Search Results (15)

Conventional methods for calculating sortie mission reliability of shipborne vehicle layouts suffer from excessive computational overhead, long runtimes, and large labeled data requirements. To address these limitations, this work proposes a specialized graph neural network architecture tailored for limited-data small-sample scenarios, denoted as the Small-Sample Graph Neural Network (SS-GNN). The proposed SS-GNN integrates multi-relational graph convolutional layers, an adaptive attention weighting mechanism, small-sample regularization techniques, and an uncertainty quantification module to accurately capture the heterogeneous multidimensional dependencies between vehicles. To further improve learning performance under data-scarce conditions, we employ a hybrid training strategy combining meta-learning-based pretraining, contrastive learning for representation enhancement, knowledge distillation, and transfer learning. Experimental results demonstrate that SS-GNN substantially outperforms traditional reliability calculation methods, classical machine learning models, and state-of-the-art GNN baselines across three key dimensions: predictive accuracy, computational efficiency, and generalization robustness, while also providing theoretically grounded uncertainty estimates for all predictions. This work provides both a theoretical foundation and a practical technical framework for shipborne vehicle reliability prediction and offers a generalizable solution for small-sample graph regression tasks in industrial domains. Future work will focus on extending the approach to extremely low-data regimes via specialized few-shot learning algorithms, incorporating dynamic relation modeling for time-varying sortie processes, and integrating domain knowledge graphs to broaden its operational applicability. Full article

This paper addresses the critical challenge of semantic segmentation for remote sensing images (RSIs) under extremely limited labeled data. A high-quality initial model is paramount for downstream semi-supervised or weakly supervised learning paradigms, as it mitigates error propagation from the outset. We conducted a systematic investigation into self-supervised pretraining to serve this precise need. Within the low-label regime, we identify and tackle two pivotal factors limiting performance: (1) the domain shift between large-scale pretraining data and specific target tasks, and (2) the deficiency in local feature learning caused by large-window masking in visual foundation model (VFM) pretraining. To resolve these issues, we first benchmark various pretraining strategies, demonstrating that a two-phase General-Purpose Pretraining (GPPT) followed by Domain-Adaptive Pretraining (DAPT) framework is optimal, significantly outperforming both single-phase methods and the existing two-phase paradigm initialized from ImageNet. Subsequently, we propose an Edge-Guided Masked Image Modeling (EGMIM) method for the DAPT phase, which explicitly integrates edge priors to guide the masking and reconstruction process, thereby enhancing the model’s capability to capture fine-grained local structures. Extensive experiments on four RSI benchmarks validate the effectiveness of our approach, showing consistent and substantial gains, particularly in extreme low-label scenarios. Beyond empirical results, we provide in-depth mechanistic analyses to explain the synergistic roles of GPPT and DAPT. Full article

Printed circuit board (PCB) defect detection is critical to manufacturing quality, yet tiny, low-contrast defects and limited annotations challenge conventional systems. This study develops an ECA–DCN-lite–BiFPN–CARAFE-enhanced YOLOv5 detector by modifying You Only Look Once (YOLO) version 5 (YOLOv5) with Efficient Channel Attention (ECA) for channel re-weighting, a lightweight Deformable Convolution (DCN-lite) for geometric adaptability, a Bi-Directional Feature Pyramid Network (BiFPN) for multi-scale fusion, and Content-Aware ReAssembly of FEatures (CARAFE) for content-aware upsampling. A single-cycle semi-supervised training pipeline is further introduced: a detector trained on labeled images generates high-confidence pseudo-labels for unlabeled data, and the combined set is used for retraining without ratio heuristics. Evaluated on PKU-PCB under label-scarce regimes, the full model improves supervised mean Average Precision at an Intersection-over-Union threshold of 0.5 (mAP@0.5) from 0.870 (baseline) to 0.910, and reaches 0.943 mAP@0.5 with semi-supervision, with consistent class-wise gains and faster convergence. Ablation experiments validate the contribution of each module and identify robust pseudo-label thresholds, while comparisons with recent YOLO variants show favorable accuracy–efficiency trade-offs. These findings indicate that the proposed design delivers accurate, label-efficient PCB inspection suitable for Automated Optical Inspection (AOI) in production environments. This work supports SDG 9 by enhancing intelligent manufacturing systems through reliable, high-precision AI-driven PCB inspection. Full article

