Search Results (751)

Underground cables are critical infrastructure for electrical power and communication transmission, and their reliable operation is of paramount importance to urban public safety. Although Distributed Acoustic Sensing (DAS) enables wide-range, continuous, and real-time monitoring, traditional DAS signal processing methods suffer from poor intrusion discrimination and weak anti-interference capability. To address these limitations, we propose a dual-branch network based on multi-domain feature fusion, integrating a Multilayer Perceptron, a Long Short-Term Memory network (LSTM), and an attention mechanism. Vibration signals corresponding to four representative high-risk intrusion events were acquired through controlled field experiments, and a standardized, category-balanced dataset was constructed accordingly. Time-domain, frequency-domain and joint time-frequency features were extracted and mapped through a time-frequency weighting transformation to form one branch of the network, while the parallel branch employed an LSTM to capture long-range temporal dependencies. A multi-head attention mechanism enables deep adaptive fusion of two types of modal information and overcomes the limitations of conventional simple feature concatenation. Comparative experiments against KNN, 1D-CNN and LSTM baselines demonstrate that the proposed model achieves a test accuracy of 98.89%, outperforming all reference methods. Ablation studies further validate the necessity and effectiveness of each constituent module within the proposed architecture. The results indicate that this approach provides reliable support for DAS-based online monitoring of power cables against external damage. Full article

Distribution system restoration (DSR) has become increasingly challenging due to frequent topology changes and complex nodal interactions, especially in systems with a high penetration of distributed energy resources (DERs). Existing deep reinforcement learning (DRL) methods remain limited in representing inter-nodal relationships and incorporating domain prior knowledge. Therefore, this paper proposes a graph attention-based coupling-aware reinforcement learning method. From a non-Euclidean spatial perspective, the proposed method uses the distribution power transfer factor (DPTF) to quantify the strength of electrical coupling between nodes. The resulting coupling strengths are embedded as entries of the graph adjacency matrix, allowing the model to capture complex nodal interactions driven by power transfer. An aware graph attention network (AGAT) is further developed, where adjacency matrix with prior knowledge is introduced as a bias term in the attention coefficient calculation. This design guides GAT to generate differentiated node representations enriched with physical information. Based on the extracted graph features, proximal policy optimization (PPO) is employed to determine restoration decisions. Case studies on the IEEE 34-bus system demonstrate that the proposed method outperforms benchmark algorithms in training convergence, restored power, and online decision efficiency, enabling fast and effective distribution system restoration. Full article

Systematic measurement biases are a persistent source of degradation in airborne radar target tracking. Online bias estimation is especially difficult for single-platform operations because only one measurement stream is available, and the target state and radar biases are coupled in the same nonlinear observation model. Under weakly observable geometries, directly augmenting bias states into a recursive filter may lead to slow convergence, while fixed or overly frequent batch optimization may inject updates from weakly informative windows. To address this problem, this paper proposes a Bias Subspace Information-Guided MAP-EKF (maximum a posteriori–extended Kalman filter) (BI-MAP-EKF) for online bias estimation in single-platform airborne radar. A nine-dimensional augmented state jointly describes target motion and range, azimuth, and elevation biases. A posterior Cramér–Rao lower bound (PCRLB) is constructed for this state, where the EKF prior, windowed radar measurements, and process noise propagation are jointly considered. The bias subspace is then extracted by Schur complement, and the resulting azimuth bias PCRLB is used to decide whether the MAP update is reliable enough for EKF injection. The scheduler also includes a cooldown interval and a maximum-window safeguard, which respectively limit excessive updates under informative maneuvers and prevent indefinite waiting under weak geometries. Fifty-run Monte Carlo simulations under different maneuvering conditions show that the proposed scheduler is particularly effective in weakly informative geometries, where it improves azimuth bias and horizontal position estimation while reducing the number of accepted MAP refinements compared with the tested fixed-period MAP and moving-horizon estimation (MHE) baselines. In stronger maneuvering scenarios, it provides a competitive accuracy–cost trade-off rather than uniformly outperforming aggressive MHE in every channel. Full article

