms, including SVM, XGBoost, RF, NB, LSTM, and BERT were employed using the dataset. Among the traditional machine learning models, SVM utilizing term frequency-inverse document frequency features achieved the highest F1-Score (0.9017). However, BERT with textual features concatenated with numerical and categorical features in ensemble method surpassed the performance of traditional models, attaining F1-Score of 0.9112. To facilitate future research and enhance English online drug use classification accuracy, the dataset will be made publicly available.

The operation of transformers suffers from natural or man-made disasters, subjecting the equipment to prolonged exposure to temperature, lightning strikes, transient over-voltages, and over-current, gradually producing insulation aging phenomenon, which results in partial discharges within the transformer. Without dealing with it beforehand properly, it may lead to insulation breakdown. Nowadays, with the mature development of microchip control technology and wireless communication technology, which is helpful for realizing the research for online real-time and long-term monitoring capabilities for power equipment. A transformer operating condition monitoring and diagnostic system that can rapidly and effectively prevent the breakdown of transformer insulation, which can impact the overall power supply system is developed in this paper. The system is divided into two parts based on its function. The first part is the operating condition monitoring and real-time alert unit for the transformer, primarily composed of an embedded computing module, a sensor module, and a transmission module. Its work content is to capture real-time online partial discharge ultrasonic signals and high frequency current comparator pulse signals, and analyze and determine the condition of the internal insulation and operational status whether it is fault or not. The second part is the central control unit, consisting mainly of an industrial computer and a transmission module. Its work content is to store the ultrasonic and high frequency current comparator pulse signals from the transformer operation monitoring and real-time alert unit. It uses the software to eliminate signal noise and interference, and then utilizes artificial neural networks to identify the type of fault. In this paper, the research for the phenomenon of insulation degradation in transformer equipment aims to establish aging trend profiles through the dual malfunctioning alert and aging process analysis, as well as the long-term measurement of ultrasonic signals from partial discharges and high-frequency current comparator pulse signals. This approach provides crucial reference data and a foundation for disposable on-site measurement, assessing the phenomenon of insulation aging stages, defects and damage of the transformers effectively. It allows for timely replacement or maintenance in advance, achieving the prevention of malfunctioning and predictive diagnosis of aging.

Assessing observation noise is a critical step in the development of a stochastic model for GNSS navigation and positioning. This process ensures that the statistical properties of the observational data are accurately characterized, leading to more reliable and precise positioning results. Traditionally, the one sigma values for observation noise, 0.3 m for code and 3 mm for carrier phase, alongside elevation-dependent weighting schemes, have been standard. However, these may no longer be suitable due to significant advancements in GNSS systems, receivers, and antennas. Previous research predominantly focused on code type and PPP techniques, often limited by the inability to separately assess observation types across different frequency bands due to ionospheric delay. Furthermore, these studies were generally constrained by limited experimental data. This research advocates for the use of ultra-short baselines to eliminate atmospheric delay and other error sources, providing a detailed assessment of observation noise for various frequency bands, GNSS systems, and receiver & antenna types over an extensive period and across multiple baselines. The findings suggest a need to reconsider traditional one sigma values and elevation-dependent weighting schemes for current applications.

This study aims to tackle the challenge of high noise levels on balconies while preserving natural ventilation. Eight innovative balcony designs, incorporating elements like diffuser edges, undulating ceilings, Helmholtz resonators, grooves, or sound traps, were evaluated via finite element (FE) modeling. The extensive FE studies involved about 10 million elements per analysis case. Results showed that a standard balcony with a front parapet wall could achieve a noise reduction of around 10 dBA, with the jagged ledge design providing an additional 2 dBA improvement. Adding protruded ledge designs led to higher insertion loss (IL) by up to 9.4 dBA, especially at higher stories. Having wall-embedded Helmholtz resonators improved IL by up to 1.5 dBA. The jagged ledge design consistently exhibited positive IL across a broad frequency range from 200 Hz to 2 kHz. Combining beneficial balcony ceilings and wall ledges significantly reduced noise across lower and higher frequency ranges. Front jagged and full wavy ceilings offered positive IL throughout different storeys, proving their effectiveness against human vocal range. This study found that jagged ledge and front jagged ceiling designs, effective across various balcony heights, are viable options for improving balcony noise mitigation, providing valuable insights for architects and designers seeking practical solutions for outdoor noise reduction.

