Search Results (1,357)

Detecting small unmanned aerial vehicles (UAVs) in ground-to-air imagery is challenging because their weak visual cues must be preserved without imposing excessive computation on resource-constrained platforms. To address the unresolved trade-off between tiny-target representation and deployment efficiency, we propose a Lightweight Feature-Fusion and Small-Target Enhancement Network (LFE-YOLO), a lightweight detector that coordinates partial-channel feature extraction, efficient cross-scale fusion, high-resolution prediction, background-interference suppression, and stable tiny-box regression within a unified architecture. Specifically, C2fFaster and GSConv reduce redundant computation while maintaining multi-scale feature propagation; a P2 high-resolution detection branch and Efficient Multi-scale Attention preserve fine spatial cues and suppress background interference; and Normalized Wasserstein Distance complements Complete Intersection over Union to improve tiny-box localization stability. We also construct Det-UAV by integrating newly collected multi-platform and multi-scene UAV imagery with existing data using scene- and sequence-independent partitioning and duplicate control. Experiments on Det-UAV show that LFE-YOLO improves detection accuracy while reducing parameters and computation relative to YOLOv8s. Zero-shot evaluation on the public DUT Anti-UAV dataset further indicates favorable transferability to an unseen data distribution. TensorRT 8.2.1 deployment experiments on NVIDIA Jetson TX2 show that, under the same evaluation settings, LFE-YOLO achieves higher detection accuracy and inference throughput, lower latency, and a smaller engine size than the comparable-scale YOLOv8s and YOLO11s models. These results support a practical accuracy–efficiency balance for small-UAV detection under constrained resources. Full article

Accurate estimation of aboveground biomass (AGB) in dryland savanna woodlands is constrained by sparse field data, which has motivated widespread fusion of field plots with spaceborne LiDAR reference data from the Global Ecosystem Dynamics Investigation (GEDI). Here, we show that such fusion can substantially inflate apparent model accuracy when the two reference sources sample different spatial domains. Using 44 field plots from the Abu-Gadaf Natural Reserved Forest (AGNRF), Sudan, and 56 GEDI L4A footprints drawn from a 50 km buffer surrounding the reserve, we trained Random Forest (RF), Gradient Boosting (GB) and Classification and Regression Tree (CART) models on Sentinel-1, Sentinel-2, SRTM and Dynamic World predictors and evaluated them under 10-fold, 2 km block spatial cross-validation. The merged dataset yielded apparently moderate performance (RF: RMSE = 9.40 Mg ha⁻¹, R² = 0.33). However, GEDI-derived AGB was 2.1 times higher than field-measured AGB (18.71 vs. 8.89 Mg ha⁻¹; Kolmogorov–Smirnov D = 0.53, p < 0.001), and decomposing performance by source revealed that predictive skill within the field plot population was effectively absent (R² = 0.001–0.023). A classifier trained to discriminate data source from the predictor stack alone achieved 85% accuracy against a 56% baseline, quantile calibration removing the inter-source level difference reduced pooled R² from 0.33 to 0.13, and restricting GEDI footprints to within 20 km of the reserve reduced R² to 0.008. Apparent accuracy therefore derived largely from between-source separation rather than from structural prediction of AGB. We conclude that spatial cross-validation does not detect population heterogeneity arising from multi-source reference fusion, and that source-stratified validation is necessary. The AGB maps presented are interpreted as relative spatial patterns rather than validated absolute estimates. Full article

