Search Results (324)

As a distributed approach to Artificial Intelligence (AI) model construction over wireless networks, federated learning (FL) based on multi-device collaborative training can protect data privacy, as well as increase the computing load of local model updates. In contrast, split learning (SL) with proper model splitting can adapt to the computation and transmission capabilities among devices. In this paper, while taking advantage of FL and SL, we concentrate on a semi-decentralized hybrid federated split learning (SD-HFSL) framework, in which we surpass the limitations of a single central server and allow the shared split models to be aggregated among multiple edge servers. To verify the importance of latency optimization for training efficiency, we analyze the convergence performance of SD-HFSL while jointly considering the limited computation and communication resources. Then, aiming at maximizing the long-term training efficiency, we propose an online optimization problem that includes local model splitting and device association. Considering that the training latency is unknown to the system a priori, a context-aware online training algorithm with sublinear regret is proposed based on the framework of contextual multi-armed bandit (CMAB), where the edge servers can observe the context information of device sites for latency estimation, followed by the iterative optimization based on the evaluated information in different contexts. Experiments on several neural network models show that the proposed algorithm reduces training latency and improves test accuracy compared with the selected benchmarks. Full article

Individual tree crown (ITC) segmentation in structurally complex mixed forests remains challenging under limited annotation, uneven effective height-structure support, and severe inter-crown adhesion. Existing end-to-end instance segmentation methods often require substantial instance-level annotation, and their cross-domain transferability can degrade when applied to plots with different forest structures. This study proposes a probabilistic prior-constrained instance reconstruction framework that treats semantic segmentation output as an interpretable canopy prior and reconstructs object-level crowns through a structured post-processing pipeline. A height-aware canopy support mask (HCSM) converts the probability field into a credible operational domain through hysteresis thresholding, morphological reconstruction, and a height constraint. Constrained recovery within the support domain (E2GROW) repairs coverage deficiency through spatially bounded boundary adjustment with guard rails on area ratio and buffer distance. Selective splitting then addresses residual merge errors through branch-specific seed-guided partitioning, including an aggressive Voronoi reference branch and a more conservative LOCAL/marker-controlled watershed branch with explicit trigger and child-object filtering criteria. An instance-level evaluation loop based on Gate-3 Recall, a precision proxy, and threshold-crossing audits is used during module development as an iterative safeguard. On a single 500 × 500 m mixed conifer–broadleaf plot with 306 reference crowns retained for evaluation, the high-Recall VORv1 branch improves Recall from 0.369 to 0.673 over the internal R2 baseline produced by the semantic-prior-to-instance initialization procedure, whereas the balanced E2GROW configuration achieves the highest F1_proxy with fewer predicted objects; the overall gain originates from two distinct mechanisms: threshold-crossing boundary recovery for coverage-deficient crowns and local structural decomposition for merged crown groups. Sensitivity analysis indicates that the support-domain construction is stable across the explored parameter ranges, and that the two splitting branches realize a structural Recall–precision trade-off with no evidence of simple additive gains. The framework is modular and auditable, and its demonstrated applicability is strongest for annotation-scarce closed-canopy plots where a usable semantic canopy prior and height information are available. The reported evidence represents a single-site, within-plot methodological demonstration. Full article

