Search Results (3,088)

Hyperspectral anomaly detection application is essential in numerous different remote sensing applications, where the detection of rare and unknown targets in complex scenes is needed. The proposed anomaly detection method in this study is called L-PCAD (Laplacian PCA-based anomaly detection), which plans to combine a Linearized Alternating Direction method (LADM)-based subspace recovery algorithm with a modified RX detector to improve detection accuracy and stability. It starts with an LADM-based approach as a preprocessing stage to get a matrix with rich information relating to anomalies. The resulting low-rank background matrix is subsequently utilized as a guide for the anomaly detection process. In order to enhance the RX detector, the covariance estimation is reformulated using a graph Laplacian constructed from the low-rank background matrix. Instead of directly using the empirical covariance matrix, a normalized Laplacian is computed and subsequently transformed via principal component analysis (PCA) to obtain a stable diagonal representation. This PCA-regularized Laplacian replaces the conventional covariance matrix in the RX formulation while preserving the local spatial structure. The extensive testing of different hyperspectral datasets shows that the proposed approach provides better overall results for detection performance as compared to other hyperspectral anomaly detectors that are the state of the art. Full article

To mitigate error accumulation and long-term drift in unmanned aerial vehicle (UAV) position and attitude estimation using purely inertial measurement unit (IMU) data, this paper presents a dual-branch physics-informed long short-term memory (DPI-LSTM) network incorporating shared temporal encoding, a dual-branch structured regression framework, and physical consistency constraints. The model employs a long short-term memory (LSTM)-based temporal encoder to extract temporal features from IMU time-window sequences. Established inertial kinematic relationships are embedded into the dual-branch LSTM framework as loss constraints, providing physics-based regularisation to guide the network during training. By modelling translational and rotational states separately through the position and attitude branches, the model improves stability and physical interpretability while retaining the advantages of task decoupling. Systematic experiments were conducted on the University of Zurich First-Person View (UZH-FPV) Drone Racing dataset, and comparisons were made with traditional inertial navigation methods and representative deep learning-based inertial odometry approaches. The experimental results indicate that the proposed model demonstrates a measurable reduction in positional root mean square error (RMSE) on the evaluated test sequences, decreasing the RMSE to 0.0654 m, which represents a reduction of more than 20% when compared with inertial odometry network (IONet), convolutional neural network–long short-term memory (CNN–LSTM), and robust neural inertial navigation (RoNIN). Further ablation studies and cross-sequence evaluation indicate that the physical consistency constraints and the dual-branch architecture contribute to improved position estimation stability under the evaluated benchmark sequences. The proposed kinematically constrained framework provides a viable IMU-only position and attitude estimation module, laying the groundwork for future UAV digital twin and precision-agriculture applications where continuous and physically consistent position and attitude information is required. Full article

Road traffic injuries remain a central challenge for sustainable transport, public health, and mobility governance. The task of monitoring these injuries requires indicators that jointly capture harm severity, road and environmental context, and patterns of vehicle involvement at scale. Using harmonised English-language Romanian police crash exports (2023–2025), we build 92,790 records with 36 variables and estimate two complementary k-means typologies: a severity partition based on the fatality, injury, and vehicle-count fields (a register proxy for involvement, not vehicle-type attributes) and a context partition based on the road, environment, mechanism, and cause fields with one-hot encoding and TruncatedSVD. Reported tables and figures reproduce the archived MiniBatch pipeline for replication; for context, full-batch k-means clustering on the same embedding is the recommended default when cross-year prevalence stability is required (train–test TVD 0.039 versus 0.569 under MiniBatch). We report silhouette-guided choices ($k=6$ severity, $k=4$ context), cross-seed stability, feature ablations, and a 2023–2024 versus 2025 prevalence comparison. A Pearson ${\chi }^2$ test on severity × context labels reveals strong statistical significance, yet Cramér’s V remains small—statistical association with limited practical coupling, consistent with complementary rather than redundant partitions. Limitations include police-reported injury counts; a coarse vehicle proxy; weak context geometry; and large MiniBatch context drift, which binds inference to within-year descriptive profiling unless analysts refit the model, add version labels, or adopt full-batch context clustering. The contribution is an integrated, reproducible profiling and governance workflow for dashboards and follow-on modelling—not a fixed multi-year cluster taxonomy. Full article

