Search Results (1,545)

With the development of scientific machine learning (SciML), the proposal of physics-informed neural networks (PINNs) has provided a powerful paradigm for solving partial differential equations (PDEs). While PINNs perform well in solving high-dimensional PDEs, they perform worse than traditional numerical methods for low-dimensional problems. This discrepancy arose from potential convergence conflicts induced by distinct physical magnitude of loss terms. To decouple the convergence conflicts, we propose a partial derivative guided multi-branch physics-informed neural network (PDGM-PINN). Inspired by SciML, we treat both the solution and partial derivatives as dependent variables to be predicted. The partial derivatives are directly predicted by sub-branches, while the main branch approximates the PDE solution, and all branches share error backpropagation information. Furthermore, we redesign the loss function. The loss of the governing equation is computed with the solution and partial derivatives predicted by the main and sub-branches. Schwarz’s theorem and Kullback–Leibler divergence are incorporated into the loss terms as soft constraints of partial derivatives continuity and residual distributions consistency for the governing equations. We conducted comprehensive experimental evaluations on seven PDEs, and ablation experiments, sensitivity analyses, and complexity analyses were carried out to investigate the rationality of PDGM-PINN. The results demonstrate that PDGM-PINN achieves the best performance among PINN variants with the fewest trainable parameters, effectively avoiding architectural redundancy. Full article

The synergistic control of multiple pollutants is critically challenged by complex nonlinear interactions, strong spatiotemporal heterogeneity, and the difficulty of tracing causal drivers. Deep learning offers high predictive power but suffers from the “black-box” problem, limiting its acceptance in environmental decision-making. Explainable Deep Learning (XDL) integrates physical mechanisms with interpretable algorithms, achieving both prediction accuracy and explanatory transparency. This review systematically evaluates the effectiveness and limitations of XDL in analyzing multi-pollutant interactions, with a comparative focus on atmospheric and aquatic environments. Key techniques, including SHAP, attention mechanisms, and physics-informed neural networks, are examined for their roles in synergistic monitoring, source apportionment, and regulatory optimization. The main findings reveal that: (1) XDL, particularly the “tree model + SHAP” paradigm, has become a dominant tool for quantifying driving factors, yet most attributions remain correlational rather than causal; (2) physics-informed fusion (soft vs. hard constraints) improves physical consistency but faces unresolved conflicts between data and physical laws, with current models lacking a conflict detection mechanism; (3) cross-media comparison shows a unified technical logic of “physical mechanism guidance + post hoc feature attribution”, but atmospheric applications lead in embedding advection–diffusion constraints, while aquatic research excels in spatial topology modeling via graph neural networks; (4) critical bottlenecks include the lack of causal inference, uncertainty-unaware interpretations, and data scarcity. Future directions demand a shift from correlation-only to causal-aware attribution, from blind fusion to conflict-detecting systems, and from no evaluation standards to domain-specific validation benchmarks. XDL is poised to transform multi-pollutant governance from experience-driven to intelligence-driven approaches, provided that verifiable interpretability and physical consistency become core design principles. Full article

The aviation industry is increasingly prioritizing sustainability, with significant focus on the development of Hybrid-Electric Aircraft (HEA). By integrating electric motors with conventional combustion engines, HEA systems offer substantial environmental benefits and operational efficiency improvements. However, the successful implementation of HEA technologies is contingent upon advancements in power converter systems. This paper addresses the critical need for sustainable aviation solutions by examining the challenges and opportunities associated with High-Efficiency Aviation Power (HEAP) technology. Specifically, the study investigates the role of power converters in Hybrid-Electric Aircraft Propulsion systems, with a particular emphasis on addressing key concerns such as weight reduction, compact design, and system reliability. A comparative analysis of three converter topologies is conducted: two established configurations serve as baseline references, while a third topology, a modular, fault-tolerant DC-DC converter, is proposed for the first time in the context of hybrid-electric aircraft. Its novelty lies in the system-level use of redundancy to offer an inherent architectural advantage against cosmic-ray-induced failures a critical aviation reliability challenge that existing converter topologies do not address through hardware redundancy. This qualitative reliability advantage is presented as an architectural feature, pending quantitative validation through future hardware testing and mean-time-between-failures (MTBF) analysis. This exploration is essential for identifying the most suitable configuration for HEA integration, with the goal of overcoming challenges related to lightweight design, high efficiency, and reliability. The findings contribute to the advancement of more sustainable and efficient aviation solutions by demonstrating the potential of the proposed converter architecture. Full article