Background: China’s influenza vaccine (InfV) has undergone multiple iterations and numerous technological breakthroughs, providing tremendous impetus and solid support for the development of China’s health sector. As the number of vaccinated individuals continues to rise, the importance of ongoing surveillance and evaluation of vaccine safety has become increasingly prominent, forming part of efforts to maintain public trust in the national immunization program and ensure its sustainability. Methods: From 2016 to 2025, data on suspected adverse events following immunization (AEFIs) related to InfV administration were extracted from the Chinese National Immunization Information System (CNIIS). Data on InfV vaccination doses were obtained from the Anhui Provincial Immunization Information Management System. A descriptive statistical method was used to analyze the distribution characteristics of AEFIs, and the chi-square test was applied to evaluate differences in reporting rates. Results: Between 2016 and 2025, a total of 4026 AEFI reports related to InfV were monitored through the CNIIS. The overall reporting rate was 34.40 per 100,000 doses. Specifically, common adverse reactions and rare adverse reactions accounted for 95.88% (3860 cases) and 3.38% (136 cases), with reporting rates of 32.98 per 100,000 doses and 1.16 per 100,000 doses, respectively. Among common adverse reactions, the reporting rates of fever (axillary temperature ≥ 38.6 °C), local redness and swelling at the injection site (diameter > 5.0 cm), and local induration (diameter > 5.0 cm) were 9.62 per 100,000 doses, 1.96 per 100,000 doses, and 1.20 per 100,000 doses, respectively. Among rare adverse reactions, the reporting rates of allergic rash, angioedema, anaphylactic shock, febrile convulsions, anaphylactoid purpura, thrombocytopenic purpura, epilepsy, Guillain–Barré syndrome, and aseptic abscess were 0.98, 0.05, 0.03, 0.03, 0.02, 0.02, 0.01, 0.01, and 0.01 per 100,000 doses, respectively. No cases were reported for subunit inactivated influenza vaccine (IIV, Subunit). Statistically significant differences were observed in the reporting rates of allergic rash across different types of InfV (χ² = 36.83, p < 0.05), with trivalent inactivated influenza vaccine (IIV3, Split) and trivalent live attenuated influenza virus vaccine (LAIV3) showing the highest reporting rates. Most adverse events following vaccination occurred within 24 h after inoculation. Conclusions: From 2016 to 2025, the overall reporting rate of AEFIs after InfV administration in Anhui Province was within an acceptable range. Common adverse reactions were common, while rare adverse reactions were few, mainly consisting of allergic reactions. These results indicate that InfV has a favorable safety profile, and continuous strengthening of AEFI surveillance for InfV and improvement of surveillance quality are warranted. Full article

Scheduling in multi-layer industrial networks must remain stable even when the feedback mechanism of the environment changes inside a single production episode. The system can switch between a step-continuous regime with dense process feedback and a task-driven regime with sparse milestone feedback, so that the same state requires different behaviour before and after the switch. A regime-oblivious policy may therefore optimise the wrong action preference after a switch. We formulate this setting as a mode-switched multi-industrial-chain Markov decision process (MS-MIC-MDP) and prove that a single fixed action preference is necessarily suboptimal in at least one regime. We then propose BHERA, a belief-guided homeostatic estimation framework for regime adaptation. BHERA builds cross-layer representations, performs structured variational inference of slow and fast latent beliefs, estimates the posterior probability of the task-driven regime, and uses that posterior to regulate sample weights, entropy strength, return-prediction emphasis, and latent information capacity. A homeostatic feedback rule on the Kullback–Leibler (KL) divergence keeps the latent representation informative without allowing uncontrolled information growth, and we analyse it as a two-timescale stochastic approximation with an associated convergence argument and a per-iteration complexity bound. Experiments in a multi-layer industrial scheduling simulator show that BHERA achieves higher return, lower cost, and higher utility than CReSCENT, HiTAC-MuSE, Informed Switching, and WToE across all tested perturbations, with paired statistical tests confirming significance. Expanded ablations and parameter-sensitivity studies confirm the importance of regime belief, regime-balanced weighting, bootstrap prediction, homeostatic capacity control, and the dual-timescale latent split. Full article