Mobile edge computing (MEC) supports computation-intensive and latency-sensitive Internet of Things (IoT) applications. However, collaborative task offloading in dynamic heterogeneous environments remains challenging due to coupled physical constraints, shared resource competition, and high-dimensional decision spaces. Existing multi-agent deep reinforcement learning (MADRL) approaches often rely on static penalties or centralized action truncation for constraint handling. These methods may lead to unstable training, conservative strategies, and limited collaboration. To address these limitations, this paper proposes a constraint-aware multi-agent edge collaborative offloading algorithm (CARE-CTDE). The offloading problem is formulated as a constrained Markov decision process and addressed under a centralized training and decentralized execution (CTDE) framework. Dynamic Lagrange multipliers replace fixed penalties to improve training stability and support smoother exploration near constraint boundaries. A multi-threshold-guided Lagrangian constraint regulation mechanism further coordinates heterogeneous constraints, including energy consumption, latency, and server capacity. In addition, a congestion-driven cost allocation method transforms global resource competition into dynamic cost signals, guiding agents toward more coordinated offloading decisions. The simulation results show that CARE-CTDE achieves better scheduling performance, resource utilization, and constraint satisfaction than baseline methods in dynamic heterogeneous MEC scenarios, demonstrating its effectiveness and robustness for constrained edge computing systems. Full article

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving edge intelligence because it enables geographically distributed devices to collaboratively train a shared model without transferring raw data to a central cloud. This capability is particularly valuable for 5G and emerging 6G networks, where edge-native services are required to satisfy stringent latency, bandwidth, and privacy constraints while operating on highly heterogeneous devices and time-varying wireless channels. In practice, however, synchronous FL is often constrained by straggling clients with limited computation capability or unfavorable communication conditions, which increases round latency and reduces overall resource efficiency. To address this challenge, this study develops a rigorously structured framework for dynamic client selection and radio resource allocation in heterogeneous wireless edge environments. Each FL round is formulated as a latency-aware scheduling problem that jointly captures local computation time, uplink transmission time, minimum participation constraints, and resource block assignment. On this basis, we propose a Dynamic Client Selection and Resource Allocation (DCS-RA) method that integrates computation-aware, channel-aware, and fairness-aware scoring with greedy resource block allocation guided by marginal completion time reduction. The study further provides a clear methodological structure, workflow visualization, literature-grounded justification, dataset documentation, and uncertainty-aware result reporting. Under the reported simulation setting with 100 clients and 20 resource blocks, DCS-RA reduces the average round completion time from 1.92 s to 1.55 s on MNIST and from 2.02 s to 1.57 s on CIFAR-10, corresponding to improvements of 19.39% and 22.47%, respectively. Standard deviation reductions of 70.59% and 80.77% further indicate improved round-to-round stability and more reliable training behavior. These results support the central conclusion that lightweight joint scheduling can materially improve wall-clock FL efficiency in heterogeneous 5G/6G edge networks. Full article

ZERODUR glass-ceramic is widely used in ultra-precision optical components because of its extremely low thermal expansion and excellent dimensional stability. However, its two-phase microstructure, composed of crystalline and amorphous phases with different mechanical properties, may cause non-uniform material removal during magnetorheological polishing, thereby limiting further improvement of nanoscale surface quality. To address this issue, this study investigates the effect of oxide abrasives on the surface homogenization of ZERODUR. A single-particle abrasive–workpiece contact model based on modified Hertz contact theory and elastoplastic contact analysis was established to compare the indentation responses of CeO₂, SiO₂, and ZrO₂ abrasives in the two constituent phases. Magnetorheological polishing experiments were conducted under identical process parameters, and the polished surfaces were characterized by AFM over scan areas of 2 μm × 2 μm, 5 μm × 5 μm, and 10 μm × 10 μm. The results show that all three abrasives improved the surface quality of the ring-polished substrate, with ZrO₂ achieving the best surface homogenization performance. The lowest roughness, Ra = 0.104 nm, was obtained at a 2 μm field of view, and the ZrO₂-polished surface showed more stable roughness evolution across different scan sizes than the CeO₂- and SiO₂-polished surfaces. These results indicate that the elastic modulus, hardness, and mechanical compatibility of abrasives with ZERODUR play key roles in governing contact stress, indentation behavior, and final surface quality. This work addresses the lack of mechanistic understanding of abrasive-dependent surface homogenization in the magnetorheological polishing of two-phase ZERODUR glass-ceramic. The main innovation is the integration of contact-mechanics-based abrasive–workpiece modeling with multi-scale AFM characterization to clarify how abrasive mechanical compatibility affects nanoscale surface uniformity and to guide abrasive selection for ultra-smooth optical manufacturing. Full article

