Search Results (3,531)

Lightweight speech denoising models have made remarkable progress in improving both speech quality and computational efficiency. However, most models rely on long temporal windows as input, limiting their applicability in low-latency, real-time scenarios on edge devices. To address this challenge, we propose a lightweight hybrid module, Temporal Statistics Enhancement, Squeeze-and-Excitation-based Dual Convolutional Attention, and Band-wise Attention (TSE, SDCA, BA) Module. The TSE module enhances single-frame spectral features by concatenating statistical descriptors—mean, standard deviation, maximum, and minimum—thereby capturing richer local information without relying on temporal context. The SDCA and BA module integrates a simplified residual structure and channel attention, while the BA component further strengthens the representation of critical frequency bands through band-wise partitioning and differentiated weighting. The proposed model requires only 0.22 million multiply–accumulate operations (MMACs) and contains a total of 112.3 K parameters, making it well suited for low-latency, real-time speech enhancement applications. Experimental results demonstrate that among lightweight models with fewer than 200K parameters, the proposed approach outperforms most existing methods in both denoising performance and computational efficiency, significantly reducing processing overhead. Furthermore, real-device deployment on an improved hearing aid confirms an inference latency as low as 2 milliseconds, validating its practical potential for real-time edge applications. Full article

Accurate and real-time classification of low-latency Internet traffic is critical for applications such as video conferencing, online gaming, financial trading, and autonomous systems, where millisecond-level delays can degrade user experience. Existing methods for low-latency traffic classification, reliant on raw temporal features or static statistical analyses, fail to capture dynamic frequency patterns inherent to real-time applications. These limitations hinder accurate resource allocation in heterogeneous networks. This paper proposes a novel framework integrating wavelet transform (WT) and artificial neural networks (ANNs) to address this gap. Unlike prior works, we systematically apply WT to commonly used temporal features—such as throughput, slope, ratio, and moving averages—transforming them into frequency-domain representations. This approach reveals hidden multi-scale patterns in low-latency traffic, akin to structured noise in signal processing, which traditional time-domain analyses often overlook. These wavelet-enhanced features train a multilayer perceptron (MLP) ANN, enabling dual-domain (time–frequency) analysis. We evaluate our approach on a dataset comprising FTP, video streaming, and low-latency traffic, including mixed scenarios with up to four concurrent traffic types. Experiments demonstrate 99.56% accuracy in distinguishing low-latency traffic (e.g., video conferencing) from FTP and streaming, outperforming k-NN, CNNs, and LSTMs. Notably, our method eliminates reliance on deep packet inspection (DPI), offering ISPs a privacy-preserving and scalable solution for prioritizing time-sensitive traffic. In mixed-traffic scenarios, the model achieves 74.2–92.8% accuracy, offering ISPs a scalable solution for prioritizing time-sensitive traffic without deep packet inspection. By bridging signal processing and deep learning, this work advances efficient bandwidth allocation and enables Internet Service Providers to prioritize time-sensitive flows without deep packet inspection, improving quality of service in heterogeneous network environments. Full article

This paper proposes an Adam-optimized Deep Belief Networks (Adam-DBNs) denoising method for throat-attached piezoelectric signals. The method aims to process mechanical vibration signals captured through polyvinylidene fluoride (PVDF) sensors attached to the throat region, which are typically contaminated by environmental noise and physiological noise. First, the short-time Fourier transform (STFT) is utilized to convert the original signals into the time–frequency domain. Subsequently, the masked time–frequency representation is reconstructed into the time domain through a diagonal average-based inverse STFT. To address complex nonlinear noise structures, a Deep Belief Network is further adopted to extract features and reconstruct clean signals, where the Adam optimization algorithm ensures the efficient convergence and stability of the training process. Compared with traditional Convolutional Neural Networks (CNNs), Adam-DBNs significantly improve waveform similarity by 6.77% and reduce the local noise energy residue by 0.099696. These results demonstrate that the Adam-DBNs method exhibits substantial advantages in signal reconstruction fidelity and residual noise suppression, providing an efficient and robust solution for throat-attached piezoelectric sensor signal enhancement tasks. Full article