Plant disease recognition models trained under laboratory conditions often degrade markedly after cross-domain transfer because of the pronounced distribution gap between source and target domains and the scarcity of labeled target-domain samples. To address the transfer task from PlantVillage (PV_100) to PlantDoc, this study develops and evaluates a lightweight cross-domain few-shot plant disease recognition method under a strict PlantVillage-to-PlantDoc protocol. The method integrates EfficientNet-B0 feature extraction, cosine-similarity-based prototypical classification, and training-time target-domain BN adaptation (TBA). During training, unlabeled target-domain images are used only for BN statistical calibration, whereas inference is limited to feature extraction and prototype matching, without gradient updates or iterative optimization. Under a unified experimental protocol, the proposed method achieved cross-split mean accuracies of 42.69 ± 0.62% for one-shot and 54.24 ± 0.72% for five-shot, where ± denotes the standard deviation across three strict data splits; it outperformed ProtoNet by 7.44 and 9.43 percentage points, respectively. Ablation results indicate that TBA is the main source of performance improvement, whereas more complex adaptation strategies do not yield stable additional gains. The core encoder can be executed entirely on the NPU, with an estimated single-sample inference latency as low as 0.658 ms, indicating strong potential for encoder-level mobile deployment. Full article

This study aimed to develop and internally validate a predictive model of perceived stress among first-year military male students to examine the predictive contribution of personality traits, depressive symptoms, and psychological well-being. Understanding these psychological predictors may support interventions for students at elevated risk of stress during military and academic transition. A cross-sectional web-based survey included 274 first-year male students at the Military Technological College in Oman. Outcome measures included the Perceived Stress Scale (PSS-10), the Patient Health Questionnaire (PHQ-9) for depressive symptoms, the WHO-5 Well-being Index, and the Big Five Inventory assessing personality traits. All variables were analyzed as continuous measures. Predictive modeling was performed using Least Absolute Shrinkage and Selection Operator (LASSO) linear regression with repeated 70/30 train–test splitting across 100 iterations and 10-fold cross-validation for internal validation. The final analytic sample included 266 participants after exclusion of incomplete responses. Across the 100 internal validation runs, the LASSO model accounted for approximately 40% of the variance in perceived stress (training R² = 0.44 ± 0.04; test R² = 0.40 ± 0.08). Neuroticism (β = 0.35) and depressive symptoms (β = 0.15) showed positive associations with perceived stress, whereas psychological well-being showed a negative association (β = −0.32). PHQ-9, WHO-5, and neuroticism were selected in 100% of the repeated LASSO models, which showed the most stable predictive contribution. Model performance on the test datasets showed stable predictive accuracy (MSE = 20.24 ± 2.48; RMSE = 4.49 ± 0.28; MAE = 3.61 ± 0.23). These findings demonstrate that personality traits, depressive symptoms, and psychological well-being collectively contribute to the statistical modeling of perceived stress among military students. The internally validated associative model may support institutional interventions for students vulnerable to elevated stress, informing targeted preventive mental health strategies within military training environments. Full article

This paper investigates a distributed convex optimization problem whose objective contains three terms: a local smooth convex function, a local nonsmooth function, and a globally shared, possibly nonsmooth, nonseparable coupling function. To solve this problem, a novel distributed primal-dual proximal gradient algorithm and its asynchronous version are proposed, designated as DPD-PG and AsynDPD-PG, respectively. Each agent communicates with its neighbors locally and updates iteratively with local step-sizes and local relaxation factors. By means of the operator splitting technique, the convergence of the algorithms is rigorously established under mild assumptions. Finally, numerical experiments demonstrate the efficiency of our algorithm, confirming its practical applicability and theoretical soundness. Full article

