Search Results (2,131)

Software maintenance and release management demand proper identification of bug dependencies since priority violations or unresolved dependent issues can often lead to a chain of failures. However, dependency annotations in bug reports are extremely sparse and imbalanced. These dependencies are often expressed implicitly through natural language descriptions rather than explicit metadata. This creates challenges for automated multilabel dependency classification systems. To tackle these drawbacks, we introduce a meta-contrastive optimization framework (MCOF). This framework integrates established learning paradigms to enhance transformer-based classification through two key mechanisms: (1) a meta-contrastive objective adapted for enhancing discriminative representation learning under few-shot supervision, particularly for rare dependency types, and (2) dependency-aware Laplacian regularization that captures relational structures among different dependency types, reducing confusion between semantically related labels. Experimental evaluation on a real-world dataset demonstrates that MCOF achieves significant improvement over strong baselines, including BM25-based clustering and standard BERT fine-tuning. The framework attains a micro-F1 score of 0.76 and macro-F1 score of 0.58, while reducing hamming loss to 0.14. Label-wise analysis shows significant performance gain on low-frequency dependency types, with improvements of up to 16% in F1 score. Runtime analysis exhibits only modest inference overhead at 15%, confirming that MCOF remains practical for deployment in CI/AT pipelines. These results demonstrate that integrating meta-contrastive learning and structural regularization is an effective approach for robust bug dependency discovery. The framework provides both practical and accurate solutions for supporting real-world software engineering workflows. Full article

Monitoring muscle fatigue is essential to ensure safety and support activity in populations such as the elderly. This study introduces a novel deep learning framework for classifying muscle fatigue levels using data from wireless surface electromyographic sensors, with the long-term goal of supporting applications in Ambient Assisted Living. A new dataset was collected from healthy elderly and non-elderly adults performing dynamic tasks under controlled conditions, with muscle fatigue levels labelled through self-assessment. The proposed method employs a pipeline that transforms one-dimensional electromyographic signals into two-dimensional time–frequency images (scalograms) using the Continuous Wavelet Transform, which are then classified by a fine-tuned, pre-trained Convolutional Neural Network. These images are then classified by pretrained Convolutional Neural Networks on large-scale image datasets. The classification pipeline includes an initial binary discrimination between non-fatigued and fatigued conditions, followed by a refined three-level classification into No Fatigue, Moderate Fatigue, and Hard Fatigue. The system achieved an accuracy of 98.6% in the binary task and 95.6% in the multiclass setting. This integrated transfer learning pipeline outperformed traditional Machine Learning methods based on manually extracted features, which reached a maximum of 92% accuracy. These findings highlight the robustness and generalizability of the proposed approach, supporting its potential as a real-time, non-invasive muscle fatigue monitoring solution tailored to Ambient Assisted Living scenarios. Full article

Micro-expression recognition (MER) is challenged by a brief duration, low intensity, and heterogeneous spatial frequency patterns. This study introduces a novel MER architecture that reduces computational cost by fine-tuning a large feature extraction model with LoRA, while integrating frequency-domain transformation and graph-based temporal modeling to minimize preprocessing requirements. A Spatial Frequency Adaptive (SFA) module decomposes high- and low-frequency information with dynamic weighting to enhance sensitivity to subtle facial texture variations. A Dynamic Graph Attention Temporal (DGAT) network models video frames as a graph, combining Graph Attention Networks and LSTM with frequency-guided attention for temporal feature fusion. Experiments on the SAMM, CASME II, and SMIC datasets demonstrate superior performance over existing methods. On the SAMM 5-class setting, the proposed approach achieves an unweighted F1 score (UF1) of 81.16% and an unweighted average recall (UAR) of 85.37%, outperforming the next best method by 0.96% and 2.27%, respectively. Full article

Multimessenger constraints tightly bound the gravitational-wave speed to be luminal, posing a strong filter for modified gravity. This paper develops a symmetry-selected Palatini framework with torsion in which exact luminality at quadratic order is achieved by construction rather than by parameter tuning. Two ingredients shape the observable sector: (i) a scalar PT projector that keeps scalar densities real and parity-even, and (ii) projective invariance implemented via a non-dynamical Stueckelberg compensator that enters only through its gradient. Under an explicit posture (A1–A6), we establish three structural results: (C1) algebraic uniqueness of torsion to a pure-trace form aligned with the compensator gradient; (C2) bulk equivalence, modulo improvements, among a rank-one determinant route, a closed-metric deformation, and a PT-even CS/Nieh–Yan route; and (C3) a coefficient-locking identity that enforces $K=G$ for tensor modes on admissible domains; hence, $c_T=1$ with two propagating polarizations. Beyond leading order, the framework yields a distinctive, falsifiable next-to-leading correction $\delta c_T^2\left(k\right)=b{k}^2/{\Lambda }^2$ (for $k\ll \Lambda$), predicting slope 2 in log–log fits across frequency bands (PTA/LISA/LVK). The analysis is formulated to be reproducible, with a public repository providing figure generators, coefficients, and tests that directly validate (C1)–(C3). Full article

