Search Results (36)

In practical well-logging datasets, severe missing values, anomalous disturbances, and highly imbalanced lithology classes are pervasive. To address these challenges, this study proposes a well-logging lithology identification framework that combines Robust Feature Engineering (RFE) with quality-aware XGBoost. Instead of relying on interpolation-based data cleaning, RFE uses sentinel values and a meta-information tensor to explicitly encode patterns of missingness and anomalies, and incorporates sliding-window context to transform data defects into discriminative auxiliary features. In parallel, a quality-aware sample-weighting strategy is introduced that jointly accounts for formation boundary locations and label confidence, thereby mitigating training bias induced by long-tailed class distributions. Experiments on the FORCE 2020 lithology prediction dataset demonstrate that, relative to baseline models, the proposed method improves the weighted F1 score from 0.66 to 0.73, while Boundary F1 and the geological penalty score are also consistently enhanced. These results indicate that, compared with traditional workflows that rely solely on data cleaning, explicit modeling of data incompleteness provides more pronounced advantages in terms of robustness and engineering applicability. Full article

To address the challenge in multi-view learning within practical application scenarios—such as smart grid multi-source monitoring and complex environment perception—where view quality often exhibits significant dynamic time-varying characteristics due to environmental interference or sensor failures, rendering traditional static fusion methods inadequate for maintaining decision-making reliability, a general adaptive robust fusion method, termed the Consensus-Aware Residual Gating (CARG) mechanism, is proposed. This approach constructs a sample-level dynamic quality assessment framework. It computes three interpretable metrics—self-confidence, group consensus, and complementary uniqueness—for each feature view in real time, thereby accurately quantifying instantaneous data quality fluctuations. A multiplicative gating structure is employed to generate dynamic weights based on these metrics, embedding a structural inductive bias of group consensus priority. Specifically, when quality degradation triggers view conflicts, the mechanism prioritizes majority-consistent reliable signals to suppress noise; when high-value complementary information emerges, it cautiously incentivizes discriminative features to rectify group bias. This design achieves adaptive perception of quality variations and robust decision-making without relying on additional weight-prediction networks. Extensive experiments are conducted on general multi-view benchmarks. The results demonstrate that CARG surpasses mainstream algorithms in accuracy, robustness, and interpretability. It effectively shields decisions from anomalous feature interference and validates its efficacy as a universal fusion framework for dynamic environments. Full article

Urban air pollution remains a critical public health issue, especially in densely populated cities where pedestrians experience direct exposure to traffic-related and environmental emissions. This study develops and tests a pollution-aware pedestrian routing framework for Thessaloniki, Greece, designed to minimize environmental exposure while maintaining route efficiency. The framework combines high-resolution air-quality data and computational techniques to represent pollution patterns at pedestrian scale. Air-quality is expressed as a continuous European Air Quality Index (EAQI) and is embedded in a network-based routing engine (OSRM) that balances exposure and distance through a weighted optimization function. Using 3000 randomly sampled origin-destination pairs, exposure-aware routes are compared with conventional shortest-distance paths across short, medium, and long walking trips. Results show that exposure-aware routes reduce cumulative AQI exposure by an average of 4% with only 3% distance increase, while maintaining stable scaling across all route classes. Exposure benefits exceeding 5% are observed for approximately 8% of medium-length routes and 24% of long routes, while short routes present minimal or no detours, but lower exposure benefits. These findings confirm that integrating high-resolution environmental data into pedestrian navigation systems is both feasible and operationally effective, providing a practical foundation for future real-time, pollution-aware mobility services in smart cities. Full article

Ensuring sustained driver attention is critical for intelligent transportation safety systems; however, the performance of data-driven driver distraction detection models is often limited by the high cost of large-scale manual annotation. To address this challenge, this paper proposes an adaptive semi-supervised driver distraction detection framework based on teacher–student learning and deformable pyramid feature fusion. The framework leverages a limited amount of labeled data together with abundant unlabeled samples to achieve robust and scalable distraction detection. An adaptive pseudo-label optimization strategy is introduced, incorporating category-aware pseudo-label thresholding, delayed pseudo-label scheduling, and a confidence-weighted pseudo-label loss to dynamically balance pseudo-label quality and training stability. To enhance fine-grained perception of subtle driver behaviors, a Deformable Pyramid Sparse Transformer (DPST) module is integrated into a lightweight YOLOv11 detector, enabling precise multi-scale feature alignment and efficient cross-scale semantic fusion. Furthermore, a teacher-guided feature consistency distillation mechanism is employed to promote semantic alignment between teacher and student models at the feature level, mitigating the adverse effects of noisy pseudo-labels. Extensive experiments conducted on the Roboflow Distracted Driving Dataset demonstrate that the proposed method outperforms representative fully supervised baselines in terms of mAP@0.5 and mAP@0.5:0.95 while maintaining a balanced trade-off between precision and recall. These results indicate that the proposed framework provides an effective and practical solution for real-world driver monitoring systems under limited annotation conditions. Full article