Semi-mangrove shrubs are important indicators of change in temperate–subtropical coastal ecotones and provide conservation-relevant habitats in shoreline transition zones. On Jeju Island, South Korea, the distribution of two key semi-mangrove species (Hibiscus hamabo and Paliurus ramosissimus) remains incompletely documented despite their monitoring value. Because these shrubs occur as narrow, fragmented patches that are difficult to delineate in satellite imagery, they may be omitted from coarse-resolution inventories. Here, we produced high-resolution semi-mangrove maps from 1 cm UAV RGB orthomosaics using a lightweight Tiny U-Net semantic segmentation model trained on field-confirmed, expert-digitized polygons from nine coastal sites. Model performance was evaluated using a site-wise training, validation, and test split. The final model achieved a pooled semi-mangrove IoU of 0.677, balanced accuracy of 0.921, precision of 0.771, recall of 0.848, and a false-positive rate of 0.007, despite the low semi-mangrove prevalence of 2.59%. On the independent test site, Tiny U-Net also outperformed standard U-Net with fewer parameters and shorter training time (IoU = 0.873 vs. 0.568; 1.9 M vs. 31.4 M parameters; 37 vs. 123 min). Probability outputs also highlighted high-confidence candidate patches outside of the labeled polygons, supporting targeted field verification and iterative inventory refinement. This UAV–deep learning workflow provides a practical baseline for fine-scale habitat assessment and repeat monitoring of vegetation dynamics along Jeju’s temperate–subtropical coast. Full article

Polymer-augmented waterflooding is a key enhanced oil recovery technique whose simulation remains computationally demanding at a high spatial resolution. This paper presents a fully GPU-resident parallel solver for the one-dimensional Buckley–Leverett polymer-flooding problem within an Implicit-Pressure–Explicit-Saturation framework. The solver combines Jacobi iteration for pressure, first-order upwind flux splitting for saturation, and a first-order upwind flux-splitting update for polymer mass with explicit concentration recovery inside a coupled Picard–IMPES iteration. Two CUDA implementations are compared: a global-memory baseline and a shared-memory variant that stages a per-block pressure tile with halo cells on chip. Both kernels were profiled on an NVIDIA GeForce RTX 2080 Ti over problem sizes from $N=65,536$ to $N=67,108,864$ and block sizes 128, 256, 512, and 1024. The two GPU implementations match the serial reference within $2\times {10}^{-8}$, and peak speed-ups are $20.2\times$ (global) and $20.1\times$ (shared). Per-kernel Nsight Compute profiling classifies every kernel in both builds as compute-bound: SM throughput is 54–83% of peak and DRAM throughput 3–29% of peak. The bottleneck is the FP64 pipeline of consumer Turing hardware (FP64 throughput is one thirty-second of FP32); three FP64 divisions per cell, from inline polymer-modified mobility recomputation, saturate the FP64 unit. Shared-memory tiling cannot improve performance because it acts on memory traffic rather than on compute throughput. The result therefore characterizes a specific regime, namely FP64 one-dimensional, low-reuse transport stencils on consumer-class NVIDIA GPUs with reduced FP64 throughput, and is not a universal property of CUDA shared memory. Full article

Ion-acoustic waves in dense quantum plasmas are strongly influenced by Fermi degeneracy, Landau quantization, and finite-temperature effects, and in many relevant environments, they also experience memory and nonlocal transport processes that cannot be captured within the planar integer Korteweg-de Vries (KdV) paradigm. In the present work, we revisit this problem by considering a two-fluid, partially degenerate electron-ion plasma in which electron trapping in the presence of a quantizing field and finite temperature is taken into account. Starting from the normalized fluid-Poisson system appropriate for such magnetized quantum plasmas, the reductive perturbation technique is used to derive the planar integer KdV equation for weakly nonlinear ion-acoustic disturbances. Within this integer-order KdV framework, we recast the evolution equation as a planar dynamical system, construct the associated Hamiltonian and effective Sagdeev-like potential, and demonstrate the existence of compressive solitary waves and nonlinear periodic modes via homoclinic and periodic phase-space orbits. Exact multi-soliton solutions and interaction states are then obtained by combining Hirota’s direct bilinear method with generalized Wronskian representations, allowing us to describe not only standard one-, two-, and three-soliton profiles but also positon-negaton interactions relevant to magnetized, partially degenerate plasmas. To incorporate hereditary and history-dependent effects that arise from anomalous transport and nonlocal temporal response in dense environments, we extend the model by introducing a Caputo time-fractional derivative, thereby obtaining a time-fractional KdV (FKdV) equation that continuously connects the classical KdV limit to fractional dynamics. The FKdV equation is analyzed using the Tantawy technique. This semi-analytical iterative scheme yields rapidly convergent series approximations for the fractional ion-acoustic soliton and provides explicit control of the approximation error. The fractional solutions show that varying the order of the Caputo derivative modifies the amplitude, width, and temporal relaxation of the solitary structures and can even split the pulse into two distinct lobes, in contrast with the nearly rigid propagation predicted by the integer-order KdV equation. Taken together, these results clarify how Landau quantization, finite electron temperature, and fractional-order memory jointly shape the morphology, robustness, and interaction properties of ion-acoustic structures in strongly magnetized quantum plasmas of astrophysical and high-energy-density laboratory interest. Full article

