Search Results (2,709)

In this work, Intelligent Bidirectional Long Short-Term Memory with Temporal Fusion Transformer-based prediction and Proximal Policy Optimization (IBT-PPO) is proposed in response to the challenges of uncertain renewable generation, fluctuating demand, and inefficient energy scheduling in hybrid renewable energy systems. The algorithm is based on a dual-stage framework that integrates machine learning forecasting with reinforcement learning-based planning. Initially, a hybrid Bi-LSTM-TFT model is employed to generate accurate short-term forecasts of wind power, solar power, and demand, which employs temporal dependencies and multi-horizon patterns. After that, the PPO strategy is designed to optimize scheduling decisions, adaptively balancing battery usage, grid reliance, and renewable dispatch. To enhance robustness, adaptive feature weighting and temporal gating strategies are incorporated, ensuring stable convergence and reduced planning redundancy. Subsequently, the energy allocation is refined through iterative learning to minimize operational cost and maximize renewable penetration. The proposed framework is evaluated as an offline/post hoc forecasting and scheduling approach, with the Bi-LSTM–TFT module exploiting historical temporal representations and the PPO agent optimizing energy-management decisions based on the resulting forecasts. The experimental evaluation is carried out using the Open Power System Data (OPSD) dataset, which provides realistic time-series data for wind, solar, demand, and electricity prices. Thus, the IBT-PPO system integrates multi-horizon probabilistic forecasting and adaptive feature weighting for better prediction and planning accuracy and achieves a 24.1% cost reduction and 95.5% renewable utilization, thereby advancing efficient and intelligent energy prediction and planning. Full article

Multi-modal MRI provides essential anatomical and pathological information for accurate brain tumor segmentation. However, deep learning-based segmentation methods are hampered by limited annotated data and incomplete modality acquisition in clinical MRI datasets. To address this issue, we propose a synthetic enhancement framework based on SCGAN-MultiJNet for multi-modal brain-tumor MRI. Specifically, SCGAN establishes a dual-branch disentangled latent space to independently encode images’ structural contour and textural features. Combined with the multi-scale fusion capability of MultiJNet, the proposed network realizes effective modality translation. Subsequently, synthetic samples are mixed with BraTS2020 training data to optimize the U-Net segmentation model. With the optimal real–synthetic data-mixing strategy, the segmentation metrics are improved: accuracy, Dice, precision, and IoU increase from 0.9857, 0.8919, 0.8980, and 0.8054 to 0.9864, 0.8962, 0.9205, and 0.8122. The proposed synthetic augmentation experimentally demonstrates enhancements in model robustness against MRI disturbances (including Gaussian blur, brightness shift, etc.). Finally, cross-domain generalization experiments conducted on the BraTS2025-SSA-Data demonstrate that introducing synthetic data augmentation can effectively boost the model’s cross-domain generalization capability. Overall, the proposed SCGAN-MultiJNet-based data synthesis algorithm provides a feasible technical solution to break the data bottleneck in multi-modal MRI brain tumor segmentation. Full article

Nuclear energy production requires robust shielding solutions to ensure the safety of personnel and equipment across a wide range of reactor technologies. Shield for Fusion (S4F) is a new development in nuclear analysis models, and codes a computational framework for optimizing radiation shielding design in fusion reactor applications using OpenMC neutronics simulations and genetic algorithms (GAs). The framework addresses four-layer shielding cabinets with six commercially viable materials, exploring 10,000 possible configurations through a template-based approach with density correction factors. The genetic algorithm efficiently converges to optimal solutions in approximately 100 simulations by balancing competing objectives: neutron flux attenuation, dose minimization, material cost, and weight. Compared to uniform sampling, the GA demonstrates superior performance by identifying high-performing parameter regions with improved attenuation and reduced cost. The framework includes an inverse design tool for rapid retrieval of configurations matching target performance criteria requested by external users, currently available for selected neutron source spectra. Results demonstrate effective multi-objective optimization for fusion shielding applications, with the open-source code available for adaptation to different simulation setups. Full article

