Search Results (476)

For high-speed pneumatic seeders, accurate real-time seed detection underpins downstream quality assessments including seed counting, seeding-rate estimation, and uniformity evaluation. Under high-speed operating conditions, seeds exhibit rapid motion, dense distribution, frequent occlusion, and severe motion-blur-induced edge degradation, posing substantial challenges for vision-based detection. This study proposes HSSD-YOLO, an improved detection algorithm built upon YOLOv11, incorporating three modules: a Motion Blur Enhanced Stem module (MBE-Stem) employing learnable Sobel gradient operators for edge feature extraction under motion blur; an Attention-enhanced Deformable Convolutional Network (ADCN) with a Residual Spatial-Channel Attention (RSCA) mechanism for adaptive sampling of irregularly shaped seeds; and an Edge-Guided Adaptive Recalibration Feature Pyramid Network (EGAR-FPN) injecting edge prior information into multi-scale feature fusion. On a self-constructed dataset of indica rice, japonica rice, and wheat seeds, HSSD-YOLO achieves 96.6% mAP@0.5 and 77.4% mAP@0.5–0.95, surpassing YOLOv11n by 2.5 and 5.4 percentage points, respectively, with only 5.2 M parameters. Ablation studies confirm synergistic gains exceeding linear superposition. Under the conditions evaluated, HSSD-YOLO outperformed all compared algorithms, providing the per-frame detection foundation for downstream seeding-quality tasks; empirical validation of those tasks on continuous video and embedded hardware remains outside the present scope. Full article

The nondestructive characterization of coating thickness, acoustic velocity, and density is essential for industrial quality control. However, conventional ultrasonic reflection coefficient amplitude spectrum (URCAS)-based inversion methods typically require prior knowledge of acoustic attenuation, which is often unavailable for thin coatings and limits their practical applicability. To address this issue, a nonlinearity-guided dual-spectrum inversion framework is proposed by combining the URCAS with a layer-phase spectrum. It is found that the layer-phase spectrum exhibits strong nonlinear sensitivity to variations in acoustic velocity and density, which helps improve parameter identifiability. Based on this property, an improved particle swarm optimization algorithm is developed to enable simultaneous inversion of thickness, velocity, and density without explicit prior attenuation information. Finite-element simulations show that the conventional URCAS method yields mean relative errors exceeding 5%, whereas the proposed method reduces these errors to below 3% under the tested conditions. Experimental validation on eight industrial polytetrafluoroethylene (PTFE) coatings with thicknesses ranging from 20.89 μm to 120.11 μm (down to approximately 0.11 λ at 10 MHz) demonstrates that the proposed method achieves average relative errors within 10% and improves inversion accuracy by about 6% compared with amplitude-only approaches. The results indicate that the proposed attenuation-independent and nonlinearity-guided strategy provides an effective solution for the quantitative nondestructive evaluation of subwavelength coatings. The method is particularly suitable for thin coatings with unknown attenuation. Full article

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

Real-world information diffusion frequently spans multiple heterogeneous platforms and relational layers, making multilayer influence maximization (MLIM) a critical and challenging problem. Existing methods for multilayer networks often rely on local structural signals for surrogate evaluation, failing to accurately characterize multi-hop diffusion and inter-layer coupling effects. In discrete combinatorial search, meta-heuristic random exploration often disrupts the structural inheritance and reuse of effective node configurations, compromising search stability and quality. To address these challenges, this paper proposes a Probabilistic-Based Multilayer Slime Mold Algorithm (PB-MSMA). It employs the slime mold algorithm as its search framework to perform discrete combinatorial optimization within a controlled candidate space. It utilizes the Preference-based Expected Diffusion Value (P-EDV) as a surrogate fitness metric during the search phase. This design reduces the need for repeated Monte Carlo simulations for iterative candidate evaluation while improving the characterization of inter-layer and higher-order diffusion effects. Furthermore, a probabilistic pipeline mechanism is introduced to encode recurring effective node configurations from historical searches as statistical priors, guiding the search process to enhance structural inheritance and stability. After the seed sets are obtained, the final influence spread of all compared methods is evaluated using 10,000 Monte Carlo simulations under the MLIC model. Experiments on six real-world multilayer network datasets and nine seed budgets show that PB-MSMA achieves a dataset-level improvement range of 3.68–14.50% over representative baselines, including CELF, DPSOMIM, Degree, DIRCI, and PRGC, with an average improvement of 10.32%. These results indicate that PB-MSMA provides an efficient seed-selection strategy for multilayer diffusion scenarios where repeated simulation-based evaluation is costly. Full article