Few-shot classification aims to generalize from very limited samples, providing an effective solution for data-scarce scenarios. From a symmetry viewpoint, an ideal Few-Shot classifier should be invariant to class permutations and treat support and query features in a balanced manner, preserving intra-class cohesion while enlarging inter-class separation in the embedding space. However, existing methods often violate this symmetry because prototypes are estimated from few noisy samples, which induces asymmetric representations and task-dependent biases under complex inter-class relations. To address this, we propose FC-SBAAT, feature collaboration, and Sparse Bias-Aware Attention Transformer, a framework that explicitly leverages symmetry in feature collaboration and prototype construction. First, we enhance symmetric interactions between support and query samples in both attention and contrastive subspaces and adaptively fuse these complementary representations via learned weights. Second, we refine prototypes by symmetrically aggregating intra-class features with learned importance weights, improving prototype quality while maintaining intra-class symmetry and increasing inter-class discrepancy. For matching, we introduce a Sparse Bias-Aware Attention Transformer that corrects asymmetric task bias through bias-aware attention with a low computational overhead. Extensive experiments show that FC-SBAAT achieves 55.71% and 73.87% accuracy for 1-shot and 5-shot tasks on MiniImageNet and 70.37% and 83.86% on CUB, outperforming prior methods. Full article

The automation of quality control in agricultural food processing, particularly the detection of incomplete peeling in taro, constitutes a critical frontier for ensuring food safety and optimizing production efficiency in the Industry 4.0 era. However, this domain is fraught with significant technical challenges, primarily stemming from the inherent visual characteristics of residual peel: extremely minute scales relative to the vegetable body, highly irregular morphological variations, and the dense occlusion of objects on industrial conveyor belts. To address these persistent impediments, this study introduces a comprehensive solution comprising a specialized dataset and a novel detection architecture. We established the Taro Peel Industrial Dataset (TPID), a rigorously annotated collection of 18,341 high-density instances reflecting real-world production conditions. Building upon this foundation, we propose MDB-YOLO, a lightweight, multi-dimensional bionic detection model evolved from the YOLOv8s architecture. The MDB-YOLO framework integrates a synergistic set of innovations designed to resolve specific detection bottlenecks. To mitigate the conflict between background texture interference and tiny target detection, we integrated the C2f_EMA module with a Wise-IoU (WIoU) loss function, a combination that significantly enhances feature response to low-contrast residues while reducing the penalty on low-quality anchor boxes through a dynamic non-monotonic focusing mechanism. To effectively manage irregular peel shapes, a dynamic feature processing chain was constructed utilizing DySample for morphology-aware upsampling, BiFPN_Concat2 for weighted multi-scale fusion, and ODConv2d for geometric preservation. Furthermore, to address the issue of missed detections caused by dense occlusion in industrial stacking scenarios, Soft-NMS was implemented to replace traditional greedy suppression mechanisms. Experimental validation demonstrates the superiority of the proposed framework. MDB-YOLO achieves a mean Average Precision (mAP50-95) of 69.7% and a Recall of 88.0%, significantly outperforming the baseline YOLOv8s and advanced transformer-based models like RT-DETR-L. Crucially, the model maintains high operational efficiency, achieving an inference speed of 1.1 ms on an NVIDIA A100 and reaching 27 FPS on an NVIDIA Jetson Xavier NX using INT8 quantization. These findings confirm that MDB-YOLO provides a robust, high-precision, and cost-effective solution for real-time quality control in agricultural food processing, marking a significant advancement in the application of computer vision to complex biological targets. Full article