Classifying power quality disturbances (PQDs) under strong noise conditions remains challenging for existing deep learning models. These models typically separate denoising from feature extraction, often rely on attention mechanisms that operate along only a single dimension, and tend to achieve high accuracy at the cost of high complexity, which limits their performance under low signal-to-noise ratio conditions and hinders practical deployment. To address these limitations, this paper proposes AD-PDAF-Net, which organically integrates three key mechanisms through a co-design strategy. Unlike conventional methods that depend on preprocessing, an adaptive soft thresholding denoising layer is embedded into a lightweight residual network to progressively suppress noise during feature extraction, thereby unifying denoising with feature learning. A parallel dual attention module independently refines features along the channel and temporal dimensions, then adaptively fuses them using learnable weights to capture both frequency domain and temporal characteristics of disturbances. The lightweight network entry replaces aggressive downsampling with small convolutions to preserve transient details, and a bidirectional long short-term memory network (BiLSTM) efficiently captures temporal dependencies. Evaluated on a dataset of 25 disturbance categories defined in IEEE Std 1159-2019, the model achieves a classification accuracy of 97.26% and a Kappa coefficient of 97.02% under 20 dB white Gaussian noise, along with an accuracy of 98.78% under mixed noise conditions. The model has only 0.36 million parameters and a computational cost of just 1.50 GFLOPS. Through this co-design, AD-PDAF-Net achieves both high noise robustness and high classification accuracy with minimal computational overhead, offering an effective solution for time series signal recognition in resource constrained environments. Full article

Educational robotics (ER) and robotics competitions offer an effective context for developing STEM (Science, Technology, Engineering, and Mathematics) competencies, technical skills, and soft skills in engineering degrees. However, current platforms reveal a pedagogical and technical gap: closed commercial systems restrict access to hardware, while open solutions frequently lack a robust and structured architecture for educational settings. Moreover, in both cases, many platforms do not achieve the hardware requirements of the most demanding competitions. To address this issue, the present article presents the design, implementation, and validation of EASYbot, a modular open-hardware robotics platform based on Arduino. The system integrates a microcontroller, a dual USB–battery power supply, high-performance motor power stages, and a plug-and-play interface for input/output and communication peripherals, enabling its use in several competition categories such as mini-sumo or maze robots. The platform is complemented by a state-based programming model and supports libraries that facilitate a learning assessment. The platform provides a scalable ecosystem, enabling students to progress from initial prototyping to optimised hardware control. The validation process encompasses a range of assessments, including technical tests, usability, and adoption evaluation through surveys. Full article

Respiratory rate (RR) is a critical indicator of physiological status, yet unobtrusive and continuous RR monitoring remains challenging, particularly in wearable applications that require soft, lightweight, and low-power sensing systems. This paper presents an integrated approach that combines a textile-embedded embroidered strain-gauge sensor with Tiny Machine Learning (TinyML) to enable real-time, on-device RR estimation. The sensing platform consists of a textile-integrated meander-pattern strain gauge and a fabric-mounted analog readout circuit, which together capture thoracic expansion during breathing. Two lightweight neural network models—a convolutional neural network (CNN) operating on raw respiratory waveforms and a dense neural network (DNN) operating on wavelet features—were developed and trained using a public strain-sensor dataset and a custom dataset collected with the textile system (TexHype dataset). Both models were optimized through 8-bit quantization and deployed to an STM32L4 microcontroller, where end-to-end on-device preprocessing, filtering, segmentation, normalization, and inference were performed. The CNN achieved the highest accuracy, with a mean absolute error (MAE) of 1.23 breaths per minute (BPM) on the TexHype dataset, but exhibited substantial inference latency (5.8–6.2 s) due to its computational complexity. In contrast, the wavelet-based DNN demonstrated lower accuracy (MAE 2.21 BPM) but achieved real-time performance with inference times of 18–96 ms, and a power overhead ($\Delta P=P_{\mathrm{active}}-P_{\mathrm{idle}}$) of approximately 3.3 mW during inference. Cross-dataset testing revealed limited generalization between different strain-sensor platforms. The findings highlight key trade-offs between accuracy, latency, and energy efficiency, and illustrate the potential of combining stretchable electronics with embedded intelligence to enable next-generation wearable respiratory monitoring systems. Full article

