Search Results (525)

Aiming at the problems of extremely scarce measured samples and significant domain shift between simulated and measured data in automatic target recognition (ATR) of air targets for spaceborne radar, this paper proposes an inverse synthetic aperture radar (ISAR) image recognition method for air targets combining physics-driven data augmentation guided by detection prior information with domain adversarial transfer learning. First, the mapping relationship between scattering point projection and ISAR images is established by using the target 3D point cloud and radar observation geometric priors, and a 2D sinc kernel function is introduced for energy distribution rendering. Then, under the unsupervised transfer learning paradigm, aiming at the distribution inconsistency between augmented data (source domain) and unlabeled simulated data (target domain), this paper designs a cross-domain recognition task experiment including six types of typical aircraft targets, and compares the cross-domain recognition performance of three transfer learning methods (model fine-tuning, deep domain confusion (DDC) and domain-adversarial neural networks (DANN)) on the target domain. Meanwhile, t-distributed stochastic neighbor embedding (t-SNE) visualization is used to analyze the feature distribution alignment ability of the models. Simulation experiments show that the DANN model with a dynamic inversion coefficient introduced in the gradient reversal layer (GRL) achieves a recognition accuracy of 99.5% on the unlabeled target domain, which is significantly superior to the model fine-tuning and DDC methods. Moreover, it makes the feature distributions of source and target domain samples highly overlapping, and maintains a strong inter-class discriminability while eliminating the domain shift. The proposed scheme provides a physically interpretable and robust technical path for few-shot radar target image recognition. Full article

Electroencephalographic (EEG) signals provide macroscopic observables of complex neural dynamics. We introduce a horizon-inspired framework in which measured EEG signals are modeled as projections of a complex wave-like representation constrained by an effective boundary analogous to an event horizon. In this formulation the signal amplitude obeys a renormalization-group scaling relation while EEG spectral entropy parameterizes the accessibility of observable modes. The resulting solutions generate oscillatory structures whose geometry and spectral signatures can be explored through signal analysis and sonification. This mapping between entropy-based neural observables and wave-like signal representations provides a physically motivated framework linking entropy measures, scale-dependent dynamics, and observable neural oscillations. The work is intentionally conceptual. It provides a falsifiable framework intended to stimulate future empirical investigations. Full article

In the assessment of bearing capacity for in-service bridge pile foundations, static load tests are costly, destructive, and difficult to scale. The traditional dynamic formula approach relies heavily on an empirical dynamic–static conversion coefficient that introduces considerable uncertainty. To address these limitations, this study proposes a non-destructive evaluation method for pile foundation bearing capacity based on measured dynamic stiffness and machine learning algorithms. Using data from a highway bridge inspection project, a dataset comprising 680 piles was compiled, including measured dynamic stiffness, geometric parameters, and design load information. An end-to-end binary classification model was constructed to map multidimensional physical features to an engineering decision target, namely, whether the bearing capacity meets the design requirement. The performance of several algorithms was compared, including logistic regression, random forest, and gradient boosting decision tree (GBDT). Among the evaluated models, the GBDT model demonstrated the best capability for capturing the complex nonlinear pile–soil interactions. On an independent test set, it achieved an accuracy of 96.3% and an F1 score of 0.96, with a very low false-negative rate, satisfying the high precision required for engineering safety screening. Feature importance analysis indicates that measured dynamic stiffness contributed approximately 42% to the classification outcome, establishing it as the dominant indicator for detecting capacity deficiencies and reinforcing its physical relevance as a key health indicator for pile foundations. This study demonstrates that data-driven methods can effectively circumvent the uncertainty associated with traditional empirical coefficients, providing a promising approach to the health monitoring and rapid evaluation of in-service bridge pile foundations. Full article