With the continuous penetration of renewable energy and power electronic equipment into modern power systems, the occurrence frequency of composite power quality disturbances has increased significantly. The accurate classification of various composite disturbances under strong noise remains a critical technical challenge. The existing single time–frequency transformation methods cannot simultaneously capture transient time-domain details and fine frequency-domain features of steady-state harmonics, while mainstream deep learning classification networks contain redundant parameters and introduce excessive computational overhead, failing to meet the real-time deployment requirements of power edge terminals. To address these limitations, a lightweight Coordinate Attention ResNet network named ResNet–LCA is proposed based on the dual-modal time–frequency fusion of the Continuous Wavelet Transform and Short-Time Fourier Transform. First, the two transforms are implemented separately to generate two groups of complementary time–frequency maps, which are concatenated along the channel dimension to fully extract the coupling features between the steady-state harmonics and the transient impulses. Second, a Haar wavelet subband mean aggregation module is designed for dimensionality reduction with negligible information loss. This module eliminates the channel redundancy introduced by the multimodal fusion and reduces the overall computational overhead at the input stage. Finally, a lightweight residual network integrated with Coordinate Attention is constructed, with Grouped Half-Convolution adopted to compress the model parameters. CA offsets the feature attenuation induced by the lightweight structural design and further improves the model’s noise immunity. A simulation verification was carried out on a simulated dataset covering 25 types of single and superimposed composite disturbances. At a signal-to-noise ratio of 20 dB, the proposed method achieved an average classification accuracy of 97.92%, with only 5.32 M total parameters and a single-sample GPU inference latency of 0.33 ms. Compared with standard ResNet-18 under 20 dB noisy conditions, the total parameter volume was reduced by 52.7%, the inference latency was shortened by 0.13 ms, and the classification accuracy was improved by 0.60 percentage points. The proposed method achieves coordinated optimization of classification accuracy, noise immunity and inference efficiency, and it can provide lightweight technical support for online intelligent power quality monitoring at the edge nodes of microgrids and islanded power systems. Full article

This paper examines mainstream platform moderation as it encounters contemporary pagan religious practice in Europe and reads what it finds as a symptom of a wider condition: the algorithm functions less as a neutral tool than as a productive instrument of an extractive political economy whose characteristic operation is the appropriation, classification, and revenue-conditioned filtering of human expression. Minority religious traditions are structurally exposed within it: too small to constitute an accommodated market, too polysemic for classifiers trained on majority devotional and Anglo-American extremism corpora, and too fragmented to extract policy concessions. Empirically, the paper draws on netnography of pagan online communities across Europe, informal conversations with 97 practitioners across nine European jurisdictions, and a corpus of 247 takedown notices and appeal exchanges (2019–2025). Three recurrent rationale-clusters—devotional content classified as occult, as extremism-adjacent, and as unsafe activity—are read as predictable outputs of the system’s cost structure rather than as ordinary classifier errors. Two concepts are proposed. Algorithmic sacredness names the transfer of gate-keeping functions previously held by ecclesiastical, state, and editorial actors, routed through Bourdieu’s meta-capital as extended to platforms. Algorithmic pluralism names a programmatic direction toward infrastructures whose governance is not capital’s. Full article

City image links perceptions of urban form and environmental quality to place identity and sociocultural sustainability. However, city-scale research rarely integrates visible streetscape characteristics with visitor narratives. Using Wuhan, China, as a case study, this study integrates panoramic streetscape imagery with online visitor reviews. Semantic segmentation was employed to quantify nine streetscape visual indicators, such as building interfaces, visible greenery and water, color characteristics, and visual disturbances. High-frequency term extraction and thematic coding identified four dimensions of visitor perception: cultural, aesthetic, leisure, and scientific–educational perceptions. Statistical and spatial analyses were subsequently conducted to examine the relationships between the visual indicators and these perceptual dimensions. Leisure and aesthetic perceptions emerged as the most prominent dimensions. Color harmony, water visibility, and visible greenery were positively associated with cultural, aesthetic, and leisure perceptions. Dense building interfaces and visual disturbances were negatively associated with aesthetic and leisure perceptions but positively associated with scientific–educational perception. Hotspots of cultural, aesthetic, and leisure narrative intensity were concentrated in core Wuchang and the East Lake area, whereas scientific–educational perception showed weaker overall spatial clustering, with localized hotspots in central urban areas. These findings suggest that integrating street-view imagery with visitor narratives can help identify spatially differentiated relationships between visible urban environments and city image. The proposed framework may facilitate the identification of sustainability-relevant visual resources and provide diagnostic evidence that may inform urban design and public-space management. Full article