Ankle dorsiflexion range of motion (ADF-ROM) deficits has been linked to impaired function, altered gait, and injury risk. This study’s objective was to examine the acute effects of static self-stretching (SSS), foam rolling (FR), and instrument-assisted soft tissue mobilization (IASTM) of the posterior lower-leg on ADF-ROM and functional ankle outcomes in individuals with ADF-ROM deficits. Thirteen healthy, physically active college students with active ADF-ROM ≤ 13°, assessed in a non-weight-bearing position, completed all three interventions in a randomized, within-subject repeated-measures design. Pre- and post-intervention assessments included ADF-ROM, ankle plantar flexor isometric strength (APF-IS), single-leg countermovement vertical jump (SLCVJ), anterior reach distance in the Y-Balance Test (A-YBT), and gait parameters (contact time and plantar pressure). A two-way repeated-measures ANOVA with Bonferroni post hoc tests was used. Effect sizes reported as partial eta squared (${\eta }_p^2$) and Cohen $d_{\mathrm{z}}$. All interventions significantly improved ADF-ROM (p < 0.001; ${\eta }_p^2$ = 0.885), with IASTM showing the largest increase (50.7%, $d_{\mathrm{z}}$= 2.15), followed by FR (35.4%, $d_{\mathrm{z}}$ = 2.20) and SSS (21.5%, $d_{\mathrm{z}}$ = 1.82). Differences between IASTM and FR (p > 0.05, $d_{\mathrm{z}}$ = 0.40) and between FR and SSS (p > 0.05, $d_{\mathrm{z}}$ = 0.69) were nonsignificant, while IASTM was significantly greater than SSS (p < 0.05, $d_{\mathrm{z}}$ = 0.92). Significant gains were also seen in A-YBT (p < 0.05; ${\eta }_p^2$ = 0.302) and rearfoot plantar pressure (p < 0.01; ${\eta }_p^2$ = 0.482), although pairwise comparisons were nonsignificant and demonstrated small-to-moderate effect sizes ($d_{\mathrm{z}}$ = 0.35–0.52). No significant changes occurred in APF-IS, SLCVJ, or contact time and mid- and forefoot plantar pressures during roll-off. In conclusion, all interventions improved ADF-ROM, with IASTM and FR being comparably effective. However, only slight improvements in dynamic balance and certain gait parameters were noted, with no effect on strength or power. Full article

Canestrato di Castel del Monte (CCM) is a traditional sheep cheese from the Abruzzo region of Italy, strongly linked to local pastoral practices and characterized by high cultural and commercial value. Ensuring its authenticity is therefore essential to protect both producers and consumers. In this study, Attenuated Total Reflectance Fourier Transform Infrared (ATR-FTIR) spectroscopy combined with chemometric modelling was investigated for the classification of traditional sheep cheeses. A dataset of approximately 2000 spectra obtained from Canestrato di Castel del Monte (CCM), low-ripening CCM, and Pecorino Toscano was analyzed using different modelling strategies. Partial Least Squares Discriminant Analysis (PLS-DA) and Sequential Preprocessing through Orthogonalization combined with Linear Discriminant Analysis (SPORT-LDA) were first applied to simultaneously separate the three categories. Subsequently, a class-modelling approach based on Soft Independent Modelling of Class Analogy (SIMCA) was used to authenticate CCM and low-ripening cheeses. The discriminant models achieved excellent classification performance: accuracies close to 100% for CCM and low-ripening CCM and around 95% for Pecorino Toscano. SIMCA provided reliable rejection of non-target samples, although with lower sensitivity compared to discriminant approaches. Overall, the results demonstrate that ATR-FTIR spectroscopy coupled with appropriate chemometric modelling represents a powerful strategy for the authentication and classification of traditional sheep cheeses. Full article

