Search Results (5,390)

Wear on historic staircases is often used as evidence for conservation assessment and historical interpretation, yet existing studies are largely descriptive and rarely provide a quantitative explanation of how observed wear relates to long-term pedestrian use. To address this limitation, this paper proposes a physics-constrained inversion framework for analyzing directional preference and wear-related usage regimes from geometric wear profiles of heritage staircases. An Archard-type wear model is extended to account for spatial footfall distribution, cumulative abrasion, material deterioration, and environmental loss, and the reconstruction problem is formulated as an inverse parameter estimation task. Bayesian uncertainty quantification is introduced to estimate posterior distributions, credible intervals, and parameter coupling. A unified workflow is developed for staircase geometry representation, reference surface reconstruction, profile extraction, regularized height field construction, forward simulation, and inverse solution. Nine synthetic scenarios with different usage levels and directional preferences are tested under 1%, 3%, and 5% noise, and the method is further applied to a publicly available three-dimensional heritage staircase model. Under 3% noise, profile correlation coefficients for three representative scenarios reach 0.9646, 0.9807, and 0.9868, indicating strong recoverability of geometric wear morphology under model-consistent conditions. The results indicate that directional preference, material hardness, and some degradation-related parameters are identifiable, whereas pedestrian volume and the wear coefficient show strong compensation. Overall, the proposed framework provides a quantitative basis for identifying directional asymmetry, analyzing parameter identifiability, and supporting geometry-based interpretation in heritage staircase studies. Full article

With the increasing integration of distributed energy sources, fault restoration in power distribution systems faces challenges in terms of real-time performance and adaptability. To effectively manage the uncertainty and volatility of distributed generation, this paper proposes a rapid self-healing strategy based on a dynamic operational grid. By enabling real-time topological reconfiguration and utilizing adaptive resource allocation, the proposed method accommodates the inherent fluctuations of distributed energy sources. First, a dynamic grid weighted graph theory model is constructed, and an emergency control strategy combining particle preprocessing and stepwise optimization is designed to achieve rapid fault response. Then, a “primary-secondary” two-tier restoration mechanism is established: the primary layer integrates the Floyd algorithm with optimized adaptive dynamic programming to achieve millisecond-level restoration of critical loads; the secondary layer employs an improved particle swarm algorithm incorporating Lévy flight perturbations and adaptive weighting to maximize the restoration of general loads. Simulations on a 56-node system demonstrate that this method achieves 100% restoration of critical loads under various fault scenarios. Even under extreme conditions, it can restore 90.88% of secondary loads and 44.63% of tertiary loads, forming a self-healing system characterized by “second-level detection and minute-level restoration,” thereby significantly enhancing system resilience. Full article

To improve the sustainability of intelligent building operation and enhance grid adaptability in the presence of uncertainty, this paper presents a coordinated optimization method that jointly exploits virtual energy storage and waste heat recovery. A thermal modeling framework is developed to represent the coupling relationships among air conditioning operation, waste heat utilization, and indoor comfort requirements. On this basis, building thermal inertia is incorporated into an IDM-informed two-stage robust optimization framework, where distributional bounds derived from the Imprecise Dirichlet Model are transformed into data-driven interval uncertainty sets for wind–photovoltaic output and outdoor temperature. To make the model computationally tractable, the column-and-constraint generation method is employed for iterative solution. Numerical results verify that the proposed method can effectively unlock the flexibility of the cooling system and improve the utilization of recoverable heat resources while maintaining acceptable indoor comfort, even under adverse operating conditions. Overall, the proposed strategy strengthens system resilience, reduces carbon-related operational pressure, and provides more dependable demand-side support for secure power system operation. Full article