This study examined rural pre-service teachers’ preferences for online learning platforms, Telegram, WhatsApp, and Moodle discussion forums in the Open Distance e-Learning environment. This group of students experiences digital illiteracy, limited access to assistive technologies, and network challenges, which may prevent them from optimally utilising formal learning platforms such as Moodle. They can, however, use Telegram and WhatsApp, as they regularly engage informally on these platforms. Against this backdrop, this study explored rural pre-service teachers’ experiences with Moodle and these social media platforms in an Open-Distance e-Learning space. This study employed a descriptive, qualitative case study with semi-structured interviews, guided by Siemens’ Connectivism theory. Fifteen student teachers from the College of Education in an ODeL institution were purposively sampled to provide in-depth insights into their lived experiences of platform use. The findings revealed that, although each platform served a unique instructional function, their perceived professionalism, safety, and interactivity differed substantially. Social media platforms such as Telegram and WhatsApp were lauded for their immediacy, accessibility, and low bandwidth usage, chiefly among rural pre-service teachers from economically disadvantaged communities. However, participants perceived these platforms as unprofessional, disruptive, and unsafe. Conversely, Moodle’s discussion forum was viewed as a credible, structured space that fostered academic discipline through the presence and guidance of lecturers. These contrasting perceptions highlight tensions between accessibility and academic regulation within ODeL environments. Although prior studies support incorporating social media platforms into LMSs, this research extends this discourse by emphasising the need to balance accessibility, interaction, and academic integrity within resource-constrained contexts. The study concludes that social media platforms and discussion forums can complement each other in ODeL, encouraging student interaction and inclusion, while discussion forums ensure educational rigour, safety, and institutional integrity. Full article

Diffusion probabilistic models are powerful generative tools but are purely data-driven, limiting their ability to incorporate domain knowledge—such as physical laws, degradation trends, or engineering priors—in scientific and engineering applications. We introduce Prior-Guided Diffusion Processes (PGDPs), a unified mathematical framework that integrates arbitrary differentiable prior knowledge into the reverse diffusion dynamics by augmenting the score function with a guidance term derived from a prior potential V(x,t) and weighted by a time-dependent strength γ_t. This formulation subsumes existing mechanisms (classifier guidance, model-based diffusion, physics-informed corrections) as special cases. We analyze the guided path measures, providing an upper bound on the Kullback–Leibler divergence between guided and unguided marginals (Theorem 1), quantifying the inherent trade-off between data fidelity and prior satisfaction. Experiments on synthetic data confirm the predicted dependence on γ_t. On the NASA C-MAPSS turbofan benchmark, we enforce compressor-oriented physical constraints (e.g., speed–pressure consistency, monotonicity) within PGDP; remaining useful life scores are reported only as reference metrics under transparent protocols. A cross-domain study on the NASA IGBT accelerated aging dataset, using the same backbone with a replaced physics module, achieves a 99.98% reduction in monotonicity loss, demonstrating generality across distinct degradation mechanisms. PGDP provides a principled, extensible template for knowledge-informed generative modeling with theoretical guarantees and verifiable physical consistency. Full article

Deep neural networks are vulnerable to adversarial examples, even in hard-label black-box settings where only the top-1 prediction is available. To address the challenges of high-dimensional optimization under limited query budgets, we propose two query-efficient attack methods: Adam-OPT, which integrates Adam-based adaptive optimization into the ray-search framework to stabilize and accelerate zeroth-order gradient updates; Prior-Adam-OPT, which further incorporates transfer-based priors from surrogate models to enhance gradient estimation. Adam-OPT leverages historical gradient information and per-parameter adaptive updates to improve convergence, while Prior-Adam-OPT constructs a prior-guided orthogonal search basis that combines surrogate and random directions, enhancing both gradient accuracy and query efficiency. Our approach demonstrates superior performance across CIFAR-10, ImageNet, and zero-shot CLIP models, consistently reducing perturbation magnitudes and improving attack efficiency compared to state-of-the-art hard-label attacks. Ablation studies highlight the importance of the number of vectors used for gradient estimation and the quality of surrogate models, showing that combining adaptive optimization with transfer-based priors provides a scalable and robust framework for generating high-quality adversarial examples in challenging black-box scenarios. Full article

