Search Results (363)

Transparent clinical decision-making remains a critical barrier to deploying deep learning in medical diagnosis. Post hoc explanation methods approximate model behaviour after training but cannot guarantee that explanations faithfully reflect the underlying reasoning. This study proposes a Self-Explaining Neural Network (SENN) for Parkinson’s Disease (PD) screening via Ground Reaction Force (GRF) gait analysis, enforcing intrinsic interpretability through learnable basis concepts and input-dependent relevance scores computed jointly with the prediction. The architecture combines a four-block residual CNN backbone with stochastic depth regularisation, a 16-concept encoder with diversity and stability constraints, and temperature-scaled probability calibration for reliable clinical operating points. Evaluated on the PhysioNet Gait in Parkinson’s Disease dataset (306 subjects, 16 GRF sensors per foot), SENN achieves a subject-level ROC-AUC of 0.916 [95% CI: 0.867–0.964], sensitivity of 0.913 [0.862–0.963], specificity of 0.671 [0.485–0.858], and Average Precision of 0.942 [0.918–0.967], reported across five independent random seeds. Comparative evaluation against four deep learning baselines—CNN-Residual, BiLSTM, CNN-LSTM, and CNN-Attention—confirms that the interpretability constraints impose no statistically significant reduction in discriminative performance, with all pairwise ROC-AUC confidence intervals overlapping. Concept-level analysis reveals that the three most discriminative concepts correspond to disrupted midfoot loading patterns, increased step-length variability, and bilateral cadence asymmetry—all established biomechanical hallmarks of parkinsonian gait—providing clinically grounded, patient-specific explanations without post hoc approximation. These findings demonstrate that rigorous intrinsic interpretability and competitive predictive accuracy are simultaneously achievable in deep gait analysis, supporting the clinical adoption of transparent diagnostic AI. Full article

Deep reinforcement learning (DRL) for autonomous mobile robot navigation faces several inherent limitations. The stochastic nature of actions generated by DRL policies can undermine performance consistency, while inefficient exploration frequently delays the learning process or prevents the discovery of optimal solutions. This research aims to enhance the robustness of path planning by addressing these challenges. To achieve this goal, we propose a hybrid approach that integrates the flexible decision-making capabilities of deep reinforcement learning with the stability of traditional path planning. The proposed model adopts the Twin Delayed Deep Deterministic Policy Gradient (TD3) network as its base. Notably, we pre-process LiDAR point cloud data to extract only essential features for the state representation, thereby preventing performance degradation from high-dimensional inputs and improving computational efficiency. Our model optimizes the learning process through two core strategies. First, it prioritizes experience data generated during training based on negative rewards, guiding the model to learn more frequently from critical failures rather than redundant successes. Second, it dynamically compares the action proposed by the TD3 network with a goal-oriented action from a classical path-planning algorithm in real time. By selecting the action with the higher estimated value, the model guides the policy toward a stable and effective trajectory from the earliest stages of training. To validate the efficacy of our approach, we conducted simulation-based experiments comparing the performance of the proposed model with existing reinforcement learning networks. To ensure statistical significance and mitigate the impact of random initialization, all reported results are averaged over 10 independent runs with different random seeds. The results quantitatively demonstrate that our model achieves significantly higher and more stable reward values, confirming a robust improvement in the path-planning process. Full article

Instance segmentation in heterogeneous waste scenes remains challenging due to object variability, deformable shapes, partial occlusion, and large appearance differences across packaging types. This study presents a YOLOv11-based deep learning framework for mixed plastic waste instance segmentation, developed to connect visual perception with reliable material quantification. The framework integrates curated instance-level annotations, strict split isolation, multi-stage optimization, training strategy ablation, and seed-robustness analysis to support reproducible model selection. Experimental results on a held-out test set show that the optimized model achieves a mask mAP@50:95 of 0.9337, indicating strong segmentation performance under heterogeneous waste-scene conditions. To extend the analysis beyond standard vision metrics, the framework incorporates a physics-informed mask-to-mass module that converts predicted masks into class-specific mass estimates using geometric calibration and material priors. Applied to a representative stream of 1253 detected objects, the system estimated a total plastic mass of 15.48 ± 1.08 kg, corresponding to a theoretical H₂ potential of 0.41 ± 0.04 kg and a greenhouse-gas avoidance of 34.57 ± 4.15 kg CO₂e. Overall, the proposed framework extends waste-scene understanding beyond vision-level assessment toward physically grounded, data-driven decision support for smart material recovery systems. Full article