In resource-constrained edge agricultural environments, the accurate recognition of toxic weeds poses dual challenges related to model lightweight design and the few-shot generalization capability. To address these challenges, a multi-strategy recognition framework is proposed, which integrates a lightweight backbone network, a pseudo-labeling guidance mechanism, and a contrastive boundary enhancement module. This approach is designed to improve deployment efficiency on low-power devices while ensuring high accuracy in identifying rare toxic weed categories. The proposed model achieves a real-time inference speed of 18.9 FPS on the Jetson Nano platform, with a compact model size of 18.6 MB and power consumption maintained below 5.1 W, demonstrating its efficiency for edge deployment. In standard classification tasks, the model attains 89.64%, 87.91%, 88.76%, and 88.43% in terms of precision, recall, F1-score, and accuracy, respectively, outperforming existing mainstream lightweight models such as ResNet18, MobileNetV2, and MobileViT across all evaluation metrics. In few-shot classification tasks targeting rare toxic weed species, the complete model achieves an accuracy of 80.32%, marking an average improvement of over 13 percentage points compared to ablation variants that exclude pseudo-labeling and self-supervised modules or adopt a CNN-only architecture. The experimental results indicate that the proposed model not only delivers strong overall classification performance but also exhibits superior adaptability for deployment and robustness in low-data regimes, offering an effective solution for the precise identification and ecological control of toxic weeds within intelligent agricultural perception systems. Full article

Precise classification of unsound wheat grains is essential for crop yields and food security, yet most existing approaches rely on vision-only models that demand large labeled datasets, which is often impractical in real-world, data-scarce settings. To address this few-shot challenge, we propose UWGC, a novel vision-language framework designed for few-shot classification of unsound wheat grains. UWGC integrates two core modules: a fine-tuning module based on Adaptive Prior Refinement (APE) and a text prompt enhancement module that incorporates Advancing Textual Prompt (ATPrompt) and the multimodal model Qwen2.5-VL. The synergy between the two modules, leveraging cross-modal semantics, enhances generalization of UWGC in low-data regimes. It is offered in two variants: UWGC-F and UWGC-T, in order to accommodate different practical needs. Across few-shot settings on a public grain dataset, UWGC-F and UWGC-T consistently outperform existing vision-only and vision-language methods, highlighting their potential for unsound wheat grain classification in real-world agriculture. Full article

Winter wheat yield prediction is critical for optimizing field management plans and guiding agricultural production. To address the limitations of conventional manual yield estimation methods, including low efficiency and poor interpretability, this study innovatively proposes an intelligent yield estimation method based on a convolutional neural network (CNN). A comprehensive two-factor (fertilization × irrigation) controlled field experiment was designed to thoroughly validate the applicability and effectiveness of this method. The experimental design comprised two irrigation treatments, sufficient irrigation (C) at 750 m³ ha⁻¹ and deficit irrigation (M) at 450 m³ ha⁻¹, along with five fertilization treatments (at a rate of 180 kg N ha⁻¹): (1) organic fertilizer alone, (2) organic–inorganic fertilizer blend at a 7:3 ratio, (3) organic–inorganic fertilizer blend at a 3:7 ratio, (4) inorganic fertilizer alone, and (5) no fertilizer control. The experimental protocol employed a DJI M300 RTK unmanned aerial vehicle (UAV) equipped with a multispectral sensor to systematically acquire high-resolution growth imagery of winter wheat across critical phenological stages, from heading to maturity. The acquired multispectral imagery was meticulously annotated using the Labelme professional annotation tool to construct a comprehensive experimental dataset comprising over 2000 labeled images. These annotated data were subsequently employed to train an enhanced CNN model based on ResNet50 architecture, which achieved automated generation of panicle density maps and precise panicle counting, thereby realizing yield prediction. Field experimental results demonstrated significant yield variations among fertilization treatments under sufficient irrigation, with the 3:7 organic–inorganic blend achieving the highest actual yield (9363.38 ± 468.17 kg ha⁻¹) significantly outperforming other treatments (p < 0.05), confirming the synergistic effects of optimized nitrogen and water management. The enhanced CNN model exhibited superior performance, with an average accuracy of 89.0–92.1%, representing a 3.0% improvement over YOLOv8. Notably, model accuracy showed significant correlation with yield levels (p < 0.05), suggesting more distinct panicle morphological features in high-yield plots that facilitated model identification. The CNN’s yield predictions demonstrated strong agreement with the measured values, maintaining mean relative errors below 10%. Particularly outstanding performance was observed for the organic fertilizer with full irrigation (5.5% error) and the 7:3 organic-inorganic blend with sufficient irrigation (8.0% error), indicating that the CNN network is more suitable for these management regimes. These findings provide a robust technical foundation for precision farming applications in winter wheat production. Future research will focus on integrating this technology into smart agricultural management systems to enable real-time, data-driven decision making at the farm scale. Full article