Transmission lines in Southwestern China are highly exposed to compound hazards induced by extreme winds and ice and snow conditions. This study assesses future changes in extreme wind hazards and their spatial overlap with baseline ice susceptibility under the SSP2-4.5 emission scenario, using high-resolution dynamically downscaled climate projections. Compared to the historical period (1995–2014), the results indicate a marked intensification of extreme spring wind events over northwestern Southwestern China and the transitional zone between the Sichuan Basin and the Hengduan Mountains during 2041–2060. The occurrence frequency of wind speeds exceeding historical 50-year return levels is projected to increase by 5–10 times in complex terrain, particularly along the Golmud–Qaidam belt. The Comprehensive Extreme Wind Index (CEWI) identifies the Golmud–Wulanwusu–Qaidam river basin belt as the region of highest wind hazard amplification. Meanwhile, analysis of historical observations reveals that icing-prone conditions occur on more than 25 days each spring in the Nyenchentanglha Mountains and southeastern Tibetan Plateau valleys, establishing a baseline map of ice susceptibility. Due to methodological limitations in projecting future icing, this susceptibility map is used as a static indicator of ice-prone areas. By superimposing projected wind intensification onto the baseline ice susceptibility map, four relative hazard exposure categories are delineated. Regions of highest potential exposure are concentrated in the Bayan Har Mountains and portions of the western Hengduan Mountains, whereas northwestern basins are dominated by high wind risk alone. These results reveal pronounced spatial heterogeneity in the relative amplification of compound hazards under future warming and provide a scenario-informed scientific basis for prioritizing regions in disaster risk reduction and resilient planning of transmission infrastructure in mountainous regions. Full article

The widespread deployment of unmanned aerial vehicles (UAVs) in remote sensing has highlighted the necessity for robust object detection methods in UAV imagery. However, high-altitude UAV imagery suffers from severe background clutter that obscures target discriminability and extreme scale variations that degrade fine-grained features. To address these challenges, we propose CSSA-YOLO, a clutter-suppressed and scale-aware detection framework built upon YOLOv9. Specifically, we project dense spatial features into a low-rank token space via a Semantic Bottleneck Module (SBM). This projection acts as an information bottleneck, suppressing the background clutter while robustly retaining critical target semantic and structural priors. Furthermore, we develop a Scale-Aware Complete-IoU (SA-CIoU) loss to tackle gradient attenuation for small objects. By analytically integrating a scale-aware modulation factor with a dynamic alignment mechanism into localization optimization, SA-CIoU shifts the optimization priority to the precise localization of small and hard-to-detect instances. Extensive experiments on the VisDrone2019 benchmark demonstrate the superiority of our approach, with CSSA-YOLO achieving an mAP@0.5 of 46.0% and an mAP@0.5:0.95 of 28.4%, yielding an absolute 1.4% improvement over the YOLOv9 baseline. Furthermore, when integrated with a P2-enhanced YOLOv9 architecture, our method achieves a remarkable mAP@0.5 of 49.5%. Notably, evaluations across diverse scenarios, including the infrared (IR) thermal HIT-UAV benchmark and PCB defect detection datasets, further demonstrate the generalizability and robustness of our framework. Full article

In smart construction, identifying the competencies required of engineering–procurement–construction (EPC) safety directors is important for improving personnel selection, training, and safety-governance effectiveness. Drawing on dynamic capabilities theory, this study develops an exploratory competency framework for EPC safety directors in smart-construction contexts. A mixed-method design was adopted, combining a structured literature review, bibliometric mapping with CiteSpace, semistructured interviews, expert review, and questionnaire-based item screening. Questionnaire data from 189 valid respondents were analyzed using descriptive statistics, item analysis, Cronbach’s alpha, and KMO/Bartlett tests to preliminarily assess the internal consistency and structural suitability of the proposed indicators. The results indicate that the retained exploratory framework comprises three higher-order dimensions—sensing, seizing, and reconfiguring—covering six competency elements and eighteen indicators after the remaining trend-sensing indicator was integrated into data analytics. Compared with conventional safety-management competency frameworks, the proposed framework places greater emphasis on data analytics, intelligent systems application, and cross-departmental coordination in digitally enabled project environments. The framework can be implemented as a role-profile template for recruitment, training-needs diagnosis, and performance appraisal of EPC safety directors, while further empirical validation is required before it is used as a standardized measurement scale. Full article