This study introduces a novel hybrid model for an electromembrane stack, unifying an equivalent electrical circuit model incorporating specific resistance ($R_M,R_s$) and capacitance ($C_{gs},C_{dl}$) parameters with an empirical fouling model in a single framework. The model simplifies the traditional approach by serially connecting N ($N=10$) ion exchange membranes (anionic PC-SA and cationic PC-SK) and is validated using $NaCl$ and $N{a}_{2}S{O}_4$ solutions in comparison with laboratory tests using various voltage signals, including direct current and electrically pulsed reversal operations at frequencies of 2000 and 4000 Hz. The model specifically accounts for the chemical stratification of the cell unit into bulk solution, diffusion, and Stern layers. We also included a calibration method using correction factors (${\alpha }_i$) to fine-tune the electrical current signals induced by voltage stimulation. The empirical component of the model uses experimental data to simulate membrane fouling, ensuring consistency with laboratory-scale desalination processes performed under pulsed reversal operations and achieving a prediction error of less than 10%. In addition, a comparative analysis was used to assess the increase in electrical resistance due to fouling. By integrating electronic and empirical electrochemical data, this hybrid model opens the way to the construction of simple, practical, and reliable models that complement theoretical approaches, signifying an advance for a variety of electromembrane-based technologies. Full article

High frame rate imaging of synthetic aperture radar (SAR), also known as video SAR (ViSAR), has attracted extensive research in recent years. When ViSAR system parameters are fixed, there is a technical trade-off between high frame rates and high resolution. In traditional ViSAR, the frame rate is usually increased by increasing the carrier frequency to increase the azimuth modulation frequency and reducing the synthetic aperture time. This paper attempts to propose a strip non-overlapping mode ViSAR based on Orbital Angular Momentum (OAM) beams, which uses the topological charge of vortex electromagnetic wave (VEW) to improve the azimuth modulation frequency, to improve the frame rate. By introducing the concept of VEW frame splitting, a corresponding time-varying topological charge mode is designed for ViSAR imaging. This design successfully introduces an additional azimuth modulation frequency while maintaining the original imaging resolution, thus significantly improving the frame rate performance of the ViSAR system. However, the Bessel function term in VEW causes amplitude modulation in the echo signal, while the additional frequency modulation causes the traditional matching filter to fail. To address these problems, an improved Range-Doppler algorithm (RDA) is proposed in this paper. By employing the range cell center approximation method, the negative effect of the Bessel function on imaging is reduced effectively. Furthermore, for the introduction of tuning frequency, the azimuth matched filter is specially improved, which effectively prevents the defocusing issues caused by the mismatch of tuning frequency. Finally, the computer simulation results prove that the ViSAR system and imaging algorithm based on VEW can effectively improve the frame rate of ViSAR and maintain the imaging resolution, which provides a research direction for the development of ViSAR technology. Full article

The miniaturization of dielectric sensing has driven the development of both oscillator- and receiver-based sensors. Wide-frequency-range and low-power-consumption voltage-controlled oscillators (VCOs) are required as a reference clock for receiver-based dielectric spectroscopy. In this paper, we propose a switched coupled inductor VCO offering sufficiently wide bandwidth in a power-efficient manner. The proposed switched coupled inductor offers higher coupling factor and mutual inductance compared to direct switched inductor schemes along with a higher quality factor and tuning range. The proposed switched coupled inductor improved the frequency tuning range by 21% compared to the conventional VCO. The measurement results show that the proposed VCO oscillates from 4.7 to 8.8 GHz frequency, suitable for dielectric spectroscopy sensors. With only 4.5 mW power consumption, the proposed VCO can achieve −103.3 dBc/Hz phase noise at 1 MHz offset, with a resulting tuning range figure-of-merit (FOMT) of −187.4 dBc/Hz. Full article

This work presents a notch filter architecture based on a dual-output second-generation voltage conveyor, designed with a current-mode approach. The proposed topology employs a single frequency-selective LC branch and directly uses the two voltage outputs of the DOVCII to generate a notch response without additional active stages. Analytical expressions for the transfer function, notch frequency, and quality factor are derived, highlighting independent control of the passband gain and notch parameters. A sensitivity analysis demonstrates that the notch frequency depends exclusively on the LC product with half-order sensitivities, while the quality factor is predominantly controlled by a single resistor, resulting in predictable tuning and improved tolerance to passive component variations. Transistor-level analysis of the proposed filter was carried out using a standard AMS 0.35 μm CMOS process and has been validated through both circuit-level simulations and experimental measurements using a DOVCII implementation based on the AD844 current-feedback amplifier. Prototypes operating at 100 kHz and 50 Hz notch frequencies have been implemented, the latter employing a current-mode inductance simulator to avoid bulky passive inductors. Full article