Tropospheric evaporation ducts can trap radio waves within a refractive layer, which may guide signals above 1 GHz, enabling beyond-line-of-sight transmission. This makes duct-assisted propagation attractive for maritime communications. The marine environment is characterized by complex hydrometeorological variability and frequent extremes, particularly tropical cyclones, which can perturb duct properties and degrade link reliability. This study develops a multivariate cyclone-aware nonlinear regression framework (CNRF) to estimate contemporaneous evaporation duct strength (EDS) by integrating high-resolution dropsonde observations with tropical-cyclone descriptors from the International Best Track Archive for Climate Stewardship (IBTrACS). The framework uses CatBoost, natural-gradient boosting (NGBoost), and a multilayer perceptron (MLP) as base learners, with a random forest (RF) serving as the second-stage nonlinear fusion model. Rather than relying solely on bulk physical parameterization, the framework aims to represent the nonlinear influence of tropical cyclone-related environmental factors on duct strength. Evaluated over 1996–2024, the CNRF attains a test-set R² of 0.791 and a root mean square error (RMSE) of 5.350 M-unit, corresponding to a 23.5% improvement in RMSE over the Naval Postgraduate School (NPS) numerical model. For Hurricane Fiona (2022), the model achieves an RMSE of 6.260 M-unit, and the inclusion of tropical cyclone descriptors improves RMSE by approximately 17.0% relative to a model that excludes tropical cyclone information. The proposed framework facilitates quantitative assessment of extreme-weather-driven duct variability and supports robust design and operation of duct-enabled maritime communication systems. Full article

This study presents a methodology for predicting the geometric features of single tracks of 316L stainless steel produced by Powder-Bed Arc Additive Manufacturing (PBAAM) from four independent process parameters using a multi-modal Physics-Informed Neural Network (PINN). PBAAM shares the same powder-deposition and layering scheme as Laser Powder Bed Fusion (LPBF) but uses a low-current micro-TIG arc rather than a laser as the heat source. A multi-task PINN architecture was developed that simultaneously predicts five geometric features measured from two imaging modalities (top-view and side-view arc), namely the arc core diameter (D_q), the arc cone angle (α_c), the heat-affected zone width (w_HAZ), the track core width (d_core) and the areal equivalent track width (w_iz), from four input parameters (arc current, traverse speed, work angle and working distance). The model was assessed on a full-factorial training matrix of 36 experiments and on four pure speed extrapolation experiments above the training range. A composite quality score filter classified 23 of the training experiments as stable and 13 as unstable. On the pure validation set, the mean absolute percentage error (MAPE) was 4.25% (95% confidence interval 0.91–8.49) for the arc core diameter, 6.29% (5.07–7.59) for the arc cone angle, 8.06% (6.08–9.82) for the heat-affected zone width, and 17.02% (10.77–21.62) for the track core width. Classical regression baselines attain comparable aggregate errors on this narrowly distributed validation set; the distinguishing property of the proposed model is the joint, physically ordered prediction of all five outputs. The Ayrton voltage sub-module of the model converged to U(I) = 11.33 + 97.13/I without any direct voltage measurement, purely through the physics loss term; this function is consistent with the order of magnitude expected from the physics of low-current TIG arcs. The results indicate that physics-informed learning can be applied to the PBAAM process parameter space under small-sample conditions. This capability is demonstrated for 316L stainless steel, for the micro-TIG electrode configuration and the process window investigated here, for single tracks rather than multi-layer builds, and against a validation set of four experiments varying in a single direction. Full article

Multi-modal sentiment analysis integrates linguistic, acoustic, and visual evidence, yet the reliability of these streams varies across samples because of missing observations, masking, measurement noise, and feature corruption. This paper presents a trainable reliability-aware evidential fusion framework that estimates not only sentiment predictions but also modality-specific evidence, predictive uncertainty, observable input quality, cross-modal disagreement, and normalized sample-dependent fusion weights. Each available modality is independently encoded and processed by an evidential classification head and a quality estimation head. Availability masks enforce exact exclusion of missing streams, while estimated quality, Dirichlet uncertainty, and Jensen–Shannon disagreement jointly regulate the contribution of each observed stream. The model is optimized end-to-end using fused classification, evidential regularization, clean–corrupted consistency, reliability-calibrated cross-modal alignment, and quality regression objectives. Experiments are conducted on both CMU-MOSI and CMU-MOSEI using their official speaker-independent splits. Binary classification follows the standard non-zero protocol, in which samples with sentiment score zero are excluded from Acc-2 and binary F1 evaluation; all labeled samples are retained for seven-class accuracy, mean absolute error, and correlation. The evaluation covers complete-input, every single- and double-modality missing pattern, graded and unseen corruption, combined missing-plus-corrupted conditions, calibration, selective prediction, statistical testing, and computational efficiency. All comparative values in the main tables are identified as local controlled adaptations under the common pipeline, while selected published reference values are reported separately to prevent provenance mixing. Across both datasets, the empirical results show that the proposed method preserves competitive complete-input performance while providing larger and more consistent gains as modality availability or integrity deteriorates. Full article