Advanced Persistent Threat (APT) attacks pose a serious challenge to traditional detection methods. These methods often suffer from high false-alarm rates and limited accuracy due to the multi-stage and covert nature of APT attacks. In this paper, we propose TSE-APT, a time-series ensemble model that addresses these two limitations. It combines multiple machine-learning models, such as Random Forest (RF), Multi-Layer Perceptron (MLP), and Bidirectional Long Short-Term Memory Network (BiLSTM) models, to dynamically capture correlations between multiple stages of the attack process based on time-series features. It discovers hidden features through the integration of multiple machine-learning models to significantly improve the accuracy and robustness of APT detection. First, we extract a collection of dynamic time-series features such as traffic mean, flow duration, and flag frequency. We fuse them with static contextual features, including the port service matrix and protocol type distribution, to effectively capture the multi-stage behaviors of APT attacks. Then, we utilize an ensemble-learning model with a dynamic weight-allocation mechanism using a self-attention network to adaptively adjust the sub-model contribution. The experiments showed that using time-series feature fusion significantly enhanced the detection performance. The RF, MLP, and BiLSTM models achieved 96.7% accuracy, considerably enhancing recall and the false positive rate. The adaptive mechanism optimizes the model’s performance and reduces false-alarm rates. This study provides an analytical method for APT attack detection, considering both temporal dynamics and context static characteristics, and provides new ideas for security protection in complex networks. Full article

To meet the requirements for radar echo acquisition and feature extraction from stratified media and rough-surfaced targets, a vehicle was geometrically modelled in CAD. Monte Carlo techniques were applied to generate the rough interfaces at air–snow and snow–soil boundaries and over the vehicle surface. Soil complex permittivity was characterized with a four-component mixture model, while snow permittivity was described using a mixed-media dielectric model. The composite electromagnetic scattering from a rough-surfaced vehicle on snow-covered soil was then analyzed with the finite-difference time-domain (FDTD) method. Parametric studies examined how incident angle and frequency, vehicle orientation, vehicle surface root mean square (RMS) height, snow liquid water content and depth, and soil moisture influence the composite scattering coefficient. Results indicate that the coefficient oscillates with scattering angle, producing specular reflection lobes; it increases monotonically with larger incident angles, higher frequencies, greater vehicle RMS roughness, and higher snow liquid water content. By contrast, its dependence on snow thickness, vehicle orientation, and soil moisture is complex and shows no clear trend. Full article

XSPICE models for a generic transmission line, a microstrip line, and coupled microstrips are presented. The developed models extend general-purpose circuit simulation tools using RF circuits design features. The models could be used for circuit simulation in frequency, DC, and time domains for any active or passive RF or microwave schematic (including microwave monolithic integrated circuits—MMICs) involving transmission lines. The presented models could be used with any circuit simulation backend supporting XSPICE extensions and could be integrated without patching the core simulator code. The presented XSPICE models for microstrip lines take into account the frequency dependency of characteristic impedance and dispersion. The models were designed using open-source circuit simulation software. This study provides a practical example of the low-noise RF amplifier (LNA) design with Ngspice simulation backend using the proposed models. Full article

Ventricular arrhythmias (VAs) are critical cardiovascular diseases that require rapid and accurate detection. Conventional approaches relying on multi-lead ECG or deep learning models have limitations in computational cost, interpretability, and real-time applicability on wearable devices. To address these issues, a lightweight and interpretable framework based on multiple complex networks was proposed for the detection of life-threatening VAs using short-term single-lead ECG signals. The input signals were decomposed using the fixed-frequency-range empirical wavelet transform, and sub-bands were subsequently analyzed through multiscale visibility graphs, recurrence networks, cross-recurrence networks, and joint recurrence networks. Eight topological features were extracted and input into an XGBoost classifier for VA identification. Ten-fold cross-validation results on the MIT-BIH VFDB and CUDB databases demonstrated that the proposed method achieved a sensitivity of 99.02 ± 0.53%, a specificity of 98.44 ± 0.43%, and an accuracy of 98.73 ± 0.02% for 10 s ECG segments. The model also maintained robust performance on shorter segments, with 97.23 ± 0.76% sensitivity, 98.85 ± 0.95% specificity, and 96.62 ± 0.02% accuracy on 2 s segments. The results outperformed existing feature-based and deep learning approaches while preserving model interpretability. Furthermore, the proposed method supports mobile deployment, facilitating real-time use in wearable healthcare applications. Full article

