Search Results (33,712)

Graphs are widely used to model complex interactions among entities, yet they struggle to capture higher-order and multi-typed relationships. Hypergraphs overcome this limitation by allowing for edges to connect arbitrary sets of nodes, enabling richer modelling of higher-order semantics. Real-world systems, however, often exhibit heterogeneity in both entities and relations, motivating the need for heterogeneous hypergraphs as a more expressive structure. In this study, we address the problem of local clustering on heterogeneous hypergraphs, where the goal is to identify a semantically meaningful cluster around a given seed node while accounting for type diversity. Existing methods typically ignore node-type information, resulting in clusters with poor semantic coherence. To overcome this, we propose HHLC, a heuristic heterogeneous hyperedge-based local clustering algorithm, guided by a heterogeneity-aware conductance measure that integrates structural connectivity and node-type consistency. HHLC employs type-filtered expansion, cross-type penalties, and low-quality hyperedge pruning to produce interpretable and compact clusters. Comprehensive experiments on synthetic and real-world heterogeneous datasets demonstrate that HHLC consistently outperforms strong baselines across metrics such as conductance, semantic purity, and type diversity. These results highlight the importance of incorporating heterogeneity into hypergraph algorithms and position HHLC as a robust framework for semantically grounded local analysis in complex multi-relational networks. Full article

Infrared thermal field (ITF) prediction for meter boxes is crucial for the early warning of power system faults, yet this method faces three major challenges: data sparsity, complex geometry, and resource constraints in edge computing. Existing physics-informed neural network-graph neural network (PINN-GNN) approaches suffer from redundant physics residual calculations (over 70% of flat regions contain little information) and poor model generalization (requiring retraining for new box types), making them inefficient for deployment on edge devices. This paper proposes the PhysGraphIR framework, which employs an Adaptive Residual Sampling (ARS) mechanism to dynamically identify hotspot region nodes through a physics-aware gating network, calculating physics residuals only at critical nodes to reduce computational overhead by over 80%. In this study, a `hotspot region’ is explicitly defined as a localized area exhibiting significant temperature elevation relative to the background—typically concentrated around electrical connection terminals or wire entrances—which is critical for identifying potential thermal faults under sparse data conditions. Additionally, it utilizes a Physics Knowledge Distillation Graph Neural Network (Physics-KD GNN) to decouple physics learning from geometric learning, transferring universal heat conduction knowledge to specific meter box geometries through a teacher–student architecture. Experimental results demonstrate that on both synthetic and real-world meter box datasets, PhysGraphIR achieves a hotspot region mean absolute error (MAE) of 11.8 °C under 60% infrared data missing conditions, representing a 22% improvement over traditional PINN-GNN. The training speed is accelerated by 3.1 times, requiring only five infrared samples to adapt to new box types. The experiments prove that this method significantly enhances prediction accuracy and computational efficiency under sparse infrared data while maintaining physical consistency, providing a feasible solution for edge intelligence in power systems. Full article

Artificial neural networks (ANNs) are widely used in engineering prediction, but excessive input dimensionality can reduce both accuracy and efficiency. This study proposes a two-stage feature-reduction framework, Feature Importance Ranking and Redundancy Elimination (FIRRE), to optimize ANN inputs by removing weakly informative and redundant variables. In Stage 1, four complementary ranking methods, namely Pearson correlation, recursive feature elimination, random forest importance, and F-test scoring, are combined into an ensemble importance score. In Stage 2, highly collinear features (ρ > 0.95) are pruned while retaining the more informative variable in each pair. FIRRE is evaluated on 32 civil engineering datasets spanning materials, structural, and environmental applications, and benchmarked against Principal Component Analysis, variance-threshold filtering, random feature selection, and K-means clustering. Across the benchmark suite, FIRRE consistently achieves competitive or improved predictive performance while reducing input dimensionality by 40% on average and decreasing computation time by 10–60%. A dynamic modulus case study further demonstrates its practical value, improving R² from 0.926 to 0.966 while reducing inputs from 25 to 7. Overall, FIRRE provides a practical, robust framework for simplifying ANN inputs and improving efficiency in civil engineering prediction tasks. 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