This work reports the development of innovative enzyme–titanium nanobiohybrids synthesized via a protein-assisted approach to obtain efficient and sustainable photocatalysts for environmental remediation. By addressing the limitations of conventional TiO₂ nanoparticle synthesis, this strategy enables controlled material properties under milder, potentially scalable conditions for enhanced ROS-driven degradation of persistent dye pollutants. This work employs a bio-assisted synthesis approach using β-glucosidase as a protein scaffold, TiCl₄ as the titanium precursor, and H₂O₂ in bicarbonate buffer at room temperature, eliminating the need for harsh conditions and high temperatures. The biological moiety guides the nanoparticle formation, controlling size and morphology while preventing aggregation, all performed under mild conditions. X-ray diffraction determined that the Ti hybrid was composed of TiO₂ brookite species. TEM analyses demonstrated the formation of well-dispersed nanostructures of around 700 nm. The resulting nanobiohybrids showed excellent photocatalytic activity, achieving >99% Rhodamine B degradation under UV light in only 1 h compared to visible light. The catalyst was capable of degrading Rhodamine B at a concentration approximately 36 times above the recommended threshold for water. Furthermore, a preactivation of the catalyst by direct exposition of it to UV-395 nm light greatly enhanced the efficiency in the photocatalytic process, being inactive in visible light. The Ti–enzyme hybrid showed excellent recyclability over five consecutive cycles and retained good activity after storage, demonstrating its stability. This study introduces a sustainable and efficient route for synthesizing Ti-based nanobiohybrids, providing a promising strategy for advanced photocatalytic applications in water treatment and environmental remediation. Full article

Reference guided anime editing is challenging when the target requires both rendering style transfer and local structural change. Existing diffusion stylization methods that do not require training usually assume a fixed content layout, while drag-based editors deform local structures without enforcing a separate style reference. Directly combining them is unstable: reference attention can disrupt handle tracking during dragging, whereas stylization after dragging can weaken the edited structure. This paper proposes AnchorHandoff, a temporally coordinated diffusion framework for joint drag and style editing. Drag optimization is performed with style injection disabled, followed by a short interval without style injection that lets the edited structure stabilize. A predicted clean sample from this state after dragging is then used as an anchor: content queries are refreshed from the anchor, and reference style keys and values are replayed on the edited layout. Soft correspondences from intermediate attention features guide style injection toward compatible regions without parsers or segmentation labels. On a curated anime benchmark, controlled comparisons, ablations, and a blind study with 36 participants show that AnchorHandoff reduces residual tracking error and feature structure distortion while maintaining comparable distribution level style alignment. The method remains limited under very large structural changes, but the results highlight temporal handoff as an important factor in joint anime structure and style editing. Full article

Effective identification of corporate default risk is crucial for maintaining financial stability and safeguarding investors’ interests. Existing models remain limited in addressing class imbalance and the dynamic evolution of default-related features over time. To overcome these challenges, we propose an adaptive spherical neighborhood resampling and class-specific reliability evidential reasoning model (ASNR-crER). By combining feature-weighted minority sample reconstruction with reliability-guided recursive evidence fusion, the proposed model aims to improve the prediction accuracy of both default and non-default firms under class imbalance. This study uses Chinese listed small enterprises from 2000 to 2023 as the research sample, comprising 10,449 firm-year observations from 2182 firms. By matching default status in year t with firm indicators from t-0 to t-5, six rolling prediction windows are constructed. The empirical results show that: (1) Compared with mainstream benchmark methods, ASNR-crER achieves the best overall performance in terms of accuracy, AUC, and F1 across all prediction windows, indicating that it can more reliably identify high-risk default firms while maintaining strong recognition of non-default firms. (2) SHAP analysis indicates that financial, non-financial, and macroeconomic indicators exert time-varying effects on corporate default risk. Financial indicators, including “Retained earnings/total assets”, “Other receivables/current assets”, and “Annualized return on assets”, reflect internal capital accumulation and profitability, serving as key predictors of default risk. Non-financial indicators, such as “Top 10 Tradable Shares H-index” and “Top 10 shareholders H-index”, can provide supplementary signals for medium-term risk identification. Macroeconomic indicators, including “M2 YoY growth rate”, “Urban HH per capita income”, and “Benchmark short-term loan rate”, show stronger explanatory power in longer prediction windows. Therefore, this study provides an effective early-warning tool for financial institutions and relevant stakeholders to identify high-risk firms, and enriches empirical evidence on the time-varying drivers of corporate default risk. Full article