Cattle behavior constitutes important phenotypic information reflecting animals’ health status, activity level, and welfare condition, and is therefore of considerable significance for automated monitoring and precision management in smart livestock farming. However, under complex barn conditions, cattle behavior recognition is easily affected by factors such as illumination variation, partial occlusion, background interference, and individual differences, thereby reducing recognition stability and generalization capability. To address these challenges, this study proposes a pose-driven method for cattle behavior recognition in complex barn environments. First, a 16-keypoint annotation scheme suitable for describing bovine posture, termed cow16, was constructed. Based on this scheme, OpenPose was employed to extract heatmaps (HMs) and part affinity fields (PAFs), which were then used to build an intermediate HM/PAF posture representation. Subsequently, this representation was taken as the input to a lightweight convolutional neural network for classifying three behavioral categories: stand, walk, and lying. On this basis, class-imbalance correction during training and a multi-random-seed logits ensemble strategy during inference were further introduced. In addition, knowledge distillation was adopted to transfer knowledge from a high-performance teacher model to a lightweight student model. Experimental results demonstrate that training-stage class-imbalance correction and inference-stage multi-random-seed logits ensembling exhibit strong complementarity; when combined, the AB configuration improves the test-set Macro-F1 by 3.83 percentage points. Moreover, the distilled student model still achieves competitive recognition performance while maintaining 1× inference cost, indicating a favorable trade-off between accuracy and efficiency. This study provides a useful reference for deployment-oriented cattle behavior recognition in smart farming scenarios and offers a lightweight technical basis for subsequent practical applications. Full article

The current study assesses farmers’ knowledge of land preparation for potato planting, potato crop inputs and production practices, healthy, high-quality, and disease-free potato seeds, and their perceptions of agricultural extension services. A stratified random sample of 262 potato farmers from Hail, Qassim, Tabuk, Riyadh, and Al-Jawf was selected according to the Yamane equation. The number of completed and validated questionnaires was 231. Findings revealed that the majority of respondents have strong knowledge of land preparation for potato planting, potato crop production practices, and the selection of healthy, high-quality, and disease-free potato seeds. Moreover, the majority of farmers agreed with the role of agricultural extension in disseminating knowledge of sustainable agricultural potato cultivation practices. Farmers’ age and education level significantly influenced their knowledge of selecting healthy, high-quality, and disease-free potato seeds. Farming experience significantly influenced knowledge of land preparation for potato planting, crop inputs, production practices, and high-quality potato seeds. Monthly farm income and income from potato farms significantly influenced farmers’ knowledge of land preparation for potato planting, potato crop inputs, production practices, and healthy, high-quality, and disease-free potato seed selection. Regarding agricultural extension services, education level, monthly farm income, and income from potato crops influenced farmers’ perceptions of their effectiveness in disseminating information about sustainable agricultural practices. Moreover, the findings of multiple regressions indicate that farmers’ income from potato farms affects their knowledge of land preparation and healthy, high-quality, and disease-free potato seeds. Farming experience and income from potato farms significantly affect farmers’ knowledge of crop inputs and production practices. Education and monthly farm income affect farmers’ perceptions of agricultural extension services. The study emphasizes the need for educational programs, training, and workshops under the supervision of the Agricultural Extension Department to enhance farmers’ knowledge of sustainable potato cultivation practices. The government should provide subsidized advanced agricultural technologies in the study area, thereby enhancing crop production and livelihoods. Support from the government and the extension department would help reduce potato imports and the economic burden by improving local potato production. Full article

In recent years, genomic selection (GS) has been widely adopted in plant breeding; however, its practical application is constrained by the high cost of genotyping large segregating populations. To address this issue, this study employed a Quantitative Trait Nucleotide (QTN)-assisted GS strategy to evaluate its efficiency in reducing genotyping costs for soybean seed oil content (OC) and protein content (PC). Based on six multi-parent F₄ populations (n = 4404) derived from seven elite soybean cultivars, which were genotyped using a 20K SNP chip, we identified 83 and 110 QTNs that were significantly associated with OC and PC, respectively. Among these loci, 37 and 62 QTNs were specific to OC and PC, respectively. Genomic prediction accuracies were evaluated across different training population (TP) sizes using three marker panels: genome-wide SNPs, all detected QTNs, and trait-specific QTNs. The panel consisting of all detected QTNs exhibited significantly higher prediction accuracy than the other two panels, except for PC when using 90% of the population as the training set. Phenotypic verification of the selected individuals showed that the PC-specific QTN panel yielded higher PC values and increased OC + PC values compared with the other marker panels. These results demonstrate that a small set of QTNs provides a cost-effective approach for genomic selection in practical soybean breeding programs. Full article