Aircraft targets in SAR imagery often exhibit discrete scattering characteristics, significant variations in pose and scale, strong speckle noise in background clutter, and complex background interference, which jointly hinder stable structural feature extraction and accurate target localization. Existing detectors for SAR aircraft recognition primarily rely on bounding-box regression and classification; they do not completely exploit target structural cues, spatial attention, and frequency-domain information. To address these limitations, we propose a collaborative detection framework that integrates an uncertainty-aware keypoint-driven module (UAKM) with a fractional Fourier convolution backbone (S-FRConv). UAKM introduces a center-keypoint regression branch that jointly predicts keypoint coordinates and Laplacian scale parameters and employs a 2D Laplace negative log-likelihood loss to estimate uncertainty. The derived dense uncertainty heatmap is then used as spatial attention weights to guide distribution-based regression and multi-scale feature re-weighting, without requiring any additional annotations. S-FRConv embeds the Fractional Fourier Transform into shallow backbone layers and C2f modules, enabling joint spatial–spectral feature modeling that suppresses speckle noise and enhances edge and orientation representations. Experiments on the public SAR-AIRcraft-1.0 dataset demonstrate that the proposed method systematically improves the detection performance. For the Nano model, the overall mAP50 increases from 0.810 to 0.867, and the mAP 50:95 improves from 0.637 to 0.655 compared with the baseline, corresponding to gains of 5.7 and 1.8 percentage points, respectively. These results validate the effectiveness and generalization potential of combining uncertainty-driven spatial attention with fractional spectral feature enhancement for SAR aircraft target detection. Full article

Open-set classification for remote sensing requires models that simultaneously achieve high accuracy on known land-cover types and reliably detect novel classes absent from the training distribution—a capability essential for real-world deployment where new classes routinely emerge. Existing multimodal fusion approaches for hyperspectral imagery (HSI) and LiDAR are primarily designed for closed-set scenarios and lack robust uncertainty modeling for unknown detection. We propose a post hoc calibrated multimodal open-set framework with three tightly integrated components. First, an Uncertainty-Aware Gating Fusion (UAGF) module dynamically weights HSI and LiDAR features per sample based on modality reliability and produces a gating uncertainty signal reflecting fusion confidence. Second, an Iterative Feedback Refinement (IFR) module progressively refines fused representations over multiple iterations and captures convergence dynamics, where stable convergence indicates known samples while high feature-change variance identifies potential unknowns. Third, a compact two-signal open-set detector combines gating uncertainty and refinement variance through an EVT (Weibull)-based post hoc calibration mechanism fitted exclusively on known validation samples. The framework follows a strict zero-unknown-supervision protocol: the multimodal backbone is trained using only known-class samples, and the open-set decision threshold is derived solely from the known validation score distribution. This design decouples representation of learning from open-set decision learning, improving robustness and avoiding the objective conflicts that arise in joint training. Comprehensive experiments on three benchmark datasets—Houston2013, Muufl, and Augsburg—demonstrate that the proposed method achieves 92.79%, 84.47%, and 80.99% overall accuracy and 76.48%, 63.91%, and 56.81% unknown accuracy, outperforming the closest multimodal competitor HyLiOSR by up to 32.4 pp in unknown accuracy while maintaining competitive closed-set performance. Full article

A Bayesian convolutional neural network (BCNN) quantifies prediction uncertainty by introducing randomness into weights or activations, which is important for safety-critical applications such as medical diagnosis and autonomous driving. However, BCNN inference typically relies on Monte Carlo sampling requiring multiple forward passes, leading to computation and energy consumption far beyond standard CNN hardware acceleration. FPGA, with its parallel processing, reconfigurability, and high-energy efficiency, are ideal platforms for dedicated BCNN accelerators. This paper designs and implements an FPGA acceleration method for BCNN-using high-level synthesis. First, convolution, pooling, and fully connected modules are individually optimized. Then, a mean/variance dual-path parallel expansion is adopted, combined with mixed-precision quantization and global scaling compensation, local reparameterization sampling, parameter reordering, and ping-pong buffering, achieving low resource usage and high-energy efficiency while enabling uncertainty evaluation. Experimental results on Bayes VGG16 show resource utilization of 24,776 LUT, 23,378 FF, 115 BRAM, and 129 DSP, with total power of 2.049 W. Compared with an unoptimized Bayesian implementation, the proposed design reduces inference latency to about one-third, and its latency is only 17% higher than that of the classical VGG16. Compared with PC-based floating-point models, the accuracy loss on four BCNN models (tested on CIFAR-10) is within 1%. The predictive entropy effectively distinguishes normal, noisy, and out-of-distribution (OOD) samples, validating the uncertainty quantification capability of the BCNN FPGA accelerator. Full article