Object detection in unmanned aerial vehicle (UAV) imagery suffers from severe scale variation, dense object packing, and prohibitive computational cost when conventional detectors exhaustively evaluate high-resolution frames. Reinforcement learning (RL)-based sequential detectors offer a promising alternative by formulating localization as an active search process, yet existing methods are limited by discrete-time state transitions, sparse reward signals, and premature policy collapse. In this paper, we propose HRL-Det, a hierarchical reinforcement learning framework that addresses these challenges through two tightly coupled innovations. First, a Neural ODE-driven Continuous-Time Bellman State Evolution module models the agent’s state dynamics as a stochastic differential equation governed by the Hamilton–Jacobi–Bellman equation, enabling fine-grained temporal reasoning with memory-efficient adjoint-based backpropagation. Second, a Lyapunov-Guided Entropy-Regularized Reward Shaping mechanism constructs convergence-promoting dense rewards informed by Lyapunov stability analysis while maintaining exploration diversity through maximum entropy optimization. Extensive experiments on VisDrone2019, DroneVehicle, and MS COCO 2017 show that HRL-Det achieves mAP@0.5 of 0.412, 0.812, and 0.735, respectively, outperforming existing RL-based detectors and achieving competitive accuracy relative to representative non-RL detectors under the same COCO metric, while requiring only 17.3 M parameters and an average of 6.3 search steps per object. Full article

Nanotechnology has become an important platform in the fields of gene therapy and genome editing, providing delivery strategies that address persistent therapeutic challenges by improving the precision, efficiency, and safety of genetic modifications. This review highlights the central role of nanomaterials in overcoming persistent barriers to genetic interventions, including inefficient delivery, instability of genetic cargo, and off-target effects. Specifically, we emphasize the combined use of nanomaterials with clustered regularly interspaced short palindromic repeats and CRISPR-associated proteins (CRISPR-Cas) systems, which can improve editing specificity and therapeutic efficacy. Beyond the classical CRISPR/Cas9 platform, this review also discusses next-generation modalities such as base editors, Cas13, prime editing, and the recently described Tandem Interspaced Guide RNA and TIGR-associated protein (TIGR-Tas) system, while considering their therapeutic potential and distinct delivery challenges. By using nanomaterials, the stability and intracellular delivery of genome-editing systems are improved, enabling more effective treatments for genetic disorders and acquired diseases such as cancer and infectious diseases. In addition, nanocarriers provide controlled release, protection from degradation, and better biocompatibility, thereby improving the safety and reliability of gene-editing therapies. Despite these advances, important translational challenges remain, including immunotoxicity, large-scale manufacturing, and regulatory integration. Overall, the continued convergence of nanotechnology and genome engineering may support the development of personalized medicine strategies that adapt genetic engineering tools for patient-specific applications. Full article

Accurate object detection in agricultural environments remains challenging due to illumination variation, background clutter, partial occlusion, and overlapping fruits. Conventional object detection methods mainly rely on deterministic data augmentation strategies or feature-level refinement, which often exhibit limited robustness under complex field conditions. To address this issue, this paper proposes a Diffusion-Regularized Object Detection (DROD) framework for robust pineapple target detection in agricultural imagery. The proposed framework introduces a mathematically grounded forward diffusion and diffusion-guided representation mechanism directly in the image domain, where stochastic perturbations are generated through forward diffusion and semantically meaningful image representations are learned via diffusion-guided representation. A unified optimization framework and theoretical analyses of perturbation propagation, Lipschitz stability, and training convergence are further established to provide mathematical support for the proposed method. Extensive experiments were conducted on a self-constructed dataset containing 1600 real-world pineapple images collected under practical agricultural conditions. Comparative evaluations involving YOLOv8-s, YOLOv8-l, traditional data augmentation, and the recent JTA:GAN method demonstrate that the proposed DROD framework consistently achieves the best detection performance in terms of Precision, Recall, mAP@0.5, and mAP@0.5:0.95 while maintaining computational complexity and inference speed comparable to the original YOLOv8 architecture. Furthermore, ablation studies, diffusion parameter sensitivity analysis, visualization analysis, and experimental validation under different perturbation levels consistently verify the effectiveness and robustness of the proposed diffusion mechanism. These results demonstrate that diffusion-based regularization provides an effective and computationally efficient solution for robust agricultural object detection and offers a practical framework for intelligent precision agriculture applications. Full article