Retrieving optically inactive nutrients from satellite observations remains challenging because TN, TP, and ${\mathrm{NH}}_3$-N are only indirectly linked to water reflectance and may respond to different environmental contexts. Here, we propose MC-OIWQR, a multimodal framework that combines spatiotemporal contrastive learning from unlabeled HLS Sentinel-2 imagery with meteorological, land-use, and nighttime-light information through cross-attention fusion. Evaluated on long-term in situ observations from Lake Ontario, the framework was analyzed through modality ablation and SHAP-based attribution. Across 10 repeated stratified data partitions, MC-OIWQR achieved mean test $R^2$ values of 0.9208, 0.8663, and 0.9409 for TN, TP, and ${\mathrm{NH}}_3$-N, respectively, obtaining the highest mean $R^2$ and lowest mean RMSE among the evaluated baselines. SHAP-based analysis suggested that TN predictions were associated with land-use and nighttime-light proxies of watershed anthropogenic activity, TP predictions with hydrometeorological forcing related to precipitation and wind, and ${\mathrm{NH}}_3$-N predictions with multivariate environmental context, indicating parameter-specific attribution patterns in the trained model. Long-term retrieval maps from 2016 to 2025 revealed persistent nearshore–offshore nutrient gradients and event-driven variability in Quinte Bay. Cross-lake experiments on Lake Huron and Lake Erie provided preliminary evidence that MC-OIWQR may be adapted through lake-specific re-pretraining for TN and TP retrieval. These results suggest that optically inactive nutrient retrieval benefits from parameter-specific multimodal information rather than a uniform optical regression strategy. Full article

Accurate crop-growth estimation from unmanned aerial vehicle (UAV) imagery is important for precision agriculture, but image-only models can struggle to represent seasonal context. This study evaluates whether combining UAV imagery with weather variables and elapsed time improves continuous rice growth-rate prediction in a single-site, publicly available rice-seedling dataset spanning multiple growing seasons. A Time-Aware Late Fusion (TALF) model is introduced in which a convolutional branch encodes image features, a multilayer perceptron encodes contextual features, and the two streams are merged only at the regression head. Relative humidity, wind speed, and elapsed time are used as contextual inputs after season-aware preprocessing. Evaluation is reported on a chronological multi-season split using internal ablations rather than external generalization claims. TALF achieved a mean absolute error (MAE) of 0.031, compared with 0.1455 for the optimized image-only baseline and 0.0890 for an early-fusion image-and-weather baseline. A secondary tolerance-based metric reached 94.9% under the reported threshold. The results indicate that weather and elapsed-time context improve prediction on this dataset and that separating image and tabular encoders until the final layers is a competitive multimodal learning design under the reported protocol. Full article