A network intrusion detection system (NIDS) plays a critical role in protecting modern networked environments, but conventional approaches often struggle to balance the detection of previously unseen attacks with a low false alarm rate. This study proposes a hybrid intrusion detection model, HybridSAGETransformerGlobal, which integrates a SAGEConv-based graph neural network (GNN) and a Transformer encoder to jointly learn local structural information and global contextual dependencies from network traffic. In the proposed framework, network flows are represented as graph nodes, and edges are constructed using IP-group-aware k-nearest neighbors (KNNs) together with a temporal chain. The model further incorporates a gated fusion mechanism, multiple positional encodings, class weighting, label smoothing, and early stopping to improve training stability and detection performance. The proposed method was evaluated under a unified preprocessing and training pipeline on two benchmark datasets, UNSW-NB15 and CIC-IDS2017, using up to approximately 100,000 flow samples per dataset, and was compared with GCN, GAT, GraphSAGE, and a Transformer-only baseline. On UNSW-NB15, repeated-run evaluation over five random seeds showed that the proposed model achieved an accuracy of 0.9841 ± 0.0006, a macro-precision of 0.9684 ± 0.0010, a macro-recall of 0.9818 ± 0.0026, and a macro-F1-score of 0.9749 ± 0.0011, with statistically significant improvements over the strongest baseline in the macro-F1-score. On CIC-IDS2017, the proposed hybrid model also showed consistently strong performance, achieving an accuracy of 0.9749, a macro-precision of 0.9513, a macro-recall of 0.9722, a macro-F1-score of 0.9613, and an ROC-AUC of 0.9957. Additional ablation, sensitivity, and baseline re-optimization analyses further supported the robustness of the proposed design. These results suggest that a coordinated hybrid architecture combining structural graph learning and long-range contextual modeling can provide an effective framework for robust flow-based network intrusion detection under the evaluated settings. Full article

Old-vine vineyards often contain dozens of grapevine varieties intermingled and irregularly distributed, making plant-level varietal identification slow and expensive when based on ampelography or molecular approaches. This paper proposes a field-oriented computer-vision pipeline for Vitis vinifera variety identification using images with a natural background from the historic “Vinha Maria Teresa” parcel (Quinta do Crasto, Portugal). A single-class YOLO11 detector is trained to localize the vine leaf and generate standardized crops, and a YOLO11 classifier is then fine-tuned on leaf regions of interest (ROIs) for eight selected varieties in the Douro UNESCO region. We annotated 2015 vineyard images for classification and supplemented detection training with 2648 additional leaf images; detectors (YOLO11n/s/m) were benchmarked under four augmentation regimes and evaluated on a fixed 48-image subset, including runtime on CPU and GPU. The best detector reached mAP@50–95 of 0.918 on the benchmark, while YOLO11n achieved ∼27 FPS on CPU for fast cropping. On a 303-image test set, the best classifier (YOLO11s with mixed augmentations) achieved 94.06% Top-1 accuracy, 93.92% macro-F1, and 100% Top-5 accuracy with remaining errors concentrated among morphologically similar varieties. To assess deployment-oriented performance, classifiers trained under three input settings (manual crops, detector-generated crops, and full images) were evaluated on a held-out 48-image benchmark subset; removing the detection step reduced Top-1 accuracy from 75.00% to 68.75%, while the gap between manual and automatic crops was only 2.44 pp on successfully detected images with detection failures (14.6%) representing the primary operational bottleneck. Repeated retraining of the best manual-crop YOLO11s configuration across multiple random seeds showed stable performance with low variability in Top-1 accuracy and macro-F1. Under identical training conditions, ResNet50 and EfficientNet-B0 provided competitive baselines, but YOLO11s remained the strongest overall model on the held-out field benchmark. These results indicate that lightweight leaf detection plus crop-based classification can support scalable varietal identification in old vineyards under realistic acquisition conditions. Full article

Public deployment of generative AI in cultural institutions is constrained by small, rights-restricted datasets, strict latency and runtime-stability requirements, and limits on visitor-data collection. This study presents a deployment-oriented framework for adapting a pre-trained text-to-image diffusion foundation model to a heritage-specific visual domain using Low-Rank Adaptation (LoRA). A Stable Diffusion v1.5 backbone is specialized through data-centric curation and LoRA fine-tuning, then served through an asynchronous edge architecture that links a Unity client and a local Python (version 3.10) inference server for public-facing operation on a native 400 × 1080 vertical canvas. To support deployment decisions without collecting personally identifiable information, the system records only anonymous operational logs and evaluates sustained-load behavior under repeated inference. In a 1000-iteration profiling test, the proposed configuration maintained stable runtime behavior without observable upward memory drift, with a peak allocated VRAM of 3.04 GB and an average end-to-end latency of 3.12 s. An 8 h field deployment further indicated service continuity under public interaction, while a CLIP-based proxy analysis under matched prompts and seeds suggested improved relative style controllability after adaptation (0.848 vs. 0.799). Rather than claiming cultural authenticity or visitor-level effects, this study offers a data-centric, deployment-oriented methodology for operating public-facing generative AI under small-data, latency, and privacy constraints. Full article