The accurate reconstruction and real-time prediction of transient three-dimensional flow fields in hydraulic turbines are critical for ensuring operational stability under renewable energy-driven variable-load conditions, yet conventional computational fluid dynamics (CFD) approaches remain too computationally expensive for digital twin applications. This paper proposes a hybrid framework that integrates Proper Orthogonal Decomposition (POD) with Long Short-Term Memory (LSTM) networks to reconstruct and predict the unsteady flow field within the draft tube of a Francis turbine using only four sparse wall-mounted pressure sensors. The methodology begins with high-fidelity Large Eddy Simulation (LES) to establish a comprehensive flow field database under Part Load (PL), Best Efficiency Point (BEP), and High Load (HL) conditions. POD is subsequently applied to extract dominant coherent structures and their temporal coefficients, achieving a low-dimensional representation of the high-dimensional flow field. A comparative analysis between standard POD and weighted POD reveals that under the PL condition characterized by a strong double-helical vortex rope, the weighting effect is significant—standard POD captures 90% of the total energy with the first 2 modes, while weighted POD requires up to 8 modes to reach the same threshold. Under the BEP and HL conditions, the energy distributions of the two methods are nearly identical, yet weighted POD still yields cleaner spatial modes with sharper vortex boundaries and fewer spurious wall-region vortices. An LSTM network is then trained to establish a mapping between time-series signals from the four sensors and the POD temporal coefficients. The results demonstrate that LSTM prediction performance is governed by the spatial correlation between each mode and the sensor locations rather than by temporal regularity. Modes that project strongly onto the sensor locations—PL Modes 1–2 (R² = 0.85 and 0.513), BEP Mode 1 (R² = 0.96), and HL Mode 1 (R² = 0.92)—are reliably predictable, while PL Mode 3 and HL Mode 2, despite their regular temporal oscillations, yield strongly negative R² values (−3.366 and −186.6) because their spatial structures are concentrated away from the wall. With a condition-adaptive strategy predicting only sensor-correlated, energetic modes, the reconstructed pressure fields achieve mean L2 relative errors of 17.01% (PL), 7.17% (BEP), and 12.91% (HL). Because the mean flow dominates total pressure energy (86.66–98.07%), the effective absolute error is substantially lower. The proposed POD-LSTM framework successfully bridges the gap between high-fidelity CFD and real-time monitoring, enabling full-field flow state estimation from sparse sensor measurements without the computational expense of online simulations. This capability is particularly valuable for digital twin applications in hydraulic turbines operating under rapidly varying renewable energy conditions. Full article

The growing need to enhance observability in distribution networks has driven the development of load pseudomeasurement generation methods, particularly under partial smart meter (SM) penetration. This paper proposes a load pseudomeasurement framework that builds representative daily load profiles (load curves) from hourly SM time series using clustering techniques, with and without weather information. Markov chain models are then used to capture day-to-day dynamics by predicting the most likely next-day profile to be assigned to customers without SM. To enable this transfer, a hierarchical grouping scheme based on monthly energy consumption is introduced to map behaviors from SM-equipped customers to customers without SM measurement. The methodology is validated with real residential data from the Low-Carbon London project under multiple observability scenarios including different SM availability levels, where SM measurements are withheld from the inputs to emulate customers without SM measurement, and the resulting pseudomeasurements are benchmarked against the original measurements. The results show that the Euclidean representative curve method achieved the most robust overall performance, with a minimum MAE of 1.65 in the Reduced × 75% SM configuration. The best-performing configuration depended on the observability level: Reduced was the most robust option under medium-to-high observability, whereas Temp_reduced with a 21-day window performed best under the lowest-observability condition. In addition, the Euclidean method showed low practical deviation in the Reduced × 25% SM case, with a bias of 0.63 and Cohen’s d = 0.27. Overall, the proposed approach accurately reproduces the hourly load shape and captures inter-day variability under partial observability conditions. Full article