Respiratory diseases pose a significant threat to intensive pig farming, and cough recognition serves as a key indicator for early intervention. However, its practical application is constrained by the scarcity of labeled samples and the complex acoustic conditions of farm environments. To address these challenges, this study proposes a lightweight pig cough recognition method based on a pre-trained model. By freezing the backbone of a pre-trained audio neural network and fine-tuning only the classifier, our approach achieves effective knowledge transfer and domain adaptation with very limited data. We further enhance the model’s ability to capture temporal–spectral features of coughs through a time–frequency dual-stream module. On a dataset consisting of 107 cough events and 590 environmental noise clips, the proposed method achieved an accuracy of 94.59% and an F1-score of 92.86%, significantly outperforming several traditional machine learning and deep learning baseline models. Ablation studies validated the effectiveness of each component, with the model attaining a mean accuracy of 96.99% in cross-validation and demonstrating good calibration. The results indicate that our framework can achieve high-accuracy and well-generalized pig cough recognition under small-sample conditions. The main contribution of this work lies in proposing a lightweight fine-tuning paradigm for small-sample audio recognition in agricultural settings, offering a reliable technical solution for early warning of respiratory diseases on farms. It also highlights the potential of transfer learning in resource-limited scenarios. Full article

The escalating threat of wildfires under global climate change necessitates rigorous monitoring to mitigate environmental and socio-economic risks. Burned area (BA) mapping is crucial for understanding fire dynamics, assessing ecosystem impacts, and supporting sustainable land management under increasing fire frequency. This study aims to develop a high-resolution detection framework specifically calibrated for Mediterranean environmental conditions, ensuring the production of consistent and accurate annual BA maps. Using Sentinel-2 MSI time series over Sardinia (Italy), the research objectives were to: (i) integrate field surveys with high-resolution photointerpretation to build a robust, locally tuned training dataset; (ii) evaluate the discriminative power of multi-temporal spectral indices; and (iii) implement a Random Forest classifier capable of providing higher spatial precision than current operational products. Validation results show a Dice Coefficient (DC) of 91.8%, significantly outperforming the EFFIS Burnt Area product (DC = 79.9%). The approach proved particularly effective in detecting small and rapidly recovering fires, often underrepresented in existing datasets. While inaccuracies persist due to cloud cover and landscape heterogeneity, this study demonstrates the effectiveness of a machine learning approach for long-term monitoring, for generating multi-year wildfire inventories, offering a vital tool for data-driven forest policy, vegetation recovery assessment and land-use change analysis in fire-prone regions. Full article

In the framework of the traditional active disturbance rejection controller (ADRC), the state error feedback utilizes estimated values from the extended state observer, which may introduce phase lag. Therefore, academic researchers have proposed a modified version called the improved linear ADRC that employs output values from the plant for state error feedback except the output value from the extended state observer. However, there is limited literature exploring the relationship between traditional linear ADRC and improved linear ADRC. To address this gap, this article establishes mathmatical relationship between traditional linear ADRC and improved linear ADRC from the generalized PID control perspective, highlighting their distinctions in the frequency domain. Compared to the traditional ADRC, the improved ADRC incorporates differential terms and offers a novel approach to realize the generalized PID control via generalized PID interpretation. And to be more specific, the improved ADRC is a new way to realize the generalized PID control by three tuned parameters, and the number of parameters of the improved ADRC is fewer than that of the generalized PID control. From the time domain, numerical simulation results demonstrate that improved ADRC exhibits superior control performance by eliminating overshoot during set value tracking processes compared to the traditional ADRC. From the disturbance rejection simulations in direct current to direct current converter (DCDC), the improved ADRC can achieve better disturbance rejection performance than the traditional ADRC. The DC bus voltage drop values of the traditional ADRC are 55.8 V and 32 V; thus, the biggest voltage drop is 55.8 V, which is 7.44 times the the improved ADRC. The voltage rise of improved ADRC can be neglected compared to the voltage rise of the traditional ADRC. From the tracking performance perspective, the time to fully reach the reference value of the traditional ADRC is about 0.3 s, and the time to fully reach the reference value of the improved ADRC is about 0.15 s. Full article