In this study, the combined influence of vibration direction, feature selection strategy, and the support vector machine (SVM) kernel on the classification accuracy of unbalance faults was investigated. Experiments were carried out on a Jeffcott rotor test rig at a constant speed and under three operating conditions. The overlapping sliding window method was used for raw sample expansion. Features extracted from time domain signals and from the order and power spectra obtained in the frequency domain were ranked using the Kruskal–Wallis algorithm. Based on the feature-ranking results, the three most discriminative features for each domain–axis combination, as well as all nine most discriminative features for each axis in a hybrid manner, were fed into SVM classifiers with different kernels, and their performance was evaluated using ten-fold cross-validation. Classification using vibration signals in the vertical direction had higher accuracy rates than those using signals in the horizontal direction for the feature sets obtained in the same domains. According to the statistical results, feature set selection had a much greater impact on classification accuracy than SVM kernel choice. Power spectrum-based features allowed higher classification accuracies in all SVM algorithms compared to both the time domain features and the order spectrum-based features for detecting unbalance faults. Increasing the number of features or employing hybrid feature selection did not result in a consistent or significant enhancement in overall classification performance. Selecting the right SVM kernel shapes both the model’s flexibility and its fit to the chosen feature space; when this fit is inadequate, classification accuracy may decrease. Consequently, by selecting the appropriate vibration direction, feature set, and SVM kernel, an improvement of up to 67% in unbalance fault classification accuracy was achieved. Full article

Rolling element bearings serve as critical transmission components in industrial automation systems, yet their fault signatures are susceptible to interference from strong background noise, complex operating conditions, and nonlinear impact characteristics. Addressing the limitations of conventional methods in adaptive parameter optimization and weak feature enhancement, this paper proposes an innovative diagnostic framework integrating Improved Goose optimized Variational Mode Decomposition (IGOOSE-VMD), RobustICA, and CYCBD. First, to mitigate modal aliasing issues caused by empirical parameter dependency in VMD, we fuse a refraction-guided reverse learning mechanism with a dynamic mutation strategy to develop the IGOOSE. By employing an energy-feature-driven fitness function, this approach achieves synergistic optimization of the mode number and penalty factor. Subsequently, a multi-channel observation model is constructed based on optimal component selection. Noise interference is suppressed through the robust separation capabilities of RobustICA, while CYCBD introduces cyclostationarity-based prior constraints to formulate a blind deconvolution operator with periodic impact enhancement properties. This significantly improves the temporal sparsity of fault-induced impact components. Experimental results demonstrate that, compared to traditional time–frequency analysis techniques (e.g., EMD, EEMD, LMD, ITD) and deconvolution methods (including MCKD, MED, OMEDA), the proposed approach exhibits superior noise immunity and higher fault feature extraction accuracy under high background noise conditions. Full article