The precise localization of the pith within sawn timber cross-sections is essential for improving downstream processing accuracy in modern wood manufacturing. Existing industrial workflows still rely heavily on manual interpretation, which is labor-intensive, error-prone, and unsuitable for real-time quality control. However, automatic pith detection is challenging due to the small size of the pith, its visual similarity to knots and cracks, and the dominance of negative samples (boards without visible pith) in practical scenarios. To address these challenges, this study develops Wood-YOLOv11, a task-adapted YOLOv11-based pith detection model optimized for real-time and high-precision operation in wood processing environments. The proposed approach incorporates: (1) a dedicated sawn-timber cross-section dataset including multiple species, mixed imaging sources, and clearly annotated pith positions; (2) a negative-sample-aware training strategy that explicitly leverages pithless boards and weighted binary cross-entropy to mitigate extreme class imbalance; (3) a high-resolution (840 × 840) input configuration and optimized loss weighting to improve small-target localization; and (4) a comprehensive evaluation protocol including false-positive analysis on pithless boards and comparison with mainstream detectors. Validated on a comprehensive, custom-annotated sawn timber dataset, our model demonstrates excellent performance. It achieves a mean Average Precision (mAP@0.5) of 92.1%, a Precision of 95.18%, and a Recall of 87.72%, proving its ability to handle high-texture backgrounds and small target sizes. The proposed Wood-YOLOv11 model provides a robust, real-time, and efficient technical solution for the intelligent transformation of the wood processing industry. Full article

Background: Pregnancy induces substantial cardiovascular remodeling, yet whether maternal cardiac adaptation differs across ethnic groups remains unclear. Body size, ventricular geometry, and thoracoabdominal configuration may modulate key functional indices such as left ventricular ejection fraction (LVEF) and global longitudinal strain (LV-GLS). This systematic review compared echocardiographic characteristics between Asian and Western healthy pregnant women in late gestation and explored physiological mechanisms underlying observed differences. Methods: A comprehensive search of PubMed, Scopus, and EMBASE identified studies reporting transthoracic echocardiography in healthy singleton third-trimester pregnancies across Asian and Western populations. Extracted variables included anthropometry, ventricular dimensions and volumes, LVEF, and LV-GLS. Pooled estimates were calculated using inverse-variance weighting, with heterogeneity quantified using the I² statistic. Study quality was assessed with the NIH Case–Control Quality Assessment Tool. Comparative forest plots visualized population differences. Results: Twenty studies involving 1431 participants (578 Asian and 853 Western women) met inclusion criteria. Asian women consistently exhibited smaller ventricular chambers, higher LVEF, and more favorable LV-GLS. Importantly, these differences persisted after indexing LV-GLS to BSA, indicating that body-size normalization attenuates—but does not eliminate—population differences in myocardial deformation. Western women demonstrated slightly attenuated GLS despite preserved LVEF, plausibly attributable to larger cardiac size, higher wall stress, greater diaphragmatic elevation, and increased extrinsic thoracic compression. Between-study heterogeneity was substantial (I² > 95%) due to variation in imaging platforms, strain software, and population characteristics. Methodological quality was fair, with frequent lack of sample-size justification and incomplete confounder adjustment. Conclusions: Healthy Asian pregnant women display a hyperdynamic systolic phenotype, whereas Western women show a physiologically appropriate, load-related attenuation of LV-GLS with preserved LVEF. These findings highlight the need for ethnicity-associated and anatomy-aware echocardiographic reference values and support incorporating thoracic geometric indices, such as the modified Haller Index, into strain interpretation during pregnancy. Full article

This paper addresses semi-supervised anomaly detection in settings where only a small subset of normal data can be labeled. Such conditions arise, for example, in industrial quality control of windshield wiper noise, where expert labeling is costly and limited. Our objective is to learn a one-class decision boundary that leverages the geometry of unlabeled data while remaining robust to contamination and scarcity of labeled normals. We propose a graph-attention-regularized deep support vector data description (GAR-DSVDD) model that combines a deep one-class enclosure with a latent k-nearest-neighbor graph whose edges are weighted by similarity- and score-aware attention. The resulting loss integrates (i) a distance-based enclosure on labeled normals, (ii) a graph smoothness term on squared distances over the attention-weighted graph, and (iii) a center-pull regularizer on unlabeled samples to avoid over-smoothing and boundary drift. Experiments on a controlled simulated dataset and an industrial windshield wiper acoustics dataset show that GAR-DSVDD consistently improves the F1 score under scarce label conditions. On average, F1 increases from 0.78 to 0.84 on the simulated benchmark and from 0.63 to 0.86 on the industrial case study relative to the best competing baseline. Full article