In this paper, we investigate secrecy energy efficiency (SEE) maximization in a rate-splitting multiple access (RSMA)-enabled UAV communication system, which consists of a communication UAV serving legitimate ground users (GUs) and a cooperative jamming UAV transmitting jamming signals to degrade the channel of the eavesdropper (Eve). Taking into account the propulsion energy consumption of fixed-wing UAVs, we formulate a non-convex SEE maximization problem by jointly optimizing communication scheduling, CUAV transmit power, and the trajectories of both UAVs. To tackle the non-convex problem, an iterative optimization algorithm combined with the Dinkelbach method and successive convex approximation (SCA) is developed to obtain a suboptimal solution. Simulation results demonstrate the convergence of the proposed algorithm and show the proposed joint optimization scheme significantly improves SEE compared with benchmark schemes. Full article

Rhizosphere microbiome engineering is a promising approach that can enhance crop resilience and input use efficiency by redirecting plant–microbe–soil interactions toward predictable functions. Here, we review the mechanistic bases underlying rhizosphere assembly and stability, including root exudate-mediated selection, priority effects, keystone taxa, and metabolite-driven signaling, and connect these principles to proposed design rules for microbial inoculants. We present a generalizable Design–Build–Test–Learn (DBTL) framework for engineering synthetic microbial consortia, covering trait-to-module mapping (nutrient acquisition, phytohormone modulation, ACC deaminase activity, stress-protective metabolites, and biocontrol), compatibility screening, minimal yet robust community architectures, and iterative optimization driven by multi-omics and high-throughput phenotyping. Translation to field settings is framed as an engineering challenge defined by formulation and administration limitations, including carrier type, seed coating and encapsulation methods, shelf life, strain invasiveness, and permanence of colonization amid environmental diversity. We also summarize how integrative measurement pipelines (amplicon and shotgun sequencing, transcriptomics, metabolomics, and network or causal analyses) can advance microbiome studies from correlation to actionability. We describe how precision agriculture (sensors, remote sensing, and variable-rate inputs) and AI/ML (split-sample comparisons, transfer learning, and active learning) approaches can accelerate strain discovery, mixture optimization, and adaptive experimentation, driven by the need for stringent controls, metadata-rich reporting, and cross-site comparability. Use cases focus on stress conditions (drought, salinity, thermal extremes, and biotic stress) to demonstrate how microbial functions translate to agronomic outcomes and to highlight critical bottlenecks for reproducible, scalable microbiome products. Full article