Individuals with immunosuppressive conditions are at a higher risk of developing malignancies than those in the general population. Immunosuppression weakens tumor immunity, hinders the detection of pro-oncogenic cells, and activates oncogenic viruses. Malignancies arising in immunosuppressed patients tend to be aggressive, have a high incidence of virus-associated cancers, and are reversible in some cases. Notably, immunosuppressive agents influence the frequency and type of malignancies, as well as their clinicopathological features. Organ transplant recipients receive long-term immunosuppressants to prevent acute rejection. Post-transplant malignancies vary depending on the type of drug administered before the onset of these diseases. Patients with rheumatoid arthritis (RA) are treated with long-term immunosuppressive medications, such as methotrexate (MTX). MTX is widely recognized as being associated with a specific type of lymphoproliferative disorder (LPD), known as MTX-associated LPD. Our recent report indicated that the clinicopathological features of rheumatoid arthritis-associated lymphoproliferative disorder (RA-LPD) also vary based on the other anti-RA agents used, such as tacrolimus and tumor necrosis factor inhibitors. Therefore, the clinicopathological characteristics of post-transplant LPD and RA-LPD evolve alongside the changes in the immunosuppressants/immunomodulators administered. Understanding the various characteristics and time trends of immunosuppressive neoplasms, particularly LPDs, in relation to different immunosuppressant/immunomodulator medications is highly valuable in clinical practice. Full article

To circumvent the computational bottlenecks associated with the intermediate steps (e.g., least squares fitting) in conventional sine wave similarity principles and directly acquire the energy metrics required for stabilized sinusoidal waveform characterization, this study leverages time domain probability distribution theory. From a complementary advantage perspective, a novel transformer inrush current identification criterion is developed using the Wasserstein distance metric. The methodology employs feature discretization to extract target/template signals, transforming them into state vectors for sample labelling. By quantifying inter-signal energy distribution disparities through this framework, it achieves a precise waveform similarity assessment in sinusoidal regimes. The theoretical analysis and simulations demonstrate that the approach eliminates frequency domain computations while maintaining implementation simplicity. Compared with conventional sine wave similarity methods, the solution streamlines protection logic and significantly enhances practical applicability with accelerated response times. Furthermore, tests conducted on field-recorded circuit breaker closing waveforms using MATLAB R2022a confirm the effectiveness of the proposed method in improving transformer protection performance. Full article

Background: Inflammatory bowel diseases with an early-onset form (EO-IBDs) make up a special disease group with certain clinical and phenotypic characteristics. This article discusses the features of such early onset in a group of children, based on five years of monitoring a registry of children with IBD from a specialized center. Methods: This retrospective single-center cohort study included pediatric patients diagnosed with EO-IBD between 2019 and 2024. Clinical, laboratory, and endoscopic data were collected from medical records, including fecal calprotectin, inflammatory markers, disease activity indices, and endoscopic severity scores. Localization was classified according to the Paris system, and histological activity was assessed using the IBD-DCA score. Results: There were 20 patients with ulcerative colitis (UC) and 17 with Crohn’s disease (CD). Clinical activity was moderate or high (p = 0.179). UC was more characterized by diarrhea and rectal bleeding. CD was more often accompanied by abdominal pain, weight loss, and fever. In total, 82.4% of patients with CD had an inflammatory form. UC-like intestinal lesion was typical of both nosologies—L3 64.7% and E4 60% forms in CD and UC, respectively. Morphological activity was moderate for both nosologies (p = 0.54). IBD-U was present in 43.2% of patients. The median time after which it was possible to diagnose UC was 24 weeks (IQR 20–48) and 40 weeks (IQR 30–45.5) for CD (p = 0.56). Conclusions: Our study confirms the presence of characteristic signs of EO-IBD development, such as a frequent family history of IBD, high or moderate clinical activity during diagnosis verification, colon damage, and a high frequency of extraintestinal manifestations. Full article