Mobile robot navigation remains challenging when fast convergence, collision avoidance and deployability must be satisfied simultaneously. The original Q-learning with Artificial Potential Field (QAPF) paradigm is extended in this paper with three coordinated mechanisms that together yield a reported-horizon convergence reduction of approximately four orders of magnitude (from $\sim 3\times {10}^6$ episodes to $\sim 200$ to 230 episodes under the present protocol) and an internal-ablation collision-rate reduction of approximately one order of magnitude ($6.2\%$ to $0.3\%$), and that open a new capability frontier covering dynamic obstacles, multi-robot coordination, energy-aware velocity modulation and embedded-deployable inference timing. The first mechanism is a potential-based reward-shaping schedule whose unclipped fixed-weight form follows the policy-invariant shaping theorem, while the implemented clipped and time-varying form is used as an empirically stable approximation. Under the present experimental protocol, the reported convergence horizon is reduced from the $\sim 3\times {10}^6$ episodes reported for the original QAPF formulation to approximately 200 to 230 episodes; this comparison is protocol-dependent and is not claimed as a controlled one-to-one runtime speedup. The second mechanism is a discrete Control Barrier Function (CBF)-inspired action filter (thediscrete filter described in this paper is inspired by the continuous-time CBF literature, but does not carry a forward-invariance proof; it is used as an empirical safety mechanism rather than as a formal Control Barrier Function in the formal continuous-time sense) with per episode visit memory by which the held-out collision rate is reduced from $6.2\%$ for QAPF alone to $0.3\%$ while $93.8\%$ task completion is maintained, where this collision-rate comparison is internal to the QAPF ablation because the prior QAPF reference does not report a comparable held-out collision metric. The third mechanism is a set of extensions to dynamic obstacles, two-robot cooperative navigation under a centralized scheme (with an explicit $\mathcal{O}(N^2)$ scaling-cost analysis and three decentralization strategies for fleets beyond the small-N regime), curriculum learning and energy-aware velocity modulation. Disturbance robustness tests, empirical timeout/stagnation detection for unreachable-goal cases, i7 reference inference timing with projected embedded-device latencies, multi-axis generalization over obstacle density and grid size, scalability analysis for centralized multi-robot coordination and a scope comparison against A* and RRT* are added by the revised evaluation. Across 30 independent seeds on held-out static maps, $94.5\pm 2.1\%$ success is achieved by adaptive QAPF while $93.8\pm 2.3\%$ success with $0.3\pm 0.4\%$ collisions is achieved by QAPF+CBF. Under a separate finite robustness suite, $85.0\pm 4.1\%$ success is retained by QAPF+CBF in the combined disturbance regime. The timing study indicates that the 20 Hz real-time threshold is comfortably exceeded by all methods on the measured i7 reference platform and by all projected embedded-device equivalents. The results show that a lightweight and safety-oriented navigation policy for grid-based mobile-robot settings can be provided by APF-guided tabular reinforcement learning when it is paired with a discrete safety filter and a clarified energy and robustness analysis. Full article

Violations of Bell inequalities are commonly interpreted as evidence for nonlocal influences or as constraints on realist descriptions. We show that the failure of Bell-type factorizability arises naturally when observable outcomes are obtained through a non-injective mapping from an underlying configuration space. In this setting, the standard factorization assumption can be viewed as an implicit requirement that observable variables admit a jointly factorizable completion at the underlying level. We demonstrate that this requirement need not hold when the mapping from underlying configurations to observables is many-to-one. The resulting breakdown of probabilistic factorization does not rely on superluminal dynamics or hidden causal influences, but follows from information loss under projection. Observable outcomes correspond to equivalence classes of underlying configurations, preventing the assignment of independent local variables. We illustrate this mechanism with an explicit toy model producing Bell–CHSH violations while preserving operational no-signalling and statistical independence of measurement settings. The model is not intended to reproduce quantum correlations quantitatively, and may exceed the Tsirelson bound; its role is to isolate the structural origin of the violation. This analysis does not contradict Bell’s theorem, but identifies a class of effective descriptions for which its factorizability assumption does not apply. The framework preserves locality at the underlying level, introduces no additional hidden-variable dynamics, and does not modify quantum mechanics. It clarifies how classical factorization is recovered in regimes where the effective mapping becomes approximately injective. In the operator language of quantum theory, the same mechanism admits a natural reformulation in terms of reduction to an effective observable subalgebra by a noncommutative conditional expectation. Full article