Operational crop mapping requires classifiers capable of robust generalization across years. While feature importance is routinely used for model optimization, its temporal stability has rarely been systematically investigated, creating a critical gap in deploying reliable monitoring systems. This study moves beyond identifying “most important” features to systematically evaluate and quantify their inter-annual stability for enabling automated classification. Using six agricultural years (2018, 2019, 2020, 2023, 2024 and 2025) of Sentinel-1 and Sentinel-2 data over Morocco, we extracted 156 multi-sensor features across 12 monthly composites and analyzed their importance stability through statistical metrics, clustering, and novel composite indices: the Reliability Index (RI) and Automatic Selection Score (AuSS). This framework automates feature selection by ranking features with RI and AuSS and then applying Pareto optimization to identify a minimal stable feature set—without requiring annual retraining or expert intervention. Our analysis confirms a fundamental tension: the most discriminative features (e.g., NDVI, VH, VV) are also the most volatile, while stable features (e.g., NDRE, MSI, NDMI) offer modest predictive power. Hierarchical clustering revealed four behavioral typologies (Dominant Stable, Performant Volatile, Stable Minor, and Noise), guiding strategic feature management. Crucially, a Pareto analysis demonstrated that a refined portfolio of 6 indices (VH, VV, NDVI, NDRE, GCVI, RVI) captures 57.2% of cumulative predictive importance, filtering out inter-annual noise while preserving discriminative signal. The Voting Ensemble leveraging this Stable Portfolio maintained consistent high accuracy (87.4% accuracy, 87.2% F1-score) with minimal performance degradation during temporal transfer, while models based on volatile top features exhibited significant drops. Entropy analysis confirmed that all features in the Stable Portfolio provide consistent informational certainty, indicating that stability-driven selection does not increase model uncertainty. We conclude that feature stability is not merely a diagnostic metric but a foundational criterion for operational design. We propose a practical, metrics-driven framework for constructing automated crop classification systems that are more resilient to inter-annual climate variability. Full article

Occlusion introduces severe structural asymmetry into pedestrian representations by corrupting body topology, breaking cross-scale semantic continuity, and destabilizing identity geometry. Rather than treating occluded person re-identification (ReID) as a local visibility completion problem, this work reformulates it as a topology-preserved symmetry restoration problem: recovering symmetric identity structure from asymmetrically corrupted observations. Under this view, we present the Topology-Stable Person Re-identification Network (TSP-Net), a unified visual framework with three coordinated components: structural restoration, cross-scale symmetry alignment, and prototype-stabilized identity geometry. Specifically, Topology-Guided Occlusion and Visibility Modeling (TOVM) serves as the structural restoration component, and is realized by a closed loop of the Topology-Aware Occlusion Simulator (TOS) and the Topology-Aware Visibility Estimation (TVE) branch; Semantic-Anchored Cross-Scale Fusion (SACF) performs symmetry-consistent semantic recovery across hierarchical features; and the Prototype-Stabilized Supervision Loss (PSS Loss) regularizes identity embeddings toward topology-consistent manifold centers through momentum-updated prototypes. Experimental results on both occluded and holistic benchmarks show that TSP-Net is effective for learning occlusion-robust person representations. These findings suggest that restoring topology-preserved symmetry is a promising route for robust person re-identification under structural corruption. Full article

Objectives: Transaxillar Impella 5.0/5.5 implantation is a hybrid surgical and fluoroscopy-guided procedure. We evaluated the learning curve using radiation exposure as a marker of procedural efficiency and assessed whether structured mentorship accelerates procedural proficiency. Methods: This retrospective single-center study included consecutive transaxillar Impella 5.0/5.5 implantation attempts by two surgeons. Surgeon A adopted the technique independently, whereas Surgeon B was trained under direct proctorship. The primary endpoint was radiation exposure (dose–area product), and the secondary endpoint was fluoroscopy time. Temporal trends were analyzed by regression, and CUSUM plots were generated. Results: Of 104 procedures, 14 were excluded (12 transaortic, 2 unsuccessful). Ninety procedures were analyzed (74 Surgeon A, 16 Surgeon B). In Surgeon A, radiation exposure decreased significantly with increasing case number. In Surgeon B, no significant association between case number and radiation exposure was observed. Fluoroscopy time was not associated with case number in either group. CUSUM analysis suggested an early increase followed by stabilization in Surgeon A, whereas no clear pattern was observed in Surgeon B. The between-surgeon interaction was not statistically significant. ECMELLA configuration was the only independent predictor of increased radiation exposure, whereas device type, surgery type, and patient age were not significant predictors. Conclusions: Transaxillar Impella implantation appears to have a measurable early learning phase. Structured mentorship may attenuate the early learning phase, although this finding remains exploratory. Full article