Luminescence thermometry has evolved through decades of research focused on optimising materials and on extracting temperature information from isolated spectral features such as luminescence intensity ratios, bandwidth, line shift and excited-state lifetime. Despite extensive material development, these conventional methods remain fundamentally limited by construction: only a small subset of pre-selected spectral features is exploited, while the bulk of the temperature-relevant information encoded in the full spectrum is systematically discarded. A paradigm shift is presented here: Luminescence Thermometry 2.0 (LT 2.0), implemented through the newly developed SpectraSensML platform, in which machine learning regression operates on the entire emission spectrum to deliver temperature readout. The approach is demonstrated on a Yb³⁺-doped phosphor emitting in the near-infrared biological transparency window across 100 to 700 K. Yb³⁺ is a particularly demanding case: only the single ²F_5/2 multiplet emits, and its weakly thermally coupled Stark sub-levels yield modest sensitivity under conventional intensity-ratio thermometry. A total of 27 regression algorithms drawn from four families, namely tree ensembles, physics-aware regression models, kernel and instance methods, and neural networks, are systematically benchmarked. A sensor-fusion estimator that combines the first three principal components reaches an average root-mean-square error of 0.36 K on an unseen-temperature test set, a seven-fold improvement over the best luminescence intensity ratio variant. Standard normal variate (SNV) normalisation is identified as the most effective preprocessing strategy because it isolates the band-shape deformations that encode temperature. Single-component approaches that rely on the first principal component alone are shown to be quantitatively sub-optimal: multi-component regressors that exploit the first three principal components reduce the temperature uncertainty by close to an order of magnitude. The structural reason behind the failure of decision-tree ensembles on unseen temperatures is explained: their piecewise-constant predictions cannot interpolate beyond training set-points. The open-source SpectraSensML application used to obtain the results is released alongside the manuscript to enable reproducible community benchmarks. Full article

UAV-based insulator defect detection faces persistent challenges of multi-scale defect variation, background clutter, small-target missed detections and redundant detection-head computation. This paper proposes BEAD-Net, a real-time insulator defect detection network built upon YOLOv11n with four targeted improvements. First, an Hourglass Symmetric Residual Attention (HSRA) module replaces the standard bottleneck components within C3k2, expanding the multi-scale receptive field and suppressing background interference via a symmetric hourglass dilation schedule and channel attention recalibration. Second, a Bidirectional Diffusion Feature Pyramid Network (BDFPN) built upon the Group-wise Selective Feature Integrator (GSFI) employs group-wise adaptive gating and two-level bidirectional propagation to mitigate semantic dilution during cross-scale fusion. Third, a Task-Decoupled Asymmetric Detection Head (TDAH) concentrates spatial modeling in the regression branch while simplifying classification to lightweight $1\times 1$ operations, reducing parameter redundancy and alleviating inter-task gradient conflict. Finally, Focaler-PIoU2 integrates linear interval mapping with a normalized corner distance penalty to improve boundary regression for slender insulator structures. On the IDID dataset, BEAD-Net achieves mAP@0.5 of 83.98% and mAP@0.5:0.95 of 63.82% at 275.04 FPS with 2.49 M parameters, outperforming the baseline YOLOv11n by 2.83 and 1.55 percentage points and surpassing all compared state-of-the-art methods. Additional validation on the CPLID benchmark shows that BEAD-Net remains the top performer, confirming that the proposed improvements are not specific to a single dataset. Full article