Rapid urbanization in South Asian coastal cities is systematically dismantling natural cooling infrastructure, driving unprecedented urban heat island (UHI) intensification with severe consequences for human health, energy systems, and urban livability. Despite growing research attention, comprehensive frameworks that simultaneously capture temporal UHI dynamics, machine learning-based thermal projections, and community-grounded validation remain scarce, particularly for secondary coastal cities in tropical developing regions. This study addresses these gaps by investigating UHI dynamics in Chattogram City Corporation (CCC), Bangladesh, through three integrated methodological pillars: (1) multi-temporal remote sensing analysis using Landsat 5 and 8 imagery spanning 2005–2025; (2) comparative evaluation of five machine learning algorithms (LightGBM, Random Forest, XGBoost, SVM, and MLP) for land use/land cover (LULC) classification and land surface temperature (LST) regression, with iterative scenario projections for 2029, 2033, and 2037; and (3) a structured public perception survey of 384 residents validated through participatory mapping and focus group discussions. Landsat analysis revealed dramatic LULC transformations: built-up areas expanded 88% (12,649 to 23,719 acres), while waterbodies declined 53.1% and vegetation decreased 21.9%. Mean LST increased by 9.09 °C (from 30.94 °C to 40.03 °C), with mean UHI intensity rising from 19.59 to 33.88 standardized units over two decades. LightGBM achieved optimal LULC classification (F1-weighted: 0.765) while Random Forest best predicted LST (RMSE: 1.51, R²: 0.809). Projections indicate continued thermal escalation, with mean LST reaching 43.64 °C and UHI intensity exceeding 37.41 standardized units by 2037. Persistent thermal hotspots were identified in the southwestern coastal corridor, western industrial belt, and central business district. Community survey data corroborated satellite-derived patterns, with 73.44% of respondents observing environmental degradation, yet only 22% aware of formal heat mitigation policies, and 87% supporting vegetation-based cooling interventions. This integrated framework advances urban thermal monitoring in tropical coastal cities and provides spatially targeted, community-endorsed evidence for climate-responsive urban planning. Full article

Mangroves play a vital role in climate change mitigation due to their exceptional carbon sequestration capacity, as a highly productive blue carbon ecosystem. Current research on mangroves in Bamen Bay has been limited to short-term observations, lacking systematic analysis of long-term spatiotemporal dynamics and carbon storage. This study developed a decision tree method integrating SWIR1, NDVI, and NDMI, achieving high-accuracy mangrove mapping. Spatiotemporal dynamics from 2000 to 2020 were analyzed using the dynamic degree model, standard deviation ellipse, centroid model, and landscape pattern indices. Carbon storage was quantified through the InVEST model, grey prediction model, and scenario analysis. The results reveal significant mangrove expansion, with substantial net growth. Spatial aggregation strengthened despite persistent fragmentation, characterized by a shrinking standard deviation ellipse and northeastward centroid migration. Carbon storage increased considerably over the two decades. Under the baseline scenario, carbon storage would continue to grow by mid-century. Among alternative scenarios, the Green Revival scenario achieves the highest carbon storage, outperforming the baseline, while the Hard Preservation scenario achieves slightly above the baseline. The Missed Opportunity and Ecological Collapse scenarios project declines. This study provides a valuable framework for mangrove monitoring, carbon assessment, and ecological restoration, supporting regional conservation and carbon neutrality goals. Full article

Event cameras are bio-inspired vision sensors offering low latency, low power consumption, and high dynamic range, capturing motion with microsecond-level precision via a per-event triggering mechanism. Despite these advantages, the inherent sparsity and lack of color in event data hinder direct analysis, necessitating advanced deep learning approaches. To achieve low-latency and high-precision motion segmentation for indoor robotic applications, this paper introduces a dual-branch decoupled CNN framework. Specifically, Principal Component Analysis (PCA) is utilized to project 3D event point clouds into 2D motion trend maps, capturing local motion priors while suppressing ambiguity in structured environments. Concurrently, an Event Leaky Integration (ELI) model, inspired by biological membrane potentials, is designed to enhance the structural representation of sparse events. Within this framework, separate branches respectively perform motion validation and shape extraction and are fused via a Spatial Gated Fusion (SGF) module to suppress static background interference. It is demonstrated experimentally that with an input window of only 10 ms, the proposed method achieves a 77% average mIoU across five indoor test scenarios from the EV-IMO dataset with an inference latency of 10 ms per frame. Compared to state-of-the-art methods like MSRNN and GCN, which required 30–300 ms event slices, our framework achieves a favorable trade-off between computational efficiency and segmentation accuracy, maintaining competitive performance under ultra-short time windows for indoor event-based motion processing. Full article