Industrial water treatment plants are increasingly dependent on cyber–physical systems (CPS) and automated control processes for their operational safety and efficiency. However, the embedding of digital control networks exposes these critical infrastructures to sophisticated cyber–physical attacks, including malicious tampering with chemical dosing units and physical actuators. This paper proposes a robust, AI-enhanced anomaly detection framework designed to identify multi-stage malicious activities in water treatment systems using real-world industrial datasets. The proposed system is developed and validated on the Secure Water Treatment (SWaT) dataset, which contains multivariate sensor and actuator time-series data collected from a fully operational physical testbed under both normal operations and targeted cyber–physical attacks. First, high-frequency sensor noise is filtered, and cross-channel measurement reliability is maximized using a Kalman filter-based sensor fusion module. Subsequently, the fused-state vector is analyzed using an unsupervised Isolation Forest algorithm optimized for high-dimensional boundary isolation. To eliminate false negatives caused by stealthy, low-amplitude data injections that bypass purely statistical models, a deterministic, rule-based verification layer derived from physical process control logic is integrated. By integrating a discrete linear Kalman filter with an unsupervised Isolation Forest and deterministic physical rules, the framework effectively suppresses high-frequency sensor noise, achieving a 67.8% reduction in root mean square error (RMSE), while maintaining high detection accuracy across complex industrial attack scenarios. Experimental results demonstrate that the proposed hybrid framework yields superior detection capability, achieving a Precision of ≈95%, a Recall of ≈93%, a scenario-level F1-score of 94.1 % (alongside a sample-level F1-score of 21.5 %) and an edge inference latency of 0.6 ms, effectively demonstrating its suitability for deployment within simulated real-time industrial edge computing environments. The findings further confirm that combining statistical machine learning, state-space sensor fusion, and invariant physical process logic provides a resilient defense paradigm for securing critical industrial infrastructure against modern cyber–physical threats. Full article

This paper presents a machine learning-based decision support system for multiclass defect detection, utilizing exclusively heterogeneous legacy process data to minimize manual inspection time in foundries. Validated on 51,377 products across 193 defect categories, the methodology resolves structural data inconsistencies through k-nearest neighbor (kNN) imputation and piecewise winsorization. A multi-stage feature selection cascade, incorporating variance thresholding, correlation filtering, and Random Forest Feature Importance (RFFI), reduces the feature space from 139 to 78 process-critical variables. Following Synthetic Minority Over-sampling Technique (SMOTE)-based class balancing, five classifiers were benchmarked via 10-fold cross-validation and optimized using the macro-averaged F₃-score to mathematically penalize undetected defects. Light Gradient Boosting Machine (LightGBM) and Random Forest (RF) provided superior predictive baselines. To enforce strict zero-defect constraints, an asymmetric risk function shifted decision boundaries, enabling the risk-calibrated LightGBM model to reduce manual inspection volume by 9.72% with zero defect escapes. For resolving conflicting predictions, multi-algorithm decision fusion was implemented. By statistically evaluating the joint probabilities of the base models’ post-calibration outputs, a Naive Bayes Stacking meta-classifier effectively neutralizes single-algorithm inductive biases. Ultimately, synthesizing these F₃-optimized, risk-calibrated base models via meta-learning successfully isolated true defect-free components, maximizing the final inspection time reduction to 14.82% while strictly maintaining zero defect escapes. Full article

Accurate interwell connectivity characterization is critical for fine-grained waterflood optimization and reservoir management, often requiring integrated analysis across multiple disciplines and methods. Among these, injection–production response analysis stands as the most cost-effective and widely adopted approach. However, it remains highly subjective, heavily reliant on senior engineers’ decades of accumulated experience, and prohibitively labor-intensive for large-scale oilfields with hundreds of wells. With the exponential growth of production data in modern oilfields, manual analysis has become the bottleneck restricting the timeliness of reservoir management decisions. While signal processing techniques offer a promising path to automation, general-purpose algorithms fail to incorporate fundamental reservoir fluid flow laws, resulting in insufficient accuracy for practical engineering applications. To address this gap, we propose a novel connectivity identification method that mimics expert analysis logic by focusing on large-amplitude fluctuation segments rather than full-curve matching. Using curve slope as the core metric, cosine similarity quantifies trend consistency, while Root Mean Square Error (RMSE) measures amplitude proximity. Three targeted strategies enhance accuracy: key region screening with segmented matching, outlier removal accounting for time-varying lags, and multi-index weighted fusion. Validated on synthetic and mature carbonate waterflood field cases, the method improves the identification performance over benchmark Normalized Cross-Correlation (NCC) and Capacitance-Resistance Model (CRM) methods by more than 12% in both cases. It retains the reliability of traditional response analysis while achieving full automation, and can help estimate the timing of preferential flow path formation, requiring only routine production data to provide valuable reference for timely field development decision-making. Full article