As electric vehicles become widespread, home EV chargers have emerged as a key interface between household energy use and daily mobility. However, their design optimization remains insufficiently informed by large-scale user feedback. This study develops a review-driven, interpretable machine learning framework to identify design priorities for home EV chargers. Of the 26,763 reviews collected from the JD e-commerce platform, 23,893 were retained after cleaning. BERTopic extracted raw topics, which were consolidated into ten design dimensions through independent coding, inter-coder agreement assessment, and consensus adjudication. A structured large language model protocol then transformed the reviews into evidence-constrained, aspect-level semantic proxy variables representing evaluative direction and intensity. Coding reliability was evaluated against dual-coder annotations, while a matched absence-as-zero specification examined sensitivity to the treatment of unmentioned dimensions. Platform ratings were subsequently introduced as the prediction target, and repeated data partitions and cross-model SHAP comparisons were used to assess partition- and model-level stability. Charging Performance, Operational Stability, Perceived Product Quality, and Operational Convenience and Portability consistently ranked as the most important factors associated with platform-rated satisfaction. In contrast, Installation Friendliness and After-sales Service showed asymmetric attribution patterns characterized by stronger low-value penalties than high-value gains. The framework supports translating online review evidence into product-level design priorities, while emphasizing that SHAP identifies predictive associations rather than causal effects. Full article

Non-invasive, real-time monitoring of plant water status is critical for precision agriculture and plant physiology. However, existing methods often lack continuous in situ measurement capability or are limited by temporal resolution. This paper proposes a novel non-invasive method based on xylem electrical conductivity, inspired by industrial non-contact fluid measurement. As a ground-based complement to remote sensing, this approach demonstrates the feasibility of online, in situ, and non-invasive monitoring of water stress in grapevine stems under controlled laboratory conditions. The industrial C⁴D sensing system is adaptively modified into a specialized Plant-C⁴D sensor with an array-based design for batch signal acquisition. To validate the electrical response to water loss, a gravimetric natural dehydration experiment was conducted, demonstrating a clear correlation between electrical signals and water content changes in detached stem samples. Full-day dynamic experiments are conducted under three conditions: normal water supply, varying water stress, and plant inactivation. Sensitive characteristic parameters are extracted through signal analysis, and a pattern recognition framework is established to eliminate environmental interference and suppress individual differences. Experimental results on 24 plant samples (Shine Muscat) show that the method accurately discriminates viable from inactivated plants with an accuracy of 91.67% (22/24 correct). Furthermore, the Fuzzy C-Means (FCM) clustering algorithm successfully quantifies the severity of water stress in viable plants, yielding results consistent with actual water supply conditions. While these findings demonstrate the capability of Plant-C⁴D sensor to capture stem water status-related information, the current results do not establish full physiological validation, warranting further exploration with in vivo experiments. Full article

The increasing diffusion of Renewable Energy Communities offers new opportunities to support vulnerable households through locally generated renewable energy. However, current Home Energy Management Systems mainly optimize energy efficiency and cost reduction, while providing limited support for protecting critical household loads under constrained energy availability. This paper proposes an AI-based Energy Guardianship framework that combines a commissioning phase, in which a Local Appliance Atlas is created from the electrical signatures of the appliances actually installed in a specific dwelling, with an online phase that identifies operating appliances from aggregated measurements and dynamically allocates available energy according to appliance priority. Appliance identification is performed using rich electrical signatures including transient behavior, dynamic V-I trajectories, harmonic information, power profiles, and conventional electrical features extracted from aggregate voltage and current measurements. Unlike conventional home energy management systems, where appliance identification is mainly used to optimize energy consumption, the proposed framework exploits NILM information to support socially aware decisions that preserve critical services while delaying or limiting non-essential loads. A low-cost monitoring architecture is developed to recognize household appliances through electrical signatures and classify loads according to their criticality. When power thresholds are approached, the system recommends demand-side actions, postpones non-essential consumption, and protects critical devices. Preliminary simulation scenarios demonstrate the feasibility of the proposed framework in protecting vulnerable users under limited energy availability while simultaneously improving photovoltaic self-consumption and reducing dependence on grid energy. Although optimization is not the primary objective, the framework naturally supports renewable-aware energy scheduling and future interaction with energy service providers. Full article