This review focuses on electromagnetic imaging methods widely used in urban geophysics and civil engineering. The rapid growth of the urban population and the increase in the frequency of extreme events related to climate change make novel approaches to the geophysical monitoring of urban areas and civil infrastructures essential in the context of programs for the sustainability and resilience of cities. In this scenario, there is a growing interest in using ground-based electromagnetic methods to investigate strategic infrastructures such as bridges, tunnels, dam embankments, power plants, energy plants and pipelines in a non-invasive way. The development of cost-effective, user-friendly sensor arrays, robust methodologies for tomographic data inversion, and AI-based and machine learning techniques has rapidly transformed these methods. This review critically analyzes the results relating to the application of ground-based electromagnetic methods in infrastructure monitoring and surveillance over the past 20 years by presenting a selection of best practice examples and studies planned to support programs for the resilience and maintenance of engineering infrastructures. The analysis reveals that these methods are highly effective in addressing a broad spectrum of monitoring issues in view of effective maintenance of civil infrastructures. In fact, these methods are essential for detecting the geometry of buried objects (e.g., bars and voids), enabling the early detection of degradation phenomena, and mapping water infiltration processes inside structures, as well as many other challenging applications. Finally, prospectives for development are identified in terms of using soft robot technologies, miniaturized sensors, and AI-based methods to acquire, process and interpret data as well as to design smart operational guidelines for infrastructure management. Full article

The large-scale integration of distributed energy resources poses numerous challenges to distribution networks. At present, multi-terminal flexible interconnection has become a key development trend for active distribution networks integrated with high-penetration distributed energy resources. Conventional unified power flow controllers (UPFCs) are mainly designed for high-voltage transmission networks and lack distribution-adapted control strategies, making it difficult for them to meet the networking requirements for multi-terminal interconnection. Moreover, most existing studies still focus on two-terminal devices, soft open points and improved UPFC topologies for transmission networks. Existing multi-port schemes mostly adopt only shunt-side structures without series compensation branches, which fail to regulate voltage magnitude and phase difference, thus failing to suppress closing inrush currents and mitigate busbar voltage sags. Meanwhile, such schemes struggle with three-phase imbalance, feeder load imbalance and bidirectional power flow fluctuations in distribution networks, and lack adaptive power allocation capability among multiple ports. To solve the above problems, this paper proposes a VSC-based series–shunt hybrid multi-terminal flexible interconnection converter. The proposed topology consists of one series-side VSC and n − 1 shunt-side VSCs connected through a common DC capacitor; it removes the shunt-side transformer, and effectively reduces cost and volume, while achieving phase shifting, voltage regulation and power flow control. Meanwhile, dual closed-loop PI cross-decoupling control and a flexible closing strategy are adopted to independently regulate the active and reactive power of each feeder, adapt to three-phase imbalance and load imbalance conditions, suppress inrush currents, and realize flexible power mutual support among multiple ports, thereby significantly enhancing adaptability to distribution networks. Full article

This study investigates the “soft-kill” mechanism of unmanned aerial vehicles (UAVs) under high-power electromagnetic pulse (EMP) exposure. Unlike previous research focused on hardware destruction, we identify flight control paralysis caused by Pulse Width Modulation (PWM) signal logic threshold violation as the primary failure mode. To resolve discrepancies between theory and experiment, a 1 × 1 m loop antenna model was implemented in CST Studio Suite. Results demonstrate that EMP coupling in drone arm wiring predominantly generates differential mode (DM) noise. This explains why conventional ferrite beads fail while full-body shielding remains effective. Our findings provide a theoretical basis for low-power anti-drone system optimization and hardened UAV design guides. Full article

Wireless sensor networks using battery-powered, low-cost sensors, due to their non-rechargeability and strictly limited energy resources, are more sensitive to energy efficiency than other networks of this type. Clustered wireless sensor networks address this problem. In these networks, the most energy-intensive communication, i.e., a long-range one, is carried out via designated nodes, called cluster head nodes, while other cluster nodes communicate with their cluster heads. Cluster head node selection is handled by appropriate routing protocols, and newly designed protocols are first tested in simulations. Among the simulators of cluster head selection protocols, those implemented in a MATLAB environment play an important role, and among these, those implementing a first-order radio model to estimate the energy cost of transmission, both at the transmitter and at the receiver, play a particularly important role. This paper presents and discusses the energy aspects of MATLAB-based open-source wireless sensor network environments that employ the first-order radio model for the simulation of cluster head selection protocols. Current MATLAB-based open-source simulators of cluster head selection protocols were inventoried and analyzed. The review results showed that the first-order radio model had been used in its classic form for years, with the same default parameters. Although the simulators were written using different programming paradigms, precluding simple copy-and-paste, the first-order radio model was generally similar. However, there were exceptions to this rule. A hard exception is the simulator for a body-area wireless sensor network, which only implements a version of the first-order radio model specific to that environment. Soft exceptions are two simulators of the popular cluster head selection protocol, which implemented only half the functionality of the classic first-order radio model. On the one hand, this demonstrates both the widespread use of a conservative approach to the model, which ensures relatively easy repeatability of simulation results, and, on the other hand, the flexibility of the model, which allows its extension to other environments. Finally, the limitations of the model are presented and directions for future research are indicated. Full article