Plant disease recognition is a critical technology for ensuring food security and advancing precision agriculture. However, challenges such as class imbalance, heterogeneous image quality, and limited model interpretability remain unresolved. In this study, we propose a Synergistic Dual-Augmentation and Class-Aware Hybrid (SDA-CAH) model designed to achieve robust and interpretable recognition of plant diseases. Our approach introduces two innovative augmentation strategies: (1) an optimized MixUp method that dynamically integrates class-specific features to enhance the representation of minority classes; and (2) a customized augmentation pipeline that combines geometric transformations with photometric perturbations to strengthen the model’s resilience against image variability. To address class imbalance, we further design a class-aware hybrid sampling mechanism that incorporates weighted random sampling, effectively improving the learning of underrepresented categories and optimizing feature distribution. Additionally, a Grad-CAM–based visualization module is integrated to explicitly localize lesion regions, thereby enhancing the transparency and trustworthiness of the predictions. We evaluate SDA-CAH on the PlantVillage dataset using a pretrained EfficientNet-B0 as the backbone network. Systematic experiments demonstrate that our model achieves 99.95% accuracy, 99.89% F1-score, and 99.89% recall, outperforming several strong baselines, including an optimized Xception (99.42% accuracy, 99.39% F1-score, 99.41% recall), standard EfficientNet-B0 (99.35%, 99.32%, 99.33%), and MobileNetV2 (95.77%, 94.52%, 94.77%). For practical deployment, we developed a web-based diagnostic system that integrates automated recognition with treatment recommendations, offering user-friendly access for farmers. Experimental evaluations indicate that SDA-CAH outperforms existing approaches in predictive accuracy and simultaneously defines a new paradigm for interpretable and scalable plant disease recognition, paving the way for next-generation precision agriculture. Full article

Efficient and stable path planning in dynamic and obstacle-dense environments, such as large-scale structure assembly measurement, is essential for improving the practicality and environmental adaptability of mobile robots in measurement and quality inspection tasks. However, traditional reinforcement learning methods often suffer from inefficient use of experience and limited capability to represent policy structures in complex dynamic scenarios. To overcome these limitations, this study proposes a method named DPDQN-TER that integrates Transformer-based sequence modeling with a multi-branch parameter policy network. The proposed method introduces a temporal-aware experience replay mechanism that employs multi-head self-attention to capture causal dependencies within state transition sequences. By dynamically weighting and sampling critical obstacle-avoidance experiences, this mechanism significantly improves learning efficiency and policy performance and stability in dynamic environments. Furthermore, a multi-branch parameter policy structure is designed to decouple continuous parameter generation tasks of different action categories into independent subnetworks, thereby reducing parameter interference and improving deployment-time efficiency. Extensive simulation experiments were conducted in both static and dynamic obstacle environments, as well as cross-environment validation. The results show that DPDQN-TER achieves higher success rates, shorter path lengths, and faster convergence compared with benchmark algorithms including Parameterized Deep Q-Network (PDQN), Multi-Pass Deep Q-Network (MPDQN), and PDQN-TER. Ablation studies further confirm that both the Transformer-enhanced replay mechanism and the multi-branch parameter policy network contribute significantly to these improvements. These findings demonstrate improved overall performance (e.g., success rate, path length, and convergence) and generalization capability of the proposed method, indicating its potential as a practical solution for autonomous navigation of mobile robots in complex industrial measurement scenarios. Full article

Background and objectives: Evaluating Large Language Models (LLMs) presents two interrelated challenges: the general problem of assessing model performance across diverse tasks and the specific problem of using LLMs themselves as evaluators in pedagogical and educational contexts. Existing approaches often rely on single metrics or opaque preference-based methods, which fail to capture critical dimensions such as explanation quality, robustness, and argumentative diversity—attributes essential in instructional settings. This paper introduces PEARL, a novel framework conceived, operationalized, and evaluated in the present work using LLM-based scorers, designed to provide interpretable, reproducible, and pedagogically meaningful assessments across multiple performance dimensions. Methods: PEARL integrates three specialized rubrics—Technical, Argumentative, And Explanation-focused—covering aspects such as factual accuracy, clarity, completeness, originality, dialecticality, and explanatory usefulness. The framework defines seven complementary metrics: Rubric Win Count (RWC), Global Win Rate (GWR), Rubric Mean Advantage (RMA), Consistency Spread (CS), Win Confidence Score (WCS), Explanation Quality Index (EQI), and Dialectical Presence Rate (DPR). We evaluated PEARL by evaluating eight open-weight instruction-tuned LLMs across 51 prompts, with outputs scored independently by GPT-4 and LLaMA 3:instruct. This constitutes LLM-based evaluation, and observed alignment with the GPT-4 proxy is mixed across metrics. Results: Preference-based metrics (RMA, RWC, and GWR) show evidence of group separation, reported with bootstrap confidence intervals and interpreted as exploratory due to small samples, while robustness-oriented (CS and WCS) and reasoning-diversity (DPR) metrics capture complementary aspects of performance not reflected in global win rate. RMA and RWC exhibit statistically significant, FDR-controlled correlations with the GPT-4 proxy, and correlation mapping highlights the complementary and partially orthogonal nature of PEARL’s evaluation dimensions. Originality: PEARL is the first LLM evaluation framework to combine multi-rubric scoring, explanation-aware metrics, robustness analysis, and multi-LLM-evaluator analysis into a single, extensible system. Its multidimensional design supports both high-level benchmarking and targeted diagnostic assessment, offering a rigorous, transparent, and versatile methodology for researchers, developers, and educators working with LLMs in high-stakes and instructional contexts. Full article