Road traffic safety is central to socially resilient and sustainable cities, yet many middle-income countries lack harmonized subnational data on exposure, infrastructure, and enforcement. This study examines whether routinely available demographic composition can serve as a practical structural baseline for provincial traffic accident rates and as a diagnostic layer for richer safety models. Using official province–year data from Türkiye (2008–2019 and 2022–2024; n = 1215), demographic shares by sex, education, and age were treated as compositional inputs and transformed using isometric log-ratio (ILR) methods, with GDP per person included as a scalar covariate. A Tabular Residual Network (ResNet) was trained on the historical panel and evaluated on a post-period calibration/evaluation window (2022–2024), which was used for checkpoint selection and seed screening rather than as an independent held-out test set. Among the evaluated specifications, the ResNet seed-ensemble achieved the strongest performance on the 2022–2024 calibration/evaluation period (R² = 0.5717), outperforming the best single-seed model (R² = 0.5539), a province-specific last-value-carried-forward temporal heuristic based on 2019 values (R² = 0.4779), tree-based tabular benchmarks (Random Forest: R² = 0.1328; XGBoost: R² = 0.0706), and pooled statistical reference models (linear: R² = 0.1375; negative binomial: R² = 0.0686; Poisson: R² = −0.0634). Year-wise diagnostics indicated gradual temporal drift, suggesting that periodic recalibration or the inclusion of additional policy-relevant covariates is needed to preserve calibration. Overall, ILR-based compositional geodemography provides a scalable and interpretable baseline for traffic safety monitoring and prioritization in data-constrained settings. Full article

Background/Objectives: Tablet development requires simultaneous optimization of multiple quality attributes under limited experimental budgets, yet formulation–property relationships are highly nonlinear in mixture systems. To support pre-formulation decision-making prior to extensive tablet prototyping, this study proposes an AI framework that organizes formulation and process data together with raw-material property records into a reusable database, and enriches conventional composition/process features with physically motivated mixture descriptors derived from raw-material properties and formulation/process settings. Methods: Mixture-level scalar descriptors are constructed by composition-weighted aggregation of material properties, and particle size distribution (PSD) is incorporated via a compact set of summary statistics computed from composition-weighted mixture PSDs. Three feature sets are compared: (i) Materials + Processes (MP), (ii) MP with scalar Descriptors (MPD), and (iii) MPD with PSD summaries (MPDD). Five target properties are modeled: hardness, disintegration time, flow function, cohesion, and thickness. We train and evaluate Random Forest, Extra Trees Regressor, Lasso, Partial Least Squares, Support Vector Regression, and a multi-branch neural network that processes the three feature blocks separately and concatenates them for prediction. For interpolation assessment, repeated Train/Dev/Test splitting (5:3:2) across multiple random seeds is used, and the effect of feature augmentation is quantified by paired RMSE improvements with bootstrap confidence intervals and paired Wilcoxon signed-rank tests. To assess robustness under practical formulation updates, rolling-origin time-series splits are employed and Applicability Domain indicators are computed to characterize out-of-distribution coverage. Results: Across interpolation evaluations, mixture-descriptor augmentation (MPD/MPDD) improves hardness and disintegration time in most settings, whereas gains for flow function are smaller and cohesion/thickness show mixed effects under limited sample sizes. Conclusions: Under extrapolation-oriented evaluation, the descriptors can improve hardness but may degrade disintegration-time prediction under covariate shift, emphasizing the need for careful descriptor selection and dimensionality control when deploying pre-formulation predictors. Full article