This paper explores the potential of amorphous and nanocrystalline glass-coated microwires as highly versatile, miniaturized sensing elements, leveraging their intrinsic nonlinear magnetization dynamics. In magnetic systems, this approach is particularly advantageous because the degree of nonlinearity can be externally tuned using stimuli such as applied magnetic fields, mechanical stress, or temperature variations. From this context, we summarize key properties of microwires—including bistability, a specific easy magnetization direction, internal stress distributions, and magnetostriction—that can be tailored through composition and annealing. In this review, we compare for the first time two key contactless readout methodologies: (i) time-domain detection of the switching field and (ii) frequency-domain harmonic analysis of the induced voltage. These principles have been successfully applied to a broad range of practical sensors, including devices for monitoring mechanical stress in structural materials, measuring temperature in biomedical settings, and detecting magnetic particles. Together, these advances highlight the potential of microwires for embedded, wireless sensing in both engineering and medical applications. Full article

The analysis of ground-penetrating radar data generally relies on the visual identification of structures on selected profiles and their interpretation in terms of buried features. In simple cases, inverse modelling of the acquired data set can facilitate interpretation and reduce subjectivity. These methods suffer from severe restrictions due to antenna resolution limits, which prevent the identification of tiny structures, particularly in forensic, stratigraphic, and engineering applications. Here, we describe a technique to obtain a high-resolution characterization of the underground, based on the forward modelling of individual traces (A-scans) of selected radar profiles. The model traces are built by superposition of Ricker wavelets with different polarities, amplitudes, and arrival times and are used to create reflectivity diagrams that plot reflection amplitudes and polarities versus depth. A thin bed is defined as a layer of higher or lower permittivity relative to the surrounding material, such that the top and bottom reflections are subject to constructive interference, determining the formation of an anomalous peak in the trace (tuning effect). The proposed method allows the detection of ultra-thin layers, well beyond the Rayleigh vertical resolution of GPR antennas. This approach requires a preliminary estimation of the instrumental uncertainty of common monostatic antennas and takes into account the frequency-dependent attenuation, which causes a spectral shift of the dominant frequency acquired by the receiver antenna. Such a quantitative approach to analyzing radar data can be used in several applications, notably in stratigraphic, forensic, paleontological, civil engineering, heritage protection, and soil stratigraphy applications. Full article

The ultrasonic guided wave method is successfully used for structural health monitoring (SHM) of aircraft structures utilizing PZT (Pb-Zr-Ti based piezoceramic material) sensors for guided wave generation and detection. To increase the mechanical durability of the sensors in operational conditions, this paper demonstrates the feasibility of the integration of PZTs into the Glass fiber/Polymethyl methacrylate (G/PMMA) composite plate and evaluates the possibility of impact damage detection using generated guided waves. Two types of PZT sensors were embedded into different layers during the manufacturing process. Generally, radial mode disc sensors are used for Lamb wave generation, and thickness-shear square-shaped sensors are used for both Lamb and shear wave generation. First, the wave propagation was analyzed considering the sensor type and sensor placement within the layup. The main objective was to propose the optimal sensor network with embedded sensors for successful impact damage detection. Lamb wave frequency tuning of disk sensors and unique vibrational characteristics of integrated shear sensors were exploited to selectively actuate only one guided wave mode. Finally, the Reconstruction Algorithm for the Probabilistic Inspection of Damage (RAPID) was utilized for damage localization and visualization. Full article

This study presents a comprehensive performance analysis of four different control strategies, Proportional–Integral (PI), classical Sliding Mode Control (SMC), Super-Twisting SMC (ST-SMC), and Exponential Reaching Law SMC (ERL-SMC), applied to the speed regulation of a Hall-effect sensored Brushless DC (BLDC) motor. A mathematically detailed BLDC motor model, three-phase inverter structure with safe commutation logic, and a high-frequency PWM switching scheme were implemented in the MATLAB/Simulink-2024a environment to provide a realistic simulation framework. The control strategies were evaluated under multiple test scenarios, including variations in supply voltage, mechanical load disturbances, reference speed transitions, and steady-state operation. The comparative results reveal that the classical SMC and PI controllers suffer from significant oscillations, overshoot, and limited disturbance rejection capability, especially during voltage and load transients. The ST-SMC algorithm improves robustness and reduces the chattering effect inherent to first-order SMC but still exhibits noticeable oscillations near the sliding surface. In contrast, the proposed ERL-SMC controller demonstrates superior performance across all scenarios, achieving the lowest steady-state ripple, the shortest settling time, and the most stable transition response while significantly mitigating chattering. These results indicate that ERL-SMC is the most effective and reliable control strategy among the evaluated methods for BLDC speed regulation, which requires high dynamic response and disturbance robustness. The findings of this study contribute to the advancement of SMC-based BLDC motor control, providing a solid foundation for future research that integrates observer-based schemes, adaptive tuning, or real-time hardware implementation. Full article