With the explosive growth in the quantity of electrical equipment in distribution networks, traditional manual inspection struggles to achieve comprehensive coverage due to limited manpower and low efficiency. This has led to frequent equipment failures including partial discharge, insulation aging, and poor contact. These issues seriously compromise the safe and stable operation of distribution networks. Real-time monitoring and defect identification of their operation status are critical to ensuring the safety and stability of power systems. Currently, commonly used methods for defect identification in distribution network electrical equipment mainly rely on single-image or voiceprint data features. These methods lack consideration of the complementarity and interleaved nature between image and voiceprint features, resulting in reduced identification accuracy and reliability. To address the limitations of existing methods, this paper proposes distribution network electrical equipment defect identification based on multi-modal image voiceprint data fusion and channel interleaving. First, image and voiceprint feature models are constructed using two-dimensional principal component analysis (2DPCA) and the Mel scale, respectively. Multi-modal feature fusion is achieved using an improved transformer model that integrates intra-domain self-attention units and an inter-domain cross-attention mechanism. Second, an image and voiceprint multi-channel interleaving model is applied. It combines channel adaptability and confidence to dynamically adjust weights and generates defect identification results using a weighting approach based on output probability information content. Finally, simulation results show that, under the dataset size of 3300 samples, the proposed algorithm achieves a 8.96–33.27% improvement in defect recognition accuracy compared with baseline algorithms, and maintains an accuracy of over 86.5% even under 20% random noise interference by using improved transformer and multi-channel interleaving mechanism, verifying its advantages in accuracy and noise robustness. Full article

Sub-meter-resolution Polarimetric Synthetic Aperture Radar (PolSAR) imagery enables precise building footprint extraction but introduces complex scattering correlated with fine spatial structures. This change renders both traditional methods, which rely on simplified scattering models, and existing deep learning approaches, which sacrifice spatial detail through multi-looking, inadequate for high-precision extraction tasks. To address this, we propose an Orthogonal Dual-Resolution Network (ODRNet) for end-to-end, precise segmentation directly from single-look complex (SLC) data. Unlike complex-valued neural networks that suffer from high computational cost and optimization difficulties, our approach decomposes complex-valued data into its orthogonal real and imaginary components, which are then concurrently fed into a Dual-Resolution Branch (DRB) with Bilateral Information Fusion (BIF) to effectively balance the trade-off between semantic and spatial details. Crucially, we introduce an auxiliary Polarization Orientation Angle (POA) regression task to enforce physical consistency between the orthogonal branches. To tackle the challenge of diverse building scales, we designed a Multi-scale Aggregation Pyramid Pooling Module (MAPPM) to enhance contextual awareness and a Pixel-attention Fusion (PAF) module to adaptively fuse dual-branch features. Furthermore, we have constructed a VHR PolSAR building footprint segmentation dataset to support related research. Experimental results demonstrate that ODRNet achieves 64.3% IoU and 78.27% F1-score on our dataset, and 73.61% IoU with 84.8% F1-score on a large-scale SLC scene, confirming the method’s significant potential and effectiveness in high-precision building extraction directly from SLC. Full article

With the rapid development of the Internet of Things (IOT), 5G, and modern power systems, demand-side loads are becoming increasingly observable and remotely controllable, which enables demand-side flexibility to participate more actively in grid dispatch and emergency support. Under extreme rainstorm conditions, however, component failure risk rises and the availability and dispatchability of demand-side flexibility can change rapidly. This paper proposes a risk-aware emergency regulation framework that translates rainstorm information into actionable multi-load aggregation decisions for urban power systems. First, demand-side resources are quantified using four response attributes, including response speed, response capacity, maximum response duration, and response reliability, to enable a consistent characterization of heterogeneous flexibility. Second, a backpropagation (BP) neural network is trained on long-term real-world meteorological observations and corresponding reliability outcomes to estimate regional- or line-level fault probabilities from four rainstorm drivers: wind speed, rainfall intensity, lightning warning level, and ambient temperature. The inferred probabilities are mapped onto the IEEE 30-bus benchmark to identify high-risk areas or lines and define spatial priorities for emergency response. Third, guided by these risk signals, a two-level coordination model is formulated for a load aggregator (LA) to schedule building air conditioning loads, distributed photovoltaics, and electric vehicles through incentive-based participation, and the resulting optimization problem is solved using an adaptive genetic algorithm. Case studies verify that the proposed strategy can coordinate heterogeneous resources to meet emergency regulation requirements and improve the aggregator–user economic trade-off compared with single-resource participation. The proposed method provides a practical pathway for risk-informed emergency regulation under rainstorm conditions. Full article

The rapid development of unmanned aerial vehicle (UAV) technology necessitates reliable recognition methods. Radio frequency (RF)-based recognition is promising, but conventional real-valued CNNs (RV-CNNs) typically discard phase information from RF spectrograms, leading to degraded performance under low-signal-to-noise ratio (SNR) conditions. To address this, this paper proposes a complex-valued CNN (CV-CNN) that operates on a constructed complex representation, where the real part is the logarithmic power spectral density (PSD) and the imaginary part is derived from Sobel edge detection. This enables genuine complex convolutions that fuse magnitude and structural cues, enhancing noise resilience. As complex-valued networks are known to be sensitive to architectural choices, we conduct comprehensive ablation experiments to investigate the impact of key hyperparameters on model performance, revealing critical stability constraints (e.g., performance collapse beyond 4–5 network depth). Evaluated on the 25-class DroneRFa dataset, the proposed model achieves 100.00% accuracy under noise-free conditions. Crucially, it demonstrates significantly superior robustness in low-SNR regimes: at −20 dB SNR, it attains 15.58% accuracy, over seven times higher than a dual-channel RV-CNN (2.20%) with identical inputs; at −15 dB, it reaches 45.86% versus 14.03%. These results demonstrate that the CV-CNN exhibits potentially superior robustness and interference resistance in comparison to its real-valued counterpart, maintaining high recognition accuracy even under low-SNR conditions. Full article