The continuous prediction and uncertainty quantification of unconfined compressive strength (UCS) and the fracture-related index of anisotropy (FRIA) are essential for optimizing drilling operations and hydraulic fracturing design in shale gas development. However, machine-learning-based log inversion often suffers from (1) spatial information leakage caused by autocorrelation in well logs, (2) implicit target contamination during multi-source data fusion, and (3) biased evaluation under random data splitting, which can overestimate apparent performance and underestimate extrapolation risk in deep heterogeneous intervals. To address these limitations, we propose a leakage-free, physics-constrained framework for predicting UCS and FRIA in the Weiyuan shale gas reservoir. Using 18,440 quality-controlled, depth-aligned samples, we adopt a contiguous depth-based split that preserves stratigraphic continuity while isolating training, validation, and test intervals to block spatial leakage. Under a strict leakage-free protocol, we evaluate single-task ensemble trees (STL-RF/HGB), a multi-task neural network (MTL-MLP), and a physics-informed variant (PINN-MLP) for deep-interval stabilization. The best model is target-dependent: STL-RF achieves R² = 0.984 for FRIA, whereas MTL-MLP attains R² = 0.874 for UCS. For deep formations (>4800 m), PINN-MLP with a depth-continuity constraint reduces deep-interval prediction error by 47.5%. Multi-seed experiments with 95% Student’s t confidence intervals further confirm robustness. Overall, the framework provides a reproducible workflow for continuous geomechanical-parameter prediction and risk-aware deployment in deep unconventional reservoirs. Full article

Deploying lightweight convolutional neural networks (CNNs) to provide vision services on resource-constrained Internet of Things (IoT) devices has become the mainstream approach to addressing computing and energy consumption constraints. However, these IoT devices often operate in complex outdoor environments (e.g., fog, rain, and snow), and the quality of the data they collect is easily degraded, causing standard lightweight CNNs to experience a significant performance drop under such corrupted data. To this end, this paper proposes a Generative Nonlinear Transformation Filter (GNTF) method to improve the generalization performance of lightweight CNNs on corrupted data. The core of the GNTF is that only a portion of the filters are used as learnable parameters (named seed filters), while the remaining filters are generated by applying the nonlinear transformation to the seed filters, which is randomly initialized and fixed during training. This design makes the model parameters less dependent on the training data distribution, thereby regularizing the model, mitigating overfitting, and enhancing its robustness to data degradation. The GNTF further analyzes the structural characteristics of lightweight CNNs, showing that significant performance improvements can be achieved simply by replacing the depthwise convolutional modules. Furthermore, this paper examines the properties of various nonlinear transformation functions and finds that model robustness can be improved by applying simple translations. To verify the effectiveness of the GNTF, we conducted extensive experiments on the CIFAR-10/-100, CIFAR-10-C/-100-C, and ICONS-50 datasets, using the MobileNetV2, ShuffleNetV2, EfficientNet, and GhostNet models. The results show that the proposed GNTF can improve the model’s accuracy on corrupted data while reducing the number of trainable parameters in most cases. For example, on the CIFAR-10-C dataset, ShuffleNetV2 with the GNTF improves accuracy by about 3.3% over the original model while slightly reducing the number of trainable parameters. Full article

We introduce Self-Competitive Distillation (SCD), a parameter-neutral training strategy aimed at influencing optimization dynamics without increasing model size or relying on external teachers. Two identical instances of the same architecture, initialized with different random seeds, are trained jointly and dynamically exchange asymmetric teacher–student roles based on instantaneous performance, enabling knowledge transfer between diverging optimization trajectories. Under fixed parameter and training budgets, SCD is observed to improve the realized effective capacity of lightweight architectures, yielding a higher test accuracy at matched epochs. Across multiple lightweight vision models and datasets, SCD demonstrates gains in both in-domain performance and cross-domain generalization, as measured by xScore. These results suggest that, within the evaluated experimental conditions, SCD can help mobile models make more effective use of training dynamics, while the underlying architecture remains the primary determinant of effective capacity in resource-constrained settings. Full article

This study addresses the automatic classification of sugar beet seeds according to their spraying levels using RGB images, aiming to enable a fast, practical, and non-destructive early warning system without chemical analysis. A dataset of 16,519 seed images acquired under controlled lighting conditions was used to evaluate YOLOv8-CLS and YOLO11-CLS architectures, including the n, s, m, l, and x scale variants within the Ultralytics framework. All experiments were conducted using a 10-fold cross-validation strategy, with models trained under different batch size and learning rate configurations. The results indicate that both architectures achieve reliable performance, with accuracy values ranging from approximately 78–83% for YOLOv8-CLS and 80–82% for YOLO11-CLS models. ROC-AUC scores consistently above 0.94 demonstrate strong inter-class discrimination. Misclassification analysis shows that errors mainly occur between visually similar intermediate treatment levels, particularly 25% and 50%. Despite this challenge, low log-loss values and balanced precision–recall profiles indicate stable decision behavior. Overall, the findings confirm that sugar beet seed treatment levels can be effectively distinguished using only RGB imagery, providing a potentially low-cost and scalable approach for early warning and quality control in seed treatment processes. Full article