Background and Objectives: Fragility fractures of the sacrum are increasingly recognized in elderly osteoporotic patients and can cause persistent pain, immobility, and progressive pelvic ring instability. We previously described a modified S1 corridor targeting the higher-density cranial–ventral S1 vertebral body for safe percutaneous implant placement. This study reports the clinical outcomes of osteoporotic and pathologic sacral fractures treated through this corridor and presents an exploratory comparison of two 3D-printed titanium sacroiliac fusion implants: the triangular iFuse™ Implant System and the threaded iFuse TORQ™ (SI-BONE, Inc., Santa Clara, CA, USA). Materials and Methods: This retrospective single-center study analyzed 58 patients with fragility or pathologic sacral fractures (FFP IIIb–V; OF 2–5) treated via the modified S1 corridor between January 2021 and March 2026. Of these, 27 patients received triangular iFuse™ implants, and 31 patients received threaded iFuse TORQ™ implants. The primary outcome was procedural safety (implant revision, neurological injury, cortical breach). Secondary outcomes included the Oswestry Disability Index (ODI), Visual Analog Scale (VAS) for pain, operative time, and need for additional fixation. Group comparisons used non-parametric tests; multivariable linear regression adjusted for age, fracture severity (OF classification), and additional fixation. Results: At a mean follow-up of 17.8 ± 9.1 months (iFuse) and 4.1 ± 2.1 months (TORQ), no implant revisions, clinically significant cortical breaches, or neurological injuries were observed in either group. Patient-reported outcome data were available for 48 of 58 patients (20 iFuse, 28 TORQ). Patients in the iFuse™ group were older (80.9 ± 8.5 vs. 76.0 ± 9.8 years; p = 0.050), and OF classification differed between groups, with a higher proportion of OF 4 fractures in the TORQ™ group (p = 0.003). After adjustment for age, OF classification, and additional fixation, TORQ™ implantation was associated with a 15.6-point lower postoperative ODI (p < 0.001), a 13.5-point greater ODI improvement (p < 0.001), a 0.94-point lower postoperative VAS (p = 0.006), and a 1.36-point greater VAS reduction (p < 0.001). Findings remained significant in a sensitivity analysis restricted to patients without additional fixation. Conclusions: Sacroiliac fusion via a modified density-oriented S1 corridor was safe for both large implant types, with no revisions in the analyzed cohort. In this retrospective, non-randomized cohort, threaded iFuse TORQ™ implants were associated with better patient-reported outcomes after adjustment for baseline imbalances. Because the groups were not randomized and follow-up duration differed substantially, these comparative findings are hypothesis-generating and require confirmation in prospective, controlled studies. Full article

Autonomous driving systems face significant challenges in deploying object detection models that must balance accuracy, real-time performance, and lightweight design on resource-constrained in-vehicle platforms. However, inadequate multi-scale feature fusion and redundant feature representations in existing methods limit their deployment on such platforms. To address these issues, we propose an Adaptive Multi-Scale Fusion Lightweight Network (AMSFNet) based on YOLOv11. We introduce a Spatial and Channel Reconstruction Attention Fusion (SCRAFusion) mechanism that employs a Mixup–Reconstruct–Fuse strategy to adaptively integrate multi-scale features, thereby enhancing feature representation, particularly for small objects. Building on this mechanism, we develop a C2fSCConv module that incorporates Spatial and Channel Reconstruction Convolution (SCConv) and SCRAFusion to reduce spatial and channel redundancy and enhance feature representation. Furthermore, we formulate a Scale-aware Dynamic IoU (SDIoU) loss that dynamically adjusts bounding-box regression weights based on target size to improve localization across object scales. Experimental results demonstrate that AMSFNet achieves a favorable balance among detection accuracy, model complexity, and real-time performance, reaching 31 FPS on an NVIDIA Jetson Nano (4 GB). Full article

Accurate crop yield prediction provides essential information for strategic decision-making and precision agriculture, yet achieving reliable forecasts across unseen growing seasons remains challenging. The main objective of this study is to develop a two-stage data assimilation framework that integrates multi-scale environmental data to improve yield predictions and overcome the spatial–temporal autocorrelation limitations of standard machine learning (ML) models. Utilizing an eight-year continuous dataset (2018–2025) of durum wheat fields in Thessaly, Greece, this study integrates high-resolution Sentinel-2 multispectral imagery with macro-scale ERA5-Land meteorological variables. Eight ML algorithms are trained to predict yield at the pixel level. To test model generalization and prevent overfitting, the framework is evaluated using both standard random splitting and leave-one-year-out (LOYO) cross-validation. Concurrently, multiple linear regression (MLR) is utilized to select the most significant meteorological predictors from monthly temperature (maximum and minimum) and precipitation data, which are then integrated into the pixel-level predictions via additive and multiplicative late-fusion assimilation. The results demonstrate that, while standard random splitting produces high explained variance (R² > 0.90), LOYO validation shows a predictive maximum of approximately 50% explained variance. The late-fusion assimilation slightly reduces interannual offsets, from an RMSE of 966 kg ha⁻¹ to 902 kg ha⁻¹. However, the R² values remain static due to informational saturation. This study concludes that, while integrating regional climate data improves absolute annual yield magnitudes, securing reliable agricultural forecasts requires the integration of localized agronomic metadata, such as soil properties and field-specific management practices. Full article