In Virtual Power Plants (VPPs), computing the Optimal Energy Flow (OEF) for integrated electricity–heat systems is essential but challenged by highly asymmetric topologies and multi-timescale characteristics. Traditional data-driven models often fail to extract cross-domain coupling features and violate physical laws, yielding infeasible solutions. To address these challenges, this paper proposes an efficient OEF framework based on a Hierarchical Physics-Informed Heterogeneous Graph Neural Network (HPI-HGNN). First, a lossless mapping mechanism transforms physical networks into a heterogeneous graph, utilizing generalized edge attributes and feature projection to resolve dimensional discrepancies. Second, an attention-driven feature fusion algorithm is developed to adaptively evaluate path sensitivities and deeply extract cross-domain features. Finally, a hierarchical constraint mechanism embeds polar-coordinate power flow and thermo-hydraulic balance equations directly into hidden layers. This approach enables mechanism-guided optimization through layer-wise cross-gradient feedback. Simulations on a coupled IEEE 33-bus power and 32-node thermal system show that HPI-HGNN improves prediction accuracy for key variables (voltage magnitude, phase angle, and temperature) by 42.58–78.51% compared to a baseline PINN. Furthermore, it effectively suppresses voltage and temperature limit violations to a near-zero level, ensuring a highly accurate and physically reliable solver for secure online VPP scheduling. Full article

This study explores how artificial intelligence (AI)-driven labour market analytics can support the alignment of university curricula with emerging skill demands and inform the development of targeted micro-credentials. A mixed-methods approach was applied, combining AI-assisted analysis of approximately 30,000 online job advertisements in Latvia with ESCO-based skill mapping, curriculum analysis, and expert interviews. The study develops and validates a three-layer analytical framework integrating labour market demand, professional standards, and programme learning outcomes. Three occupations—Personnel Specialist, Finance Manager, and Organisation Manager—were analysed at Riga Technical University as proof-of-concept cases. The findings demonstrate that strict one-to-one ESCO matching overestimates curriculum gaps because labour market and educational actors often describe competencies at different levels of abstraction. Composite matching significantly improves alignment estimates by identifying functionally equivalent competencies embedded across curricula. Nevertheless, the analysis reveals a persistent under-representation of digital competencies across all programmes, confirmed by industry experts. Interviews further identify a “pedagogical transfer gap”, where formally acquired competencies are insufficiently applied in practice, and highlight employer support for high-quality micro-credentials focused on technical upskilling. The study contributes an AI-assisted curriculum-monitoring framework that combines large-scale skill extraction, semantic alignment, and stakeholder validation, offering universities a practical tool for evidence-based curriculum renewal and lifelong learning development. Full article

Structural health monitoring (SHM) relies heavily on the real-time extraction of valid information from raw streaming vibration data. However, the widely used traditional variational mode decomposition (VMD) method has two critical technical bottlenecks, which include key decomposition parameters that rely on manual empirical setting with unavoidable subjectivity and batch processing mechanisms that cannot support online real-time denoising of continuous monitoring data. To overcome these challenges, this paper develops a novel Recursive Sliding Bandwidth-Aware Variational Mode Decomposition (RSBAVMD) method and carries out a full set of scientific research. Firstly, we introduce the weighted spectrum trend (WST) method to adaptively divide the signal spectrum into sub-bands and automatically solves the optimal number of decomposition modes and the matched penalty factor for each mode, eliminating the dependence on manual parameter tuning. Then, to enable online processing of streaming SHM data, we introduce an online iterative update method based on recursive sliding Fourier transform, thus breaking the offline application limitation of conventional VMD. We conduct validation experiments using numerical simulated signals and measured structural vibration data. The results indicate that the proposed RSBAVMD method achieves adaptive determination of components and penalty factors. Compared with traditional VMD and mainstream online denoising methods, this method has the best denoising effect. Compared with the VMD method, the proposed method reduces analysis time by about 80% and is less affected by the amount of analyzed data. The proposed RSBAVMD method can satisfy the real-time denoising requirements of streaming vibration data while ensuring accuracy, providing reliable support for online SHM and structural state assessment. Full article