Dominant flow channels formed during the late stages of waterflooding can severely reduce sweep efficiency and intensify ineffective interwell circulation. Conventional identification approaches, including tracer testing, well testing, and numerical simulation, often suffer from high operational cost, long execution time, or limited adaptability to heterogeneous interwell connectivity. Although ant colony optimization (ACO) is suitable for path-search problems in reservoir networks, its performance depends strongly on hyperparameter settings, and sample-by-sample parameter tuning introduces substantial online computational overhead. This study proposes a structure-informed GIN–ACO framework for adaptive dominant flow channel identification in connection-element reservoir graphs. A physics-constrained benchmark model is first established using Darcy’s law and the connection element method to provide reference flow paths. A geometry-based surrogate model is then developed to approximate flow splitting coefficients efficiently while preserving the main physical trends. Based on graph topology and geometric descriptors, a graph isomorphism network is trained to predict task-specific ACO parameters, replacing iterative online search with direct parameter inference. Experiments on 1000 synthetic reservoir graphs show that the proposed method achieves a 100% success rate with an average online computation time of 143.5 ms, outperforming fixed-parameter ACO, PSO-ACO, and BO-ACO. On 20 semi-realistic SPE10 reservoir models, GIN–ACO achieves a success rate of 92 ± 1% with an average runtime of 160.3 ± 5 ms. Ablation studies further confirm that graph-structure learning, combined topology–geometry features, and GIN-based parameter prediction are essential for robust performance. The proposed framework provides a promising and computationally efficient route for structure-aware dominant channel identification in connection-element reservoir models. Full article

This study proposes a systematic annotation framework to improve the robustness of end-to-end automatic speech recognition (ASR) in a complex low-resource dialect setting, using Hainan Lingao dialect as a case study. The framework consists of three components: semantically complete utterance segmentation instead of fixed-duration clipping; structured annotation at the lexical, sentence, and pragmatic-behavior levels, including explicit tags for dialectal variation, environmental noise, and unintelligible speech as well as rules for handling overlapping speech; and a three-stage quality-assurance workflow with iterative guideline refinement. The framework was implemented in the construction of a Hainan Lingao dialect corpus from 16 speakers and evaluated using 80 h/10 h/10 h training, validation, and test splits under an identical Conformer-based ASR configuration. Compared with a plain-transcription baseline using no special tags and fixed 3 s segmentation, the full specification reduced character error rate (CER) from 8.7% to 7.9%, 24.3% to 18.5%, 19.5% to 15.2%, and 15.2% to 13.1% on clean, noisy, dialogue, and dialect-variation test sets, respectively. The corresponding sentence error rate (SER) decreased from 17.5% to 15.2%, 39.6% to 32.1%, 34.2% to 27.8%, and 28.3% to 24.5%. Ablation experiments further examined the individual contributions of pragmatic-behavior tags, noise tags, semantic segmentation, and dialect-feature annotation. Paired bootstrap testing with 10,000 resamples showed that all baseline-to-full-specification improvements were statistically significant (p < 0.01). These results indicate that systematic annotation can improve ASR robustness in this Lingao low-resource dialect setting, with the largest relative CER reductions observed in the noisy (23.7%) and dialogue (22.1%) scenarios. Full article

Accurate numerical simulation of Cr20Ni80 alloy processing relies on reliable constitutive and failure models. This study employs a comprehensive experimental–numerical approach to calibrate and validate the Johnson–Cook (J-C) parameters of Cr20Ni80 alloy under varying stress states and strain rates. Quasi-static tensile tests on smooth and notched specimens, alongside dynamic Split Hopkinson Tension Bar (SHTB) tests (1000–3000 s⁻¹), were conducted. Pulse-shaping technology was employed, and dynamic force balance was verified to ensure the physical validity of the high-strain-rate data. The constitutive parameters ($A=621.02 \mathrm{MPa}, B=543.20 \mathrm{MPa}, n=0.4564, C=0.0141$) were determined based on true stress–strain responses. Theoretical analysis confirms that the thermal softening effect caused by adiabatic heating can be neglected. Furthermore, the failure parameters ($D_1=-0.4300,{ D}_2=2.6405,{ D}_3=-0.7055$) were calibrated to capture the stress triaxiality effects ($R^2=0.978$). The parameter $D_4$ was iteratively calibrated using SHTB data from the 1000 s⁻¹ and 3000 s⁻¹ test conditions and validated using SHTB data from the 2000 s⁻¹ test condition. The engineering stress–strain curves obtained from simulations using the calibrated parameters showed good agreement with experimental results, confirming the reliability of the calibrated parameters. Full article