Several challenges hinder accurate and physically consistent dynamic parameter estimation in power systems, particularly under scenarios involving limited measurements, strong system nonlinearity, and high variability introduced by renewable integration. Although data-driven methods such as Physics-Informed Neural Networks (PINNs) provide a promising direction, they often suffer from poor generalization and training instability when faced with complex dynamic regimes. To address these challenges, we propose a Residual Physics-Informed Neural Network (Res-PINN) framework, which integrates a residual neural architecture with the swing equation to enhance estimation robustness and precision. By replacing the traditional multilayer perceptron (MLP) in PINN with residual connections and injecting normalized time into each network layer, the proposed model improves temporal awareness and enables stable training of deep networks. A physics-constrained loss formulation is employed to estimate inertia and damping parameters without relying on large-scale labeled datasets. Extensive experiments on a 4-bus, 2-generator power system demonstrate that Res-PINN achieves high parameter estimation accuracy across various dynamic conditions and outperforms traditional PINN and Unscented Kalman Filter (UKF) methods. It also exhibits strong robustness to noise and low sensitivity to hyperparameter variations. These results show the potential of Res-PINN to bridge the gap between physics-guided learning and practical power system modeling and parameter identification. Full article

To address the challenges of label sparsity and feature incompleteness in structured data, a self-supervised representation learning method based on multi-view consistency constraints is proposed in this paper. Robust modeling of high-dimensional sparse tabular data is achieved through integration of a view-disentangled encoder, intra- and cross-view contrastive mechanisms, and a joint loss optimization module. The proposed method incorporates feature clustering-based view partitioning, multi-view consistency alignment, and masked reconstruction mechanisms, thereby enhancing the model’s representational capacity and generalization performance under weak supervision. Across multiple experiments conducted on four types of datasets, including user rating data, platform activity logs, and financial transactions, the proposed approach maintains superior performance even under extreme conditions of up to 40% feature missingness and only 10% label availability. The model achieves an accuracy of 0.87, F1-score of 0.83, and AUC of 0.90 while reducing the normalized mean squared error to 0.066. These results significantly outperform mainstream baseline models such as XGBoost, TabTransformer, and VIME, demonstrating the proposed method’s robustness and broad applicability across diverse real-world tasks. The findings suggest that the proposed method offers an efficient and reliable paradigm for modeling sparse structured data. Full article

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose a Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE), to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress-detection methodologies in terms of precision, recall, and interpretability. The results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on. Full article

The ability to translate Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) into different modalities and data types is essential to improve Deep Learning (DL) for predictive medicine. This work presents DACMVA, a novel framework to conduct data augmentation in a cross-modal dataset by translating between modalities and oversampling imputations of missing data. DACMVA was inspired by previous work on the alignment of latent spaces in Autoencoders. DACMVA is a DL data augmentation pipeline that improves the performance in a downstream prediction task. The unique DACMVA framework leverages a cross-modal loss to improve the imputation quality and employs training strategies to enable regularized latent spaces. Oversampling of augmented data is integrated into the prediction training. It is empirically demonstrated that the new DACMVA framework is effective in the often-neglected scenario of DL training on tabular data with continuous labels. Specifically, DACMVA is applied towards cancer survival prediction on tabular gene expression data where there is a portion of missing data in a given modality. DACMVA significantly (p << 0.001, one-sided Wilcoxon signed-rank test) outperformed the non-augmented baseline and competing augmentation methods with varying percentages of missing data (4%, 90%, 95% missing). As such, DACMVA provides significant performance improvements, even in very-low-data regimes, over existing state-of-the-art methods, including TDImpute and oversampling alone. Full article

The Bayech basin is located in southwestern Tunisia, a highly prone region to flooding risks. The Bayech basin is characterized by wadis that adopt a wide, sometimes ill-defined bed, often intersected by low-lying areas, resulting in a semi-endoreismo, greatly disrupting the flow regimes. The Bayech basin drains the slopes of the Nementchas and Tebessa mountains in Algeria, collecting water from the Medjen Bel Abbes plain in its middle course before crossing the Gafsa djebls chain at the Gafsa gap. In this basin, flooding is generally caused by high-intensity storms and is often relatively limited in extent. The slope shape and soil type can promote rapid surface runoff during intense rainfall. Therefore, the purpose of creating a web application, labeled ClimInonda, is to respond to a critical need of readily available information on climatic, environmental, and land use data collected in this basin and its morphometric characteristics using recent methods. The application consists of three essential components: the front-