Mountain flood susceptibility in complex mountainous basins is strongly influenced by terrain–climate interactions; however, the linkage between spatial susceptibility patterns and hydrological processes remains poorly understood. This study proposes a process-oriented framework that explicitly links flood susceptibility patterns with hydrological processes, moving beyond conventional approaches that rely on independent model integration. The Baishuijiang River Basin, located in Wenxian County, southern Gansu Province, China, is selected as a representative mountainous watershed for this analysis. The specific conclusions are as follows: (1) Flood susceptibility was mapped using a Particle Swarm Optimization (PSO)-enhanced Maximum Entropy (MaxEnt) model based on multi-source environmental variables, including climatic, terrain, soil, land cover, and vegetation factors. The model achieved high predictive accuracy (Area Under the Receiver Operating Characteristic Curve (AUC) = 0.912), identifying precipitation of the driest month (bio14), elevation, and land use as dominant controlling factors. Medium-to-high-susceptibility areas account for approximately 22% of the basin and are mainly distributed along river valleys and flow convergence areas. These patterns are strongly associated with reduced infiltration capacity under dry antecedent conditions and enhanced flow concentration in steep terrain, and they exhibit clear nonlinear responses and threshold effects. (2) Hydrological simulations using Hydrologic Engineering Center–Hydrologic Modeling System (HEC-HMS) show good agreement with observed runoff (Nash–Sutcliffe Efficiency (NSE) = 0.74–0.85). Sensitivity analysis indicates that runoff dynamics are primarily controlled by the Curve Number (CN), recession constant, and ratio to peak, corresponding to infiltration capacity, recession processes, and peak discharge amplification. The spatial consistency between high-susceptibility areas and areas of strong runoff response demonstrates that susceptibility patterns can be physically explained through hydrological processes, providing a process-based interpretation rather than a purely statistical prediction. (3) Future projections indicate that medium–high-susceptibility areas remain generally stable but show a gradual expansion (+5.2% ± 0.8%) and increasing concentration along river corridors under climate change scenarios. This reflects intensified precipitation variability and enhanced runoff concentration processes, suggesting a climate-driven amplification of flood risk in hydrologically connected areas. Overall, this study goes beyond conventional susceptibility assessment by establishing a physically interpretable framework that provides a consistent linkage between environmental controls, susceptibility patterns, and hydrological responses. The proposed approach is transferable to similar mountainous basins with strong terrain–climate interactions, although uncertainties related to data limitations and single-basin application remain and require further investigation. Full article

The use of liquid hydrogen (LH₂) as a civil aircraft fuel is gaining attention due to increasing environmental concerns associated with conventional fossil fuels. The EU-funded HASTA (Hydrogen Aircraft Sloshing Tank Advancement) project aims to investigate, both experimentally and numerically, the storage of LH₂ in civil aircraft, ultimately providing design guidelines for cryogenic fuel tanks. A critical phenomenon affecting airborne cryogenic tanks is the ullage pressure drop, which can occur due to in-flight excitations that induce mixing between the liquid and gas phases. As an initial step toward understanding the sloshing dynamics in LH₂ tanks, this study investigated isothermal sloshing in a small-scale, horizontal cylindrical tank. An experimental campaign was conducted using an 80 mm × 120 mm cylindrical horizontal tank, partially filled with deionised water and subjected to vertical sinusoidal excitation. The objective was to map the liquid response regimes to the excitation frequency–amplitude range of interest. A sloshing regime map was obtained, providing a key understanding of the liquid dynamics, indicating excitation amplitudes and frequencies that can lead to phase mixing. Ten distinct sloshing modes were observed within the 4–10 Hz excitation frequency range, with this study focusing on mode (1 0), the lowest-frequency response and particularly critical for such systems. The modal frequency and damping were obtained using a sloshing surface identification algorithm, and the relationship between the sloshing force and tank displacement/velocity was analysed to provide insight into the sloshing regime. Apart from providing important insights into the sloshing regimes inside horizontal cylindrical tanks, this research also establishes the experimental characteristics needed for future numerical model calibration. Full article