Graph convolutional networks (GCNs) have achieved remarkable success in graph representation learning, yet they remain limited by over-smoothing and insufficient utilization of high-order topology. Existing high-order GCNs exploit multi-hop neighbors but ignore the purity of high-order neighborhoods: the high-order graphs they construct contain duplicated and fictional edges, which cause feature redundancy and false topological semantics. In this paper, we propose a pure high-order graph convolutional network (PHGCN) grounded in pure high-order neighborhoods. We first analyze how duplicated and fictional edges arise from powers of the adjacency matrix, and then design a graph pure high-order projection (GPHP) algorithm that eliminates both types of invalid edges. On this basis, we construct a multi-path GCN architecture with an attention-based fusion module to learn and combine features from pure high-order neighborhoods of different orders. Experiments on seven graph classification benchmarks (IMDB-B, IMDB-M, MUTAG, PROTEINS, NCI1, DD, and COLLAB) show that PHGCN achieves the best average ranking among the compared models, and ablation studies show that each component contributes to the final performance. Full article

Multi-frame fusion is standard for converting frame-by-frame license plate character detections into stable, reliable readings. Character Time-Series Matching (CTM), a leading approach, associates characters across frames using the Hungarian algorithm with a fixed Euclidean distance threshold and a translation-only motion model, reporting 96.7% accuracy on the UFPR-ALPR dataset. In this work, we demonstrate that this high performance is protocol-dependent: when ground-truth static plate crops and pre-segmented tracks are used, CTM performs strongly. However, in real-world scenarios involving moving cameras (such as drone-mounted cameras, helmet-mounted cameras, and mobile platforms) where inter-frame geometry changes dynamically, baseline multi-frame association frameworks that combine fixed spatial gates with unconstrained translation propagation fail. In these cases, temporal fusion provides no benefit and degrades plate recognition performance below the single-frame baseline. Indeed, under its own Intersection over Union (IoU) tracker, this literature method correctly reads only 15.1% of plates in traffic videos recorded with a real moving camera (86 human-verified tracks). To address this vulnerability, we propose Geo-CTM (Geometry-Constrained CTM), an association pipeline integrating height-scaled adaptive matching gates, inter-frame similarity estimation via Random Sample Consensus (RANSAC), transform-guided character coasting, and co-occurrence-constrained duplicate track elimination. Systematic motion-model ablation demonstrates that while the complete association pipeline provides the primary foundation for robustness (raising mean accuracy from 85.40% to over 91.5%), estimating a similarity transform (91.82%) delivers the most physically grounded and identifiable representation on planar plates without estimation degeneration. While our method performs comparably to CTM on ideal data when using the same detector and detections, it minimizes performance loss under geometric distortion conditions where CTM is inadequate. For instance, a statistically significant improvement is achieved under a 0 → 60° perspective change; in real traffic videos, with the tracker held fixed so that the fusion layer is the only variable, performance rises from 15.1% to 26.7% under the IoU tracker of the original system and from 16.3% to 29.1% under ByteTrack ($+11.6$ and $+12.8$ points; exact McNemar $p=0.021$ and $p=0.013$), whereas changing the tracker alone while holding the fusion layer fixed moves accuracy by only 1–2 points and is not statistically significant. Finally, our error taxonomy analysis demonstrates that on the undistorted benchmark all residual errors correspond to zero-evidence cases beyond the reach of decision-level fusion, while under dynamic perspective distortion errors are dominated by association misalignment, highlighting the specific development areas that future performance improvements must target. Full article

Accurate iris segmentation remains a fundamental challenge in iris biometric recognition and medical image analysis, particularly in challenging scenarios such as non-cooperative acquisition conditions involving variable illumination, partial occlusions, degraded image quality, and diverse unconstrained environments. Prevailing segmentation algorithms exhibit limited robustness when confronted with such challenges, and the disparity between near-infrared (NIR) and visible-light imaging modalities further compounds the complexity of achieving a robust segmentation outcome. To address these challenges, this paper introduces SwinIrisNet, a hybrid deep learning architecture that integrates Swin Transformer and convolutional neural network (CNN) branches within a U-Net framework for robust iris segmentation. The Swin Transformer branch leverages hierarchical window-based self-attention to capture global contextual dependencies, whereas the CNN branch extracts fine-grained local features essential for precise boundary delineation. A memory-efficient cross-attention fusion module combines these complementary feature representations, further enhanced by a Convolutional Block Attention Module (CBAM), Atrous Spatial Pyramid Pooling (ASPP), and attention-gated skip connections for multi-scale context aggregation. An extensive evaluation is conducted across four publicly available benchmark datasets, including UBIRIS.v2, IITD, CASIA-Thousand, and MMU.v1, encompassing both visible-light and NIR imaging environments. The proposed architecture yields F1 values of 0.9612–0.9672, Dice coefficients of 0.9489–0.9519, mIoU values of 0.9266–0.9450, precision values of 0.9565–0.9633, recall values of 0.9600–0.9672, and classification accuracies of 99.51–99.53%, with NICE1 error rates of 0.57–0.60% and NICE2 values of 1.82–2.24%, confirming pixel-level segmentation quality. Cross-database generalization experiments further demonstrate that SwinIrisNet learns transferable iris representations and generalizes effectively across heterogeneous imaging sources, with the strongest transfer occurring in the NIR-to-visible direction. A comparative analysis against existing algorithms demonstrates that the proposed architecture attains substantial performance improvements over several existing segmentation networks when evaluated on identical benchmark databases, surpassing them across the majority of qualitative and quantitative metrics while maintaining a marginally lower memory footprint. Full article