Infectious disease transmission is a complex dynamic process governed by intrinsic causal mechanisms rather than simple statistical correlations. Although deep learning paradigms have demonstrated powerful nonlinear representation capabilities, their “black-box” and purely data-driven nature often lead to a severe lack of causal consistency and logical transparency. To bridge this gap, this paper proposes CCSANet (Causally Constrained SEIR-Aware Network), an interpretable forecasting framework that seamlessly embeds epidemiological priors directly into the neural architecture. The model integrates SEIR dynamics into a temporal causal discovery framework, utilizing a mechanism-aware prior loss to guide a CausalFormer in learning a global temporal causal graph from multi-source heterogeneous data. This ensures that the identified relationships strictly adhere to the fundamental evolutionary logic of contagion. Subsequently, the extracted causal subgraphs are encoded as structural priors within a Causal-SCI-Block via a specialized masking mechanism, effectively forcing information to propagate exclusively along epidemiologically legitimate pathways. To ensure deep alignment between neural representations and physical reality, a causal strength alignment loss is introduced to synchronize the network’s attention weights with actual transmission intensities. Experimental evaluations on real-world multi-city datasets demonstrate that this integrated approach significantly outperforms baselines such as LSTM, Informer, and its predecessor, ESASNet. Under a 7-day sliding window configuration, the model maintains a Coefficient of Determination $R^2$ stably above 0.97, achieving an accuracy improvement of 5.5% to 6.2% and an 8% to 10% reduction in SMAPE, thereby demonstrating that coupling causal discovery with SEIR constraints substantially enhances both predictive precision and physical interpretability. Full article

Generative AI (GenAI) tools are increasingly used by students in higher education, including in technically demanding engineering courses. However, fluent AI-generated responses may still contain incorrect or incomplete information, creating a risk that students overestimate their reliability. This exploratory study investigates the relationship between students’ perceived usefulness of GenAI and an instructor-benchmarked reference evaluation of model outputs in two digital systems design courses. The study involved voluntary survey responses from 32 students in an undergraduate course at MIUN and 20 students in a graduate-level course at UNISA. Student perception data were combined with teacher-side benchmarking of selected GenAI models on tasks categorized by cognitive depth. Findings indicate that prior GenAI familiarity was associated with interaction frequency and average perceived usefulness, whereas self-assessed subject knowledge showed limited association. A perception–performance gap emerged, with students often rating GenAI outputs as useful even when the instructor-side evaluation identified limitations in correctness or required substantial human scaffolding. The proposed framework should be interpreted as an exploratory guideline for studying and guiding GenAI use in engineering education, rather than as a definitive benchmark of model performance. Full article

Hyperspectral anomaly detection (HAD) aims to identify rare targets without relying on prior target knowledge. However, background spectra in hyperspectral images often lie on highly complex and nonlinear manifolds, making accurate modeling challenging. Although models with strong nonlinear approximation capabilities, such as Kolmogorov–Arnold Networks (KANs), provide a promising solution for capturing such complexity, self-supervised reconstruction-based HAD methods still suffer from a fundamental issue known as anomaly leakage. When the model has high representation capacity, anomalous signatures tend to be partially reconstructed, which reduces residual contrast and degrades detection performance. To address this issue, we propose a Blind-Spot KAN-based background reconstruction network with prior purification (BKP-Net), which mitigates anomaly leakage from both data and model perspectives. Specifically, we first introduce a Background Prior Purification (BPP) module to construct a cleaner background prior. This module suppresses and replaces potential outlier pixels through spatial clustering and robust weighted mean estimation. We then design a Blind-Spot KAN-based Reconstruction backbone (BKCN) to model complex nonlinear background characteristics while preventing direct information flow from the center pixel, thereby reducing anomaly leakage during reconstruction. In addition, separable convolutions are employed to enhance spatial–spectral feature representation, followed by an attention-guided fusion mechanism to suppress cross-domain interference. Furthermore, a band-wise Guided Reconstruction Refinement (GRR) strategy is introduced in the detection phase to improve structural consistency between the reconstructed background and the original hyperspectral image, leading to more reliable anomaly discrimination. Experimental results on four hyperspectral datasets demonstrate that the proposed method achieves competitive performance compared with several representative traditional and deep learning-based detectors. Full article