Accurate and robust vehicle localization is essential for autonomous driving. However, existing visual pose estimation methods often struggle in scenarios dominated by repetitive structures or sparse textures. These conditions lead to ambiguous predictions of 3D scene coordinates and a high proportion of structured outliers—erroneous predictions forming coherent clusters that deceive standard estimators. To address these limitations, this paper proposes DOU-Pose (Depthwise Over-parameterized U-shaped Pose estimation), a visual pose estimation framework built upon the Differentiable SAmple Consensus (DSAC)* pipeline. The core idea is to enhance the discriminative capability of scene coordinate regression through improved feature extraction. Specifically, we replace standard convolutional layers with Depthwise Over-parameterized Convolution (DO-Conv), which introduces auxiliary learnable depthwise kernels during training to enrich the representational capacity of the network, while allowing their fusion into a single kernel for inference. Furthermore, a U-shaped regression network with transposed convolutions is designed to preserve spatial details and strengthen fine-grained geometric reasoning. The entire pipeline is trained end-to-end by coupling dense scene coordinate prediction with a differentiable robust estimator. Extensive experiments demonstrate that DOU-Pose achieves competitive performance on public benchmarks and clear robustness improvements on the self-collected Campus-AV dataset, especially in repetitive and low-texture outdoor driving scenarios. Full article

Liquid metals are enabling working fluids for several advanced nuclear systems, including fast reactors, accelerator-driven systems, and fusion blankets. System thermal-hydraulic (STH) codes require thermodynamically consistent property tables over pressure-temperature domains, whereas most liquid-metal correlations are available only as functions of temperature at a reference pressure. This paper presents the formulation and the code verification of four liquid-metal working fluids in RELAP5/Mod3.3: lead (Pb), lead-bismuth eutectic (LBE, denoted PbBi), lead-lithium alloy (PbLi, here Pb-17Li at.%), and sodium (Na). The liquid branch is reconstructed from reference correlations for specific volume, sound speed, and isobaric specific heat through a linearized pressure model, whose correction remains below 0.2% for the heavy liquid metals and below 1% for sodium over the whole tabulated pressure range. The reference pressure is set to the saturation pressure at the maximum tabulated temperature, which maximizes the admissible liquid domain, and a van der Waals equation of state closes the vapor branch. Liquid transport properties and selectable low-Prandtl-number heat-transfer correlations are implemented in the Fortran source code. Verification comprises property comparisons and two non-regression tests, a U-tube manometer, and a natural-circulation loop. The vapor model is a table-completion closure and must not be used for boiling-dominated transients. Full article

Adaptive restraint systems require specific occupant information, including head position, anthropometry, and safety-relevant posture states. Existing 3D human pose estimation benchmarks mostly report root-relative pose, while automotive in-cabin studies rarely evaluate these outputs across heterogeneous vehicle sensor sets. We present ICF-Fusion, a five-modality transformer fusion architecture, and evaluate it under leave-one-subject-out (LOSO) validation on the ICF-Body dataset, which includes synchronized near-infrared (NIR) camera, 60 GHz millimeter-wave (mmWave) radar, belt webbing extraction sensor (WES), seat configuration sensor (SCS), and ultra-wideband (UWB) recordings. The model localizes the head with a Mean Root Position Error (MRPE) of 6.10 cm and regresses anthropometry to mean absolute errors (MAE) of 5.36 cm for height, 3.50 cm for torso length, 1.78 cm for shoulder width, and 8.61 kg for weight. Feet-on-dashboard is detected on 9 of 10 evaluable folds without meaningful MRPE degradation. The full sensor fusion outperformed every single modality on all three tasks, but NIR alone nearly matched it for head localization and feet-on-dashboard detection. The fusion advantage was substantial only for the anthropometry estimation task. Full article