To proactively identify performance anomaly evolution and potential operational risks of marine main engines and reserve a sufficient time window for maintenance intervention, this paper proposes a data-driven multi-algorithm fusion framework for performance evaluation and anomaly early warning of marine main engines. The framework first adopts a steady-state detection strategy to filter valid operating conditions and introduces the CLIQUE clustering algorithm to realize adaptive partitioning of high-dimensional operating parameters; comparative experiments with the classical K-means++ clustering algorithm demonstrate that CLIQUE achieves finer-grained operating condition classification without pre-defining the number of clusters and better adapts to the uneven distribution of actual marine engine operating conditions, which addresses the limitations of traditional single-parameter analysis and conventional dimensionality reduction methods in practical shipboard scenarios. On this basis, the Mahalanobis distance evaluation model is constructed under each partitioned operating condition, which further improves the stability and anti-interference performance of quantitative performance assessment for the main engine. Meanwhile, by integrating cumulative anomaly trend analysis and the Yamamoto mutation test, the framework accurately captures statistical mutation characteristics of the performance deviation trajectory and identifies the first mutation point as the retrospective candidate change point, forming a systematic anomaly detection mechanism. Validation using field measurement data from a 6RT-flex82T marine main engine shows that the proposed framework can comprehensively characterize the overall operating state of the main engine and capture long-term performance deviation evolution patterns. Retrospective analysis indicates that the first statistical mutation of the multivariate performance deviation precedes the significant abnormal fluctuation of a single parameter by approximately 20 days, showing the potential of providing a maintenance buffer period. The proposed method can provide technical reference and support for condition-based maintenance of marine main engines and intelligent operation and maintenance of shipboard power equipment. Full article

Multispectral pan-sharpening aims to fuse high-resolution panchromatic and low-resolution multispectral imagery. However, this process introduces spatial artifacts and spectral distortions. Assessing the quality of fused images remains a fundamental challenge due to the absence of full-resolution ground-truth data. This paper provides a comprehensive review of Image Quality Assessment (IQA) frameworks tailored for pan-sharpened imagery. After overviewing major fusion approaches, including Component Substitution (CS), Multi-Resolution Analysis (MRA), Variational Optimization (VO), and Deep Learning (DL), the review analyzes the evaluation techniques used to benchmark them. It then systematically examines the evolution of evaluation protocols, from classical reference-based metrics relying on Wald’s protocol to full-resolution consistency models and recent no-reference (NR) algorithms. The analysis highlights critical methodological bottlenecks within the field, including unrealistic scale-invariance assumptions in consistency-based metrics, dependence on arbitrary parameters, and severe cross-sensor overfitting in deep learning approaches. Furthermore, the review addresses the mismatch between mathematical fidelity, human visual perception, and practical applicability. Finally, it outlines future research directions, focusing on spatial quality mapping and task-driven assessment protocols that validate fusion efficacy based on its impact on automated remote sensing applications. Full article

This paper investigates the distributed fusion estimation problem for multi-sensor cyber-physical systems (CPSs), where the communication channels from local estimators to the fusion center are subject to random packet dropouts. Packet dropouts induced by either network congestion or intermittent denial-of-service (DoS) attacks are modeled as Bernoulli random variables. When a local estimate is lost, a prediction compensation strategy is adopted at the fusion center, where the missing data are replaced by their one-step predictors. By constructing an augmented state consisting of the original state, local prediction errors, and virtual measurements, the multi-sensor system is transformed into a stochastic system with random parameter matrices and one-step autocorrelated noises. Based on the transformed system, a distributed state fusion (DSF) filter is proposed via the innovation analysis method, whose filter gain depends on the successful-reception probabilities. The stability of the proposed DSF filter is analyzed, and a sufficient condition for the existence of a steady-state filter is obtained. The steady-state gain can be pre-computed offline, thereby reducing the online computational burden. Simulation results validate the effectiveness of the proposed algorithm. Full article