Gas concentration in coal mine return-air corners is affected by ventilation, mining disturbance and gas drainage conditions, and it shows strong nonstationarity, local fluctuation and dynamic multi-point correlations. To improve frequency information separation, monitoring point relationship modeling, and short-term prediction accuracy, a variational mode decomposition (VMD)-based dual-branch spatiotemporal graph method is proposed. Gas concentrations from four key monitoring points are used as inputs, and the return-air corner gas concentration is taken as the output. First, the raw series are decomposed by VMD and reconstructed into low- and high-frequency components. Then, two branches are built for different frequency components. The low-frequency branch combines adaptive graph learning, graph convolution and gated recurrent units to extract global variation features, while the high-frequency branch combines graph attention and gated recurrent units to capture local disturbance features. Finally, a feature-fusion module generates multi-step predictions, and a lightweight short-term warning strategy is developed based on the predicted values. The proposed model achieves MAE, RMSE and R² values of 0.0338, 0.0471 and 0.9499 in one-step prediction, respectively, and outperforms GRU, LSTM, GCN-GRU, GAT-GRU, VMD-GRU, Informer and STGCN under three-step and six-step conditions. Cross-dataset validation and inference time analysis indicate good adaptability and online prediction potential. Full article

With the rapid development of social media and online interactive platforms, online public opinion has become a vital information source for public emotional expression, social risk perception, and decision support. However, public opinion texts are typically characterized by short length, obscure semantics, complex emotional expressions, and strong context dependence, making it difficult for traditional lexicon-based or shallow neural network methods to achieve stable and robust performance in sentiment discrimination tasks. To address these issues, this paper proposes BERT-BiLSTM-MHSA-Capsule (BBMC), hereafter referred to as BBMC, an online public opinion sentiment analysis model based on multi-level semantic feature fusion. The model first utilizes the pretrained language model BERT to extract dynamic semantic representations with context-aware capabilities; subsequently, a Bidirectional Long Short-Term Memory (BiLSTM) network is employed to model the bidirectional temporal dependencies within the texts, while a Multi-Head Self-Attention (MHSA) mechanism is introduced to achieve adaptive focusing on key emotional information. Building upon this, a three-layer cascaded capsule network is constructed to achieve structured modeling of high-order emotional attributes through vector neurons and dynamic routing mechanisms, effectively mitigating the loss of spatial feature information caused by traditional pooling and fully connected structures. Experimental results on a manually annotated online public opinion dataset show that BBMC achieves better performance than the evaluated baseline models in terms of accuracy, recall, and F1-score. These results indicate the empirical effectiveness of the proposed task-oriented feature-integration strategy and capsule-based classification head for online public opinion sentiment analysis. Full article

Accurate single-step prediction of stack NO_x concentration is essential for emission monitoring and ammonia-injection control in cement kiln SNCR–SCR hybrid denitrification systems. However, this task is challenging because industrial kiln data are affected by nonstationary emission fluctuations, nonlinear multivariable coupling, process-dependent time delays, and online deployment constraints. To address these process-specific challenges, this study develops a leakage-free dynamic soft-sensing framework for stack NO_x concentration prediction. In the proposed framework, variational mode decomposition (VMD) is used to characterize the multi-scale nonstationarity of the stack NO_x sequence under a sliding-window protocol. Trend-guided maximal information coefficient (MIC) analysis is then applied for nonlinear feature selection and delay compensation using only the training data, and the identified feature subset and delay parameters are fixed for validation and testing. A TCN-SE-LSTM model is constructed to extract temporal dependencies, recalibrate informative feature channels, and capture long-lag dynamic behavior. In addition, the Dual Adaptive Constrained Ivy Algorithm (DAC-IVY) is used only for offline hyperparameter optimization, so that the online stage requires only the trained prediction model. Experiments using 21,600 raw samples collected from an actual cement kiln Distributed Control System (DCS) show that the proposed framework achieves an RMSE of 0.2084 mg/Nm³ and an $R^2$ of 0.9844 on the test set, outperforming conventional baseline models. These results indicate that the proposed framework can provide an effective soft-sensing basis for subsequent denitrification control and operational optimization. Full article