Semantic segmentation of very-high-resolution remote sensing imagery benefits from combining RGB appearance with Digital Surface Model (DSM) height information, especially in urban scenes where spectrally similar objects often differ in elevation. On the ISPRS Vaihingen and Potsdam benchmarks, BATFNet achieves mIoU scores of 84.06% and 85.31%, respectively, outperforming representative RGB–DSM fusion baselines on most land-cover categories. BATFNet is a supervised boundary-aware Transformer fusion network that uses DSM-derived edge priors to guide bidirectional cross-modal attention and decoder refinement. With a dual-branch ResNet-50 backbone for modality-specific feature extraction, the proposed framework effectively integrates RGB and DSM information while recovering fine spatial details. These results show that exploiting DSM-derived structural cues improves boundary delineation and reduces confusion among spectrally similar urban classes. Full article

Transformer-based speech enhancement (SE) architectures suffer from high computational complexity, while existing lightweight state space model (SSM) approaches are constrained to fixed one-dimensional scanning that cannot fully exploit the two-dimensional time–frequency structure of speech spectrograms. To address these limitations, we propose DOM-MUSE, a lightweight U-Net-style SE framework built upon the Mamba-2 SSM with four targeted innovations. First, a Deformable Feature Extractor (DFE) predicts per location spatial offsets that warp the feature sampling grid to align with speech formant trajectories and harmonic structures, providing geometrically coherent inputs to the state space model. Second, a DOM Mamba Block with Cross-Dimensional Gated Fusion (CDGF) deploys two parallel Mamba-2 instances scanning the time and frequency axes independently, and uses Taylor Channel Attention (TCA) to derive semantic gates that modulate each SSM output before fusion. Third, a Phase-Guided Feature Conditioner (PGFC) computes local phase-gradient gates that suppress noise-dominated activations prior to the SSM stage, making the feature extraction pathway implicitly phase-aware. Fourth, an Attention-Based Skip Connection (ABSC) replaces conventional concatenation skip connections with a learned channel gate, adaptively controlling the information flow from the encoder to the decoder. Experiments on the VoiceBank-DEMAND benchmark demonstrate that DOM-MUSE outperforms the reproduced MUSE baseline on all five evaluation metrics—including PESQ (+0.077), CSIG (+0.058), CBAK (+0.026), COVL (+0.070), and STOI (+0.002)—while reducing the parameter count by 24% (0.51 M to 0.39 M). Notably, DOM-MUSE also surpasses MUSE++ on perceptual quality metrics (PESQ +0.061, COVL +0.032) despite MUSE++ employing dynamic SNR augmentation and an augmented multi-objective loss that DOM-MUSE deliberately omits, demonstrating that the proposed architectural innovations yield genuine improvements independent of training strategy. When DOM-MUSE is additionally trained under the same augmented protocol as MUSE++, it achieves PESQ of 3.46 and COVL of 4.22, further confirming the complementary nature of architectural and training improvements. Full article