Automated monitoring of welfare-relevant behavior in laying hens (Gallus gallus domesticus) has advanced with developments in computer vision, deep learning, and precision livestock farming (PLF). This narrative review integrates the ethological basis of welfare indicators with the development and readiness of monitoring technologies. It distinguishes routinely expressed diagnostic behaviors, including preening, locomotion, dustbathing, feeding, drinking, and nesting, from high-priority welfare risks such as aggression, piling, feather pecking, and inactivity or prostration. The review traces the progression from manual ethograms to semi-automated tools and recent artificial intelligence (AI) applications. These include You Only Look Once (YOLO)-based detection, multi-object tracking with BoT-SORT (a robust association-based tracking algorithm), pose estimation, and multimodal sensor fusion. Application-specific Technology Readiness Levels (TRL 1–9) indicate that most behavior-analysis systems remain at TRL 4–6. Several technologies extend into TRL 6–8, whereas few established systems reach TRL 9. Persistent barriers include domain shift under production conditions, annotation costs, inconsistent validation protocols, and limited economic accessibility. By linking welfare relevance, evaluation level, and deployment evidence, this review identifies priorities for scalable and actionable monitoring in commercial laying-hen production. Full article

Laser powder bed fusion (LPBF) is a disruptive additive manufacturing process for producing high-performance Inconel superalloy parts with complex shapes for the aerospace, energy, and other demanding industries. However, uniform part quality remains a persistent challenge, as process parameters, melt-pool dynamics, microstructural evolution, defect formation, and mechanical performance are closely coupled across a wide range of spatial and temporal scales. In previous reviews, these dimensions have been considered in isolation with limited insight into their interactions and implications for predictive process control. The present review aims to address this lacuna by proposing a unified Process–Structure–Property–Control (PSPC) framework for LPBF-produced Inconel 625, 718, and 738. The discussion begins with material attributes governing alloy processability, and then synthesises the melt-pool physics governing thermal behaviour, solidification, and energy transfer. Attention then turns to a critical assessment of grain evolution, defect formation, and process stability, showing how the thermal history governs microstructural development and, in turn, mechanical performance via linked process–structure–property relationships. Progress in multiscale numerical modelling, such as finite-element analysis, computational fluid dynamics, phase-field modelling, cellular automata, and phase-diagram calculation (CALPHAD), is reviewed to establish a comprehensive modelling ecosystem for predictive LPBF. The review also discusses the potential of emerging technologies, such as beam shaping, multi-laser processing, in situ monitoring, artificial intelligence, and powder recyclability, to increase the robustness and productivity of the process. Building on these advances, a digital-twin-enabled predictive-manufacturing framework that integrates physics-based models, data-driven algorithms, and real-time monitoring is introduced to enable closed-loop process optimisation. The review ends with a scientific synthesis and future research roadmap for intelligent, reliable, and autonomous LPBF of next-generation Inconel superalloys. Full article

Accurate carbon price prediction and fluctuation analysis are essential for carbon market risk management and achieving carbon neutrality goals. However, carbon prices exhibit complex multi-scale nonlinear dynamics intertwined with time-varying external factors, hindering reliable forecasting. This study constructs a hybrid prediction framework integrating CEEMDAN, Sample Entropy (SE) reconstruction, and the Coefficient of Variation (VC) ensemble algorithm. SHapley Additive exPlanations (SHAP) quantifies scale-specific nonlinear factor contributions, while TVP-SV-VAR captures dynamic carbon price-driver correlations. Empirical results indicate that the CEEMDAN-SE preprocessing strategy significantly improves the prediction accuracy of baseline models. The CEEMDAN-SE-GRU model achieves optimal performance, with an R² of 0.96 and over 60% reductions in both MSE and MAE relative to the baseline GRU model. Meanwhile, the VC ensemble outperforms single models and alternative fusion strategies. SHAP identifies scale-heterogeneous drivers: short-run prices follow sentiment and macro outlooks, medium-run trends tie to industrial costs and global markets, long-run paths align with energy transition and global climate governance. The TVP-SV-VAR model uncovers significant time-varying spillover effects on raw carbon prices. Based on these findings, we recommend establishing multi-layered dynamic monitoring and early warning systems, constructing a differentiated and adaptive policy toolkit, refining cross-market risk isolation and buffering mechanisms, and advancing institutional improvements through gradual implementation. Full article