Soil liquefaction poses a significant risk to foundations during earthquakes, prompting the need for simple, risk-aware screening tools that go beyond single deterministic boundaries. This study creates a probability-calibrated dual-threshold screening rule using a random forest (RF) classifier trained on 208 SPT case histories with quality-based weights (A/B/C = 1.0/0.70/0.40). The model is optimized with random search and calibrated through isotonic regression. Iso-probability contours from 1000 bootstrap samples produce paired thresholds for fines-corrected, overburden-normalized blow count N_1,60,CS and normalized cyclic stress ratio CSR_7.5,1 at target liquefaction probabilities P_liq = 5%, 20%, 50%, 80%, and 95%, with 90% confidence intervals. On an independent test set (n = 42), the calibrated model achieves AUC = 0.95, F₁ = 0.92, and a better Brier score than the uncalibrated RF. The screening rule classifies a site as susceptible when N_1,60,CS is at or below and CSR_7.5,1 is at or above the probability-specific thresholds. Designed for level ground, free field, and clean-to-silty sand sites, this tool maintains the familiarity of SPT-based charts while making risk assessment transparent and auditable for different facility importance levels. Sensitivity tests show its robustness to reasonable rescaling of quality weights. The framework offers transparent thresholds with uncertainty bands for routine preliminary assessments and to guide the need for more detailed, site-specific analyses. Full article

Precise underwater object detectors can provide Autonomous Underwater Vehicles (AUVs) with good situational awareness in underwater environments, supporting a wide range of unmanned exploration missions. However, the quality of optical imaging is often insufficient to support high detector accuracy due to poor lighting and the complexity of underwater environments. Therefore, this paper develops an efficient and precise object detector that maintains high recognition accuracy on degraded underwater images. We design a Cross Spatial Global Perceptual Attention (CSGPA) mechanism to achieve accurate recognition of target and background information. We then construct an Efficient Multi-Scale Weighting Feature Pyramid Network (EMWFPN) to eliminate computational redundancy and increase the model’s feature-representation ability. The proposed Occlusion-Robust Wavelet Network (ORWNet) enables the model to handle fine-grained frequency-domain information, enhancing robustness to occluded objects. Finally, EMASlideloss is introduced to alleviate sample-distribution imbalance in underwater datasets. Our architecture achieves 81.8% and 83.8% mAP on the DUO and UW6C datasets, respectively, with only 7.2 GFLOPs, outperforming baseline models and balancing detection precision with computational efficiency. Full article

This paper addresses the challenges of sample scarcity and class imbalance in remote sensing image semantic segmentation by proposing a decoupled synthetic sample generation framework based on a latent diffusion model. The method consists of two stages. In the label generation stage, we fine-tune a pretrained latent diffusion model with LoRA to generate semantic label masks from textual descriptions. A novel proportion-aware loss function explicitly penalizes deviations from the desired class distribution in the generated mask. In the image generation stage, we use ControlNet to train a multi-condition image generation network that takes the synthesized mask, along with its text description, as input and produces a realistic remote sensing image. The base Stable Diffusion model’s weights remain frozen during this process, with the trainable ControlNet ensuring that outputs are structurally and semantically aligned with the input labels. This two-stage approach yields coherent image–mask pairs that are well-suited for training segmentation models. Experiments show that models trained on the synthetic samples produced by the proposed method achieve high visual quality and semantic consistency. The proportion-aware loss effectively mitigates the impact of minority classes, boosting segmentation performance on under-represented categories. Results also reveal that adding a suitable proportion of synthetic sample improves segmentation accuracy, whereas an excessive share can cause over-fitting or misclassification. Comparative tests across multiple models confirm the generality and robustness of the approach. Full article