Impervious surfaces are an important land surface indicator of urbanization level and human activity intensity, playing a crucial role in urban development monitoring and ecological environment assessment. However, in complex high-altitude regions such as the Qinghai–Xizang Plateau, the identification accuracy of existing medium-resolution impervious surface products remains limited at the regional scale due to complex land surface backgrounds, sparse distributions of impervious surfaces, and their generally small spatial extent. To address this challenge, this study proposes a Seed-Driven Grid Adaptation (SDGA) framework for large-scale impervious surface mapping over the Qinghai–Xizang Plateau. The proposed method uses the Google Satellite Embeddings (GSE) dataset as the primary input features and incorporates a 10 m impervious surface prior (P10) derived from a 2 m high-resolution impervious surface product to provide spatial constraints. Based on this prior information, a Prior-guided Hybrid Active Sampling (PHAS) strategy is developed to automatically construct high-value training samples through uncertainty-based positive sample mining and cluster-based negative sample mining. The framework first builds an initial seed knowledge base in the Lhasa seed area and subsequently performs local adaptive expansion within a 2° × 2° grid system, enabling automated impervious surface mapping across the Qinghai–Xizang Plateau. Experimental results show that, with only a small number of initial samples, the PHAS strategy significantly improves model performance, increasing the F1 score for impervious surface identification in the Lhasa seed area from 65.02% to 82.22%. During the grid-level adaptation stage, approximately 67% of the grids achieved improved accuracy, with an average F1 score increase of 0.1109 across the study area. Ultimately, the SDGA framework produced a 10 m resolution impervious surface product for the Qinghai–Xizang Plateau (SDGA-ISC10m), achieving an overall F1 score of 0.8223. Compared with seven existing medium-resolution impervious surface datasets, the proposed method demonstrates improved recognition performance under complex plateau environments, particularly in detecting sparsely distributed and small-scale impervious surfaces. The results indicate that integrating remote sensing embedding features with active learning strategies can effectively reduce the need for manual annotation and provide a new technical pathway for large-scale impervious surface mapping in complex regions. Full article

Rising antimicrobial resistance has reduced the effectiveness of empirical eradication regimens for Helicobacter pylori (H. pylori) infection, particularly those containing clarithromycin. Local resistance surveillance and identification of clinical predictors of resistance are essential to guide treatment strategies. This study evaluated antimicrobial resistance patterns and clinical determinants of resistance in a real-world tertiary-care cohort. A retrospective observational study was performed, which included 352 adult patients with confirmed H. pylori infection managed between November 2022 and November 2025. Of these, 168 patients underwent culture and antibiotic susceptibility testing, while 184 received empirical therapy. Resistance rates were calculated according to the number of isolates tested for each antimicrobial agent (available-case analysis). Multivariable logistic regression analysis was used to identify independent predictors of resistance. Among susceptibility-tested patients, resistance to at least one antimicrobial agent was detected in 44.6%. Clarithromycin resistance was most frequent (42.5%), followed by metronidazole (36.4%) and levofloxacin (14.0%), whereas amoxicillin resistance remained low (2.4%). Multidrug resistance (MDR) based on available susceptibility data was observed in 12.5% of cases, most commonly involving dual clarithromycin–metronidazole resistance. Prior eradication therapy was independently associated with resistance (adjusted Odds Ratio aOR 2.41; 95% Confidence Interval CI 1.29–4.51; p = 0.006), while demographic factors were not. Clarithromycin resistance substantially exceeds recommended thresholds for empirical triple therapy in this setting. Prior eradication therapy is the principal predictor of resistance, supporting resistance-informed and stewardship-oriented management strategies. Full article

Deep reinforcement learning often suffers from inefficient exploration, which is commonly addressed by introducing an auxiliary model that assigns intrinsic rewards when the agent encounters novel scenarios. However, such approaches increase training complexity and computational overhead. This paper proposes an Attribution-Guided Reinforcement Learning (AGRL) framework that exploits real-time attribution analysis to guide exploration in autonomous driving decision-making. The proposed method is built upon the Kolmogorov–Arnold-Network-based Interpretable Deep Reinforcement Learning (KAN-IDRL) framework. Specifically, action-wise attribution patterns are computed online, and perturbations are applied to the state inputs to measure attribution sensitivity. The resulting attribution-sensitivity signal identifies actions whose decision rationales are more locally responsive to state changes, and these actions are therefore preferentially explored. In addition, local attribution results collected from a pretrained interpretable policy are aggregated into global feature-importance scores, which are then used to initialize a trainable prior attention gate in a Prior-Attention-Enhanced Kolmogorov–Arnold Network (PAE-KAN). This design allows the policy to incorporate attribution-derived prior knowledge while maintaining sufficient adaptability for task-specific learning. Experiments across multiple autonomous driving scenarios demonstrate that the proposed AGRL framework achieves faster convergence and competitive final performance compared with representative baseline methods. These findings indicate that attribution information can be transformed from a post hoc interpretability tool into an effective guidance signal for improving reinforcement learning. Full article