Background: Electroencephalography (EEG) systems based on textile electrodes are increasingly being developed to address the need for more wearable sensor systems for brain function monitoring. Blink-related oscillations (BROs) are a new measure of brain function that corresponds to brainwave responses occurring after spontaneous blinking, and indexes neural processes as the brain evaluates new visual information appearing after eye re-opening. Prior studies have reported BRO utility as both a clinical and non-clinical biomarker of cognition, but no study has demonstrated BRO measurement using textile-based EEG devices that facilitate user comfort for real-world applications. Methods: We investigated BRO measurement using a four-channel EEG system with textile electrodes by extracting BRO responses using existing, publicly available EEG data (n = 9). We compared BRO effects derived from textile-based electrodes with those from standard dry Ag/Ag-Cl electrodes collected at the same locations (i.e., Fp1, Fp2, F7, F8) and using the same EEG amplifier. Results: Results showed that BRO effects measured using textile electrodes exhibited similar features in both time and frequency domains compared to dry Ag/Ag-Cl electrodes. Data from both technologies also showed similar performance in artifact removal and signal capture. Conclusions: These findings provide the first demonstration of successful BRO signal capture using four-channel EEG with textile electrodes, providing compelling evidence toward the development of a comfortable and user-friendly EEG technology that uses the simple activity of blinking for objective brain function assessment in a variety of settings. Full article

The vibration and noise of friction pairs are severe when cutting titanium alloy with cemented carbide tools, and the surface micro-texture can significantly reduce noise and friction. Therefore, it is very important to clarify the correlation mechanism between friction noise and friction force for processing quality control. Consequently, investigating the underlying mechanisms that link friction noise and friction is of considerable importance. This study focuses on the friction and wear acoustic signals generated by micro-textured cemented carbide–titanium alloy. A friction testing platform specifically designed for the micro-textured cemented carbide grinding of titanium alloy has been established. Acoustic sensors are employed to capture the acoustic signals, while ultra-depth-of-field microscopy and scanning electron microscopy are utilized for surface analysis. A novel approach utilizing the dung beetle algorithm (DBO) is proposed to optimize the parameters of variational mode decomposition (VMD), which is subsequently combined with wavelet packet threshold denoising (WPT) to enhance the quality of the original signal. Continuous wavelet transform (CWT) is applied for time–frequency analysis, facilitating a discussion on the underlying mechanisms of micro-texture. Additionally, features are extracted from the time domain, frequency domain, wavelet packet, and entropy. The Relief-F algorithm is employed to identify 19 significant features, leading to the development of a hybrid model that integrates Bayesian optimization (BO) and Transformer-LSTM for predicting friction. Experimental results indicate that the model achieves an R² value of 0.9835, a root mean square error (RMSE) of 0.2271, a mean absolute error (MAE) of 0.1880, and a mean bias error (MBE) of 0.1410 on the test dataset. The predictive performance and stability of this model are markedly superior to those of the BO-LSTM, LSTM–Attention, and CNN–LSTM–Attention models. This research presents a robust methodology for predicting friction in the context of friction and wear of cemented carbide–titanium alloys. Full article

In today’s increasingly interconnected digital world, cyber threats have grown in frequency and sophistication, making intrusion detection systems a critical component of modern cybersecurity frameworks. Traditional IDS methods, often based on static signatures and rule-based systems, are no longer sufficient to detect and respond to complex and evolving attacks. To address these challenges, Artificial Intelligence and machine learning have emerged as powerful tools for enhancing the accuracy, adaptability, and automation of IDS solutions. This study presents a novel, hybrid ensemble learning-based intrusion detection framework that integrates deep learning and traditional ML algorithms with explainable artificial intelligence for real-time cybersecurity applications. The proposed model combines an Artificial Neural Network and Support Vector Machine as base classifiers and employs a Random Forest as a meta-classifier to fuse predictions, improving detection performance. Recursive Feature Elimination is utilized for optimal feature selection, while SHapley Additive exPlanations (SHAP) provide both global and local interpretability of the model’s decisions. The framework is deployed using a Flask-based web interface in the Amazon Elastic Compute Cloud environment, capturing live network traffic and offering sub-second inference with visual alerts. Experimental evaluations using the NSL-KDD dataset demonstrate that the ensemble model outperforms individual classifiers, achieving a high accuracy of 99.40%, along with excellent precision, recall, and F1-score metrics. This research not only enhances detection capabilities but also bridges the trust gap in AI-powered security systems through transparency. The solution shows strong potential for application in critical domains such as finance, healthcare, industrial IoT, and government networks, where real-time and interpretable threat detection is vital. Full article