Geopolitical risks—including export controls, entity listings, and end-use restrictions—have become a major source of disruptions in semiconductor supply chains. The impact of such disruptions depends not only on the policy trigger itself but also on the vulnerability of cross-regional partnerships between supply chain partners. Specifically, under the same policy regime, firms with weak partnerships suffer far greater disruption than those with strong partnerships. Apart from risk propagation, this vulnerability also propagates through the supply chain: when an upstream supply channel has weak partnerships, its downstream stages also become more exposed to disruptions. We call this phenomenon vulnerability propagation. Existing Bayesian Network (BN) frameworks portray risk propagation through fixed parameters that do not reflect partnership vulnerability and cannot capture vulnerability propagation. To fill this gap, we propose a Dependency-Robust Bayesian Network (DeRBN) that conditions risk propagation parameters on the partnership vulnerability. A robust worst-case oriented evaluation method is developed to assess the disruption risk under data scarcity. Computational experiments on a typical semiconductor supply chain network show that (i) moving from all-strong to all-weak partnerships increases the worst-case risk by approximately 24%, (ii) the dependency-induced risk amplification is unevenly distributed across supply channels, with the most influential channel contributing approximately 2.2 times the marginal risk of the least influential one, and (iii) the relative ranking of vulnerability profiles remains perfectly stable under varying levels of data uncertainty. These results suggest that DeRBN has the potential to serve not only as a risk assessment tool but also as a diagnostic instrument for identifying and prioritizing the most vulnerable supply channels for targeted risk mitigation. Full article

The growing penetration of electric vehicles (EVs) and distributed photovoltaic (PV) generation is increasing operational uncertainty in distribution networks and intensifying long-standing challenges such as higher power losses, rising peak demand, and voltage instability. To address these issues, this paper proposes a multi-objective optimization framework for the strategic placement of smart meters equipped with demand response (DR) capability in radial distribution systems. Unlike conventional placement approaches that mainly focus on monitoring or reducing non-technical losses, the proposed method integrates active load control into the planning stage and explicitly considers the stochastic behavior of loads, PV generation, and electric vehicle charging stations (EVCSs). The problem is formulated with four objectives: minimizing total power losses, substation peak demand, voltage deviation penalty, and installation cost. A scenario-based stochastic model is employed to represent operational variability across the network. The resulting nonlinear mixed discrete optimization problem is solved using the Non-dominated Sorting Genetic Algorithm II (NSGA-II), an evolutionary multi-objective optimization technique that generates a set of Pareto-optimal solutions representing trade-offs among conflicting objectives. Smart meters are allowed to curtail a portion of controllable demand during critical loading conditions, which helps reduce feeder loading and improve voltage profiles. The proposed approach is evaluated on the IEEE 33-bus and IEEE 69-bus distribution systems. Simulation results demonstrate significant reductions in power losses and peak demand, with the IEEE 33-bus system achieving up to a 26.2% reduction in power losses and 52.5% reduction in substation peak demand compared with existing metaheuristic approaches. The results also indicate improved voltage stability and effective performance in the IEEE 69-bus system, confirming the importance of topology-aware DR-enabled planning. Overall, the findings show that embedding demand response capability within smart meter allocation can significantly enhance the resilience and operational efficiency of modern distribution networks with high EV and PV penetration. Full article

Green hydrogen is increasingly discussed as an energy carrier that can link electricity, gas, heat, and transport sectors. However, many existing reviews address this topic from separate viewpoints, such as hydrogen production technologies, Artificial Intelligence (AI) applications, or system integration, with less attention to how policy and market conditions affect deployment. This review brings these related aspects together in one structured discussion. The paper first reviews the hydrogen supply chain, including production, storage, transport, and utilization. It then discusses an integrated multi-energy architecture in which hydrogen interacts with electricity, natural gas, heat, and cooling networks. Policy instruments in five major economies, including the European Union, the United States, China, Japan, and India, are compared. The review also summarizes the main barriers to large-scale deployment, including high production costs, limited infrastructure, technological challenges, regulatory uncertainty, and supply-chain constraints. In addition, the current market structure and selected large-scale hydrogen projects planned in the United States are reviewed. The paper also examines the role of artificial intelligence in green hydrogen systems. AI applications are grouped into four main stages of the hydrogen value chain: forecasting renewable energy generation, improving electrolyzer design and operation, optimizing storage and distribution, and supporting system-level techno-economic assessment. Recent Machine Learning (ML) studies are compared based on their methods and their contributions to operation and planning. Overall, this review highlights the role of AI in enabling green hydrogen integration within multi-energy systems. Full article