Metaphor recognition plays a key role in natural language understanding and semantic analysis. This paper introduces a metaphor recognition model called EGSNet (Enhanced Gloss Siamese Network). Previous research has shown that the gloss of metaphor words contributes to their comprehension in metaphor recognition. To leverage this information, this paper incorporates gloss annotations of metaphor words into the metaphor recognition model. Mining the deep semantic information of glossed metaphorical words, and combining MIP linguistic rule to use the annotation information of metaphorical words can better perceive the semantic conflicts between the contextual meaning of the target word and its basic meaning, thereby improving the ability to recognize metaphors. Furthermore, by employing data augmentation techniques to reveal the true meaning of target words in contextual environments and combining gloss information, the EGSNet model can effectively capture subtle semantic differences in sentences as well as the linguistic characteristics of metaphors, thereby enhancing metaphor recognition performance. Experiments indicate that the EGSNet model achieves more accurate metaphor recognition results and makes a significant contribution to the field of metaphor recognition. Full article

An accurate assessment of the state of health (SOH) of lithium-ion batteries (LIBs) is crucial for ensuring the safety and reliability of energy storage systems and electric vehicles. However, existing methods face challenges: physics-based models are computationally complex, traditional data-driven methods rely heavily on manual feature engineering, and single models lack the ability to capture both local and global degradation patterns. To address these issues, this paper proposes a novel hybrid LSTM–Transformer model for LIB SOH estimation using actual measurement data. The model integrates Long Short-Term Memory (LSTM) networks to capture local temporal dependencies with the Trans-former architecture to model global degradation trends through self-attention mechanisms. Experimental validation was conducted using eight 18650 Nickel Cobalt Manganese (NCM) LIBs subjected to 750 charge–discharge cycles under room temperature conditions. Sixteen statistical features were extracted from voltage and current data during constant current–constant voltage (CC-CV) phases, with feature selection based on the Pearson correlation coefficient and maximum information coefficient analysis. The proposed LSTM–Transformer model demonstrated superior performance compared to the standalone LSTM and Transformer models, achieving a mean absolute error (MAE) as low as 0.001775, root mean square error (RMSE) of 0.002147, and mean absolute percentage error (MAPE) of 0.196% for individual batteries. Core features including cumulative charge (CC Q), charging time, and voltage slope during the constant current phase showed a strong correlation with the SOH (absolute PCC > 0.8). The hybrid model exhibited excellent generalization across different battery cells with consistent error distributions and nearly overlapping prediction curves with actual SOH trajectories. The symmetrical LSTM–Transformer hybrid architecture provides an accurate, robust, and generalizable solution for LIB SOH assessment, effectively overcoming the limitations of traditional methods while offering potential for real-time battery management system applications. This approach enables health feature learning without manual feature engineering, representing an advancement in data-driven battery health monitoring. Full article

Current research on cryptocurrency dual-offline payment systems has garnered significant attention from both academia and industry, owing to its potential payment feasibility and application scalability in extreme environments and network-constrained scenarios. However, existing dual-offline payment schemes exhibit technical limitations in privacy preservation, failing to adequately safeguard sensitive data such as payment amounts and participant identities. To address this, this paper proposes a privacy-preserving dual-offline payment method utilizing a cryptographic challenge-response mechanism. The method employs zero-knowledge proof technology to cryptographically protect sensitive information, such as the payer’s wallet balance, during identity verification and payment authorization. This provides a technical solution that balances verification reliability with privacy protection in dual-offline transactions. The method adopts the payment credential generation and credential verification mechanism, combined with elliptic curve cryptography (ECC), to construct the verification protocol. These components enable dual-offline functionality while concealing sensitive information, including counterparty identities and wallet balances. Theoretical analysis and experimental verification on 100 simulated transactions show that this method achieves an average payment generation latency of 29.13 ms and verification latency of 25.09 ms, significantly outperforming existing technology in privacy protection, computational efficiency, and security robustness. The research provides an innovative technical solution for cryptocurrency dual-offline payment, advancing both theoretical foundations and practical applications in the field. Full article