Traditional intrusion detection systems for IoT networks achieve high classification accuracy but lack interpretability and actionable incident-response capabilities, limiting their operational value in security-critical environments. This paper presents a graph-based multi-agent framework that integrates ensemble machine learning with Large Language Model (LLM)-powered incident report generation via Retrieval-Augmented Generation (RAG). The system employs a three-phase architecture: (1) a lightweight Random Forest binary pre-detection, achieving 99.49% accuracy with a 6 MB model size for edge deployment; (2) ensemble classification combining Multi-Layer Perceptron, Random Forest, and XGBoost with soft voting and SHAP-based feature attribution for explainability; and (3) a ReAct-based summary agent that synthesizes classification results with external threat intelligence from Web search and scholarly databases to generate evidence-grounded incident reports. To address the challenge of evaluating non-deterministic LLM outputs, we introduce custom RAG evaluation metrics—faithfulness and groundedness implemented via the LLM-as-Judge framework. Experimental validation on the ACI IoT Network Dataset 2023 demonstrates ensemble accuracy exceeding 99.8% across 11 attack classes; perfect groundedness scores (1.0), indicating all generated claims derive from the retrieved context; and moderate faithfulness (0.64), reflecting appropriate analytical synthesis. The ensemble approach mitigates individual model weaknesses, improving the UDP Flood F1 score from 48% (MLP alone) to 95% through soft voting. This work bridges the gap between high-accuracy detection and trustworthy, actionable security analysis for automated incident-response systems. Full article

The capacitance of the DC link is an important variable for the prediction of remaining useful life and failures in frequency inverters. The direct measurement of the DC-link capacitance in inverters operating under load is technically challenging and generally impractical. Recently, a great focus has been given to data-based soft sensors for estimating this variable. These methods, however, are evaluated based only on the estimate errors, and do not take into account the metrological aspects of these estimators. This paper proposes an uncertainty analysis method based on Monte Carlo simulations and bootstrapping that can be applied to all recently published methods for end-of-life (EOL) estimation based on data-driven regression and neural networks. A state-of-the-art model of EOL monitoring based on capacitance estimation was evaluated using the proposed framework, and an experimental study with a frequency converter drive for a brushless DC motor was performed, considering multiple output frequencies, loads and DC-link capacitance conditions. The output distributions are not symmetrical and show that the variable with the most significant impact in the propagated uncertainty is the DC link voltage. The results show confidence interval widths ranging from 12 μF to 61 μF, with wider confidence intervals obtained at higher power setpoints. Full article

Rapid increases in distributed photovoltaic (PV) penetration have brought additional challenges to distribution network planning and operation. Meanwhile, flexible interconnection devices such as soft open point integrated with battery energy storage system (E-SOP) can significantly enhance the regulatory capability and operational adaptability of the distribution system and have been widely applied in recent years. First, to improve both economic performance and voltage quality, a coordinated planning method for the multi-region flexible interconnected distribution system based on E-SOP is proposed. Second, with the ongoing growth of interconnected distribution networks, centralized optimization methods exhibit limitations in computational efficiency and privacy protection. To address this, the planning model is decomposed into several subproblems by applying the Alternating Direction Method of Multipliers (ADMM), allowing each region to optimize its local subproblem in a fully distributed manner. Additionally, a Shapley value-based cost allocation mechanism is applied to ensure fair and rational cost distribution among different distribution networks. Finally, case studies are conducted to validate the effectiveness of the proposed method. Case studies show that the proposed method reduces the system’s total annual cost by 14.90% and the electricity purchase cost by 28.61% compared with the pre-planning case. Meanwhile, the maximum voltage imbalance is reduced to within the standard range. These results validate the effectiveness of the proposed method in enhancing both economic efficiency and power quality for flexible interconnected distribution systems. Full article