Meta-analysis is a statistical tool commonly used within systematic reviews to synthesize quantitative evidence, but individual studies with atypical results or disproportionate influence can materially affect pooled estimates, heterogeneity estimates, and the conclusions drawn from evidence syntheses. Conventional outlier and influence diagnostics for meta-analysis are useful, but their interpretation often relies on asymptotic reference values or informal rules of thumb, which may be inadequate when the number of studies is limited or heterogeneity is substantial. We introduce boutliers, an R package that implements bootstrap-calibrated outlier detection and influence diagnostics for fixed-effect and random-effects meta-analysis. The package provides leave-one-study-out diagnostics based on Studentized deleted residuals, relative changes in the variance of the pooled effect estimator, and relative changes in the between-study variance, together with a likelihood-ratio diagnostic based on a mean-shifted model. For each diagnostic measure, bootstrap reference distributions, critical values, and p-values are provided to support quantitative interpretation of influential studies. We describe the statistical framework, implementation, and practical use of the package and illustrate its application using a real published meta-analysis dataset on spinal manipulative therapy for chronic low back pain. The boutliers package provides accessible tools for incorporating uncertainty-calibrated influence diagnostics into routine meta-analytic practice. Full article

This study adapted and applied a spatially distributed analytical model to estimate the annual representative leached fraction and the annual potential leached mass of atrazine in the Cauquenes catchment in Chile under contrasting Mediterranean hydroclimatic conditions. The model was based on van der Zee and Boesten and Rakonjac et al. and was modified to account for the strong seasonality of precipitation and evapotranspiration by using representative daily hydrological conditions derived from monthly averages. Spatially distributed soil, climate, land-cover, and atrazine application data were integrated at the pixel scale, including locally corrected soil organic carbon, hydraulic properties, precipitation, evapotranspiration, leaf area index, and annual atrazine dose. The model was applied to two contrasting years, 2018 and 2023, and outputs were aggregated at the pixel, land-cover, hotspot, and catchment scales. The results showed a marked hydroclimatic control on potential atrazine leaching. In the drier year, 2018, both the annual representative leached fraction and the annual potential leached mass were generally very low across the catchment, whereas in the wetter year, 2023, moderate-to-high leaching values became much more spatially extensive, and hotspot areas expanded substantially. At the catchment scale, potential leached mass increased from 0.088 kg in 2018 to 179.784 kg in 2023, while the percentage of applied mass potentially leached increased from 5.50 × 10⁻⁵% to 0.112%. Land-cover classes influenced the results both through the spatial allocation of atrazine application and through LAI-dependent partitioning of evapotranspiration. Global sensitivity analysis using the Morris method identified K_OC and DT50 as the dominant controls on annual potential leached mass, and spatial uncertainty propagation was performed. Overall, the proposed framework provides a potential annual screening estimate and may serve as a preliminary screening tool to prioritize areas for targeted monitoring and future model benchmarking in Chile. Full article

South Africa remains one of the world’s most coal-dependent electricity systems, with coal accounting for 81.57% of generation in 2023. Despite policy interventions to diversify the energy mix, structural change is slow to emerge. This study provides the first integrated, empirically calibrated forecast of South Africa’s coal-to-clean-energy transition using a unified modelling architecture that combines structural break analysis, Bayesian estimation, and an enhanced Monte Carlo simulation with dynamic volatility (10,000 stochastic pathways). The findings confirm a permanent structural break in 2011 that coincided with the implementation of REIPPPP, following which coal began a statistically significant and sustained decline of approximately 0.7–0.75% points per year. The simulation produced a full probability distribution for the transition year (2053) when coal share falls below 50%. This demonstrated that long-term uncertainty rises faster than linearly and that, under current conditions, deep decarbonisation milestones are unattainable before mid-century. Policy scenario experiments also demonstrated that accelerating the annual decline rate necessitates coordinated, synergistic policy portfolios rather than isolated interventions. These findings provide a transparent, uncertainty-explicit forecast of South Africa’s transition trajectory, as well as a decision-relevant evidence base for planning, regulation, and equitable transition implementation. Full article