This study examines consumer behavior, preferences, and knowledge regarding honey in Kosovo to inform more effective production, marketing, and policy strategies. Data were collected from 503 respondents through an online questionnaire and analyzed using a combination of artificial neural networks (ANN), decision tree modeling (CHAID), and ordinal logistic regression. The results show a high prevalence of honey consumption, strong preference for locally produced honey, and significant variability in consumer willingness to pay (WTP) based on knowledge, income, and trusted information sources. ANN identified recommendations and product familiarity as primary predictors of WTP, while the decision tree highlighted knowledge and income as key variables for segmentation. The ordinal logistic regression confirmed the importance of perceived quality and product attributes, particularly botanical and geographical origin, in shaping purchasing decisions. The use of complementary statistical models enhanced both predictive power and interpretability. The findings highlight the crucial role of consumer education and trust cues in fostering sustainable honey markets in Kosovo. Full article

This study proposes a reinforcement learning-based link selection method for Low Earth Orbit satellite networks, aiming to reduce handover frequency while extending link duration under highly dynamic orbital environments. The proposed approach relies solely on basic satellite positional information, namely latitude, longitude, and altitude, to construct compact state representations without requiring complex sensing or prediction mechanisms. Using relative satellite and terminal geometry, each state is represented as a vector consisting of azimuth, elevation, range, and direction difference. To validate the feasibility of policy learning under realistic conditions, a total of 871,105 orbit based data samples were generated through simulations of 300 LEO satellite orbits. The reinforcement learning environment was implemented using the OpenAI Gym framework, in which an agent selects an optimal communication target from a prefiltered set of candidate satellites at each time step. Three reinforcement learning algorithms, namely SARSA, Q-Learning, and Deep Q-Network, were evaluated under identical experimental conditions. Performance was assessed in terms of smoothed total reward per episode, average handover count, and average link duration. The results show that the Deep Q-Network-based approach achieves approximately 77.4% fewer handovers than SARSA and 49.9% fewer than Q-Learning, while providing the longest average link duration. These findings demonstrate that effective handover control can be achieved using lightweight state information and indicate the potential of deep reinforcement learning for future LEO satellite communication systems. Full article

We propose a vector bending sensor based on a tapered few-mode multi-core fiber (FM-MCF). A seven-core six-mode fiber is tapered with an optimized taper ratio, enabling bending sensing through power monitoring. When the tapered FM-MCF bends, coupling occurs between the central core and side cores in the tapered region. By monitoring the power of all cores and employing a power differential method, the bending direction and curvature can be reconstructed. The results show that within a curvature range of 2.5 m⁻¹ to 10 m⁻¹, the sensitivity of the ratio of the side core’s power to the middle core’s power with respect to curvature is not less than 0.14/m⁻¹. A deep fully connected feedforward neural network (DNN) is used to demodulate all power information and predict the bending shape of the optical fiber. The algorithm predicts the bending radius and rotation angle with mean absolute errors less than 0.038 m and 3.087°, respectively. This method is expected to achieve low-cost, high-sensitivity bending measurement applications with vector direction perception, providing an effective solution for scenarios with small curvatures that are challenging to detect using conventional sensing methods. Full article

Endometriosis is traditionally conceptualized as a pelvic lesion–centered disease; however, mounting evidence indicates it is a chronic, systemic, and multifactorial inflammatory disorder. This review examines the molecular dialog between ectopic endometrial tissue, the immune system, and peripheral organs, highlighting mechanisms that underlie disease chronicity, symptom variability, and therapeutic resistance. Ectopic endometrium exhibits distinct transcriptomic and epigenetic signatures, disrupted hormonal signaling, and a pro-inflammatory microenvironment characterized by inflammatory mediators, prostaglandins, and matrix metalloproteinases. Immune-endometrial crosstalk fosters immune evasion through altered cytokine profiles, extracellular vesicles, immune checkpoint molecules, and immunomodulatory microRNAs, enabling lesion persistence. Beyond the pelvis, systemic low-grade inflammation, circulating cytokines, and microRNAs reflect a molecular spillover that contributes to chronic pain, fatigue, hypothalamic–pituitary–adrenal axis dysregulation, and emerging gut–endometrium interactions. Furthermore, circulating biomarkers—including microRNAs, lncRNAs, extracellular vesicles, and proteomic signatures—offer potential for early diagnosis, patient stratification, and monitoring of therapeutic responses. Conventional hormonal therapies demonstrate limited efficacy, whereas novel molecular targets and delivery systems, including angiogenesis inhibitors, immune modulators, epigenetic regulators, and nanotherapeutics, show promise for precision intervention. A systems medicine framework, integrating multi-omics analyses and network-based approaches, supports reconceptualizing endometriosis as a systemic inflammatory condition with gynecologic manifestations. This perspective emphasizes the need for interdisciplinary collaboration to advance diagnostics, therapeutics, and individualized patient care, ultimately moving beyond a lesion-centered paradigm toward a molecularly informed, holistic understanding of endometriosis. Full article