This article investigates the source of booming noise emanating from the tailgates of electric vehicles, along with proposed strategies to mitigate it. This study involved the measurement of booming noises during on-road vehicle tests to pinpoint their origins. Additionally, operational deflection shapes (ODS) were extracted from the tailgate vibration signals to gain insight into its dynamic behavior. Modal tests were conducted on the tailgate to determine its dynamic characteristics and compared with driving test results to reveal the mechanism responsible for tailgate-induced booming noise. It was established that such noise is primarily due to the tailgate modes resulting from a combination of rigid body motion in the fore-aft direction and deformation in the central section of the panel. An analytical model of the tailgate was developed using commercial finite element analysis software to propose measures for reducing booming noise. Experimental findings validated the model accuracy. Structural enhancements were implemented to enhance the panel stiffness and improve the connection between the vehicle and tailgate via bushings to dampen the booming noise resulting from tailgate motion. Under random force inputs, analytical results demonstrated a 13.8% reduction in maximum deformation in the tailgate model in the improved structural configuration with increased panel stiffness.

We discuss the optimal control formulation for enhancement and denoising of satellite multiband images and propose to take it in the form of an L1-control problem for quasi-linear parabolic equation with non-local p[u]-Laplacian and with a cost functional of a tracking type. The main characteristic feature of the considered class of parabolic problems is the fact that the variable exponent p(t,x) and the anisotropic diffusion tensor D(t,x) are not well predefined a priori, but instead these characteristic non-locally depend on a solution of this problem, i.e., pu=p(t,x,u) and Du=D(t,x,u). We prove the existence of optimal pairs with sparse L1-controls using for that the indirect approach and a special family of approximation problems.

In underwater optical wireless communications (UOWC), scattering of the propagating light beam results in both intensity and phase variations, which limit the transmission link range and channel bandwidth, respectively. Scattering of photons while propagating through the channel is a random process, which results in the channel-dependent scattering noise. In this work, we introduce for the first time an analytical model for this noise and investigate its effect on the bit error rate performance of the UOWC system for three types of waters and a range of transmission link spans. We show that, for a short range of un-clear water or a longer range of clear water, the number of photons experiencing scattering is high, thus leading to the increased scattering noise.

It has remained a hard nut for years to segment sonar images, most of which are noisy images with inevitable blur after noise reduction. For the purpose of solutions to this problem, a fast segmentation algorithm is proposed on the basis of the gray value characteristics of sonar images. This algorithm is endowed with the advantage in no need of segmentation thresholds to be calculated. To realize this goal, it follows the undermentioned steps: first, calculate the gray matrix of the fuzzy image background. After adjusting the gray value, segment the region into the background region, buffer region and target regions. After filtering, reset the pixels with gray value lower than 255 to binarize images and eliminate most artifacts. Finally, remove the remaining noise from images by means of morphological image processing. The simulation results of several sonar images show that the algorithm can segment the fuzzy sonar image quickly and effectively, with no problem of incomplete image target shape. Thus, the stable and feasible method is testified.

Purpose: The study is aimed to quantify the effects of social noise (personal music players (PMP), high-intensity noise exposure events) and road traffic noise exposures in the sample of Slovak university students living and studying in Bratislava. Methods: There were 1,003 university students (306 males and 697 females, average age 23.13±2) enrolled in the study; 347 lived in the student housing facility exposed to road traffic noise (LAeq =67.6 dB) and 656 in the control one (LAeq =53.4 dB). Respondents completed a validated ICBEN 5-grade scale “Noise annoyance questionnaire”. The exposure to PMP was objectified by the conversion of the subjective evaluation of the volume setting and duration. With the cooperation of the ENT specialist, we arranged audiometric examinations on the pilot sample of 41 volunteers. Results: From the total sample of 1,003 students, 794 (79.16 %) of them reported the use of PMP in the course of the last week; average time of 285 minutes. There was a significant difference in PMP use between the exposed (85.59 %) and the control group (75.76 %) (p=0.01). Among PMP users 30.7 % exceeded the LAV (lower action value for industry LAeq,8h = 80 dB). On a pilot sample of volunteers (n=41) audiometry testing was performed indicating a hearing threshold shift at higher frequencies in 22% of subjects. Conclusions: The results of the study on a sample of young healthy individuals showed the importance of exposure to environmental noise from different sources (transportation, neighborhood, construction, entertainment facilities, etc.) as well as social noise and the need for prevention and intervention.