Although fine-grained spatial knowledge of the urban population distribution is fundamental for effective urban management, traditional census data lack sufficient resolution. Current disaggregation methods often struggle to probabilistically fuse heterogeneous data, such as noisy mobile signaling and building attributes, while ensuring hierarchical consistency between micro-level predictions and macro-level ground truth. To address these gaps, this study proposes a Bayesian-informed hierarchical learning (BIHL) model framework for building-level population estimation. The methodology integrates three distinct layers: (1) a data-driven prior model using a LightGBM ensemble to generate initial probabilistic estimates and uncertainty weights; (2) an enhanced neural network posterior estimator featuring a multi-branch architecture—incorporating Zone Bias Embedding and Zone Interaction networks—to capture non-linear urban dynamics and spatial heterogeneity; and (3) a constrained optimization layer utilizing a hierarchical loss function that enforces strict consistency between aggregated building estimates and official census data through dynamic curriculum learning. Through empirical validation in Haidian District, Beijing, it is demonstrated that the BIHL framework significantly outperforms baseline models (MLR, Random Forest, and LightGBM), achieving a Mean Absolute Percentage Error (MAPE) of 11.36%. This study confirms that incorporating building-level spatial locations and residential categories is vital for mitigating “spatial smoothing” and systematic under-prediction in high-density areas. This framework provides a robust, high-fidelity solution for generating residential population layers, which are essential for city planning. Full article

Multivariate time-series anomaly detection on physical sensor networks faces three challenges that generic deep learning models inadequately addressed: heterogeneous sensor reliability, context-dependent anomaly scoring, and inactionable binary outputs lacking per sensor attribution. We propose an uncertainty-aware Temporal Convolutional Network (TCN) framework built on two tightly integrated uncertainty-driven components: (i) an Adaptive Uncertainty-Aware Attention (AUAA) mechanism that gates temporal attention weights by per sensor predictive uncertainty obtained from Monte Carlo dropout; and (ii) a Dynamic Weight Adapter that learns context-sensitive blending of reconstruction error and uncertainty via a GRU over weight history. The architecture also includes an exploratory per sensor attribution head, which we audit rather than claim: a controlled-perturbation test shows it is not yet causally faithful. We complement the empirical architecture with two distribution-free theoretical results: a Chebyshev-type false-positive bound on the hybrid anomaly score, and a Monte Carlo posterior moment convergence result at rate $O\left(M^{-1/2}\right)$. Evaluated on four-month indoor air quality sensor data, the Full Enhanced model achieves $R^2=0.9988$ and MSE $1.65\times {10}^{-4}$, a $25.2\%$ MSE reduction over the Base TCN ($R^2=0.9984$, MSE $2.20\times {10}^{-4}$). Because the IAQ stream is unlabeled, the primary quantitative detection evaluation uses the labeled Skoltech Anomaly Benchmark (SKAB), a publicly available industrial water-circulation corpus disjoint from the IAQ training distribution; it yields an 8.8 × F1 advantage ($0.477$ vs. $0.054$) and a 14.4 × recall advantage ($0.418$ vs. $0.029$) for the proposed model configuration over the Base TCN at a validation-calibrated threshold applied without retuning. Against twelve established detectors under a unified protocol, the proposed model attains the best F1 and recall, while the strongest reconstruction baselines retain higher precision and a marginally higher ROC-AUC, a recall-driven trade-off. Ablation isolates each component’s contribution, the detector degrades gracefully under channel masking and noise, and the distribution-free false-positive bound is empirically respected. The framework retains a low inference cost ($0.16$ ms per window at $M=20$ Monte Carlo samples, including the uncertainty pass). Full article

Autonomous exploration requires reliable viewpoint evaluation from partial observations. Existing reinforcement-learning methods commonly approximate each action by using a scalar expected return, which is inadequate in unknown environments with heterogeneous topology. Similar local observations may correspond to different hidden structures, causing the same action to produce divergent information gains and travel costs. This perceptual aliasing makes value estimation uncertain and can propagate biased decisions through temporal-difference learning. To address this problem, we propose a distributional-value learning framework for autonomous exploration. The core idea is to replace scalar action evaluation with return-distribution estimation, where the distribution mean measures long-term utility and the variance characterizes uncertainty induced by hidden topology. Based on this formulation, task-oriented value learning is developed to stabilize target estimation and suppress optimistic viewpoint evaluation under conditions involving uncertain returns. Simulation experiments indicate that the proposed adaptation can reduce redundant motion and improve exploration efficiency over representative baselines in the tested scenarios, while a preliminary real-robot deployment suggests the feasibility of transferring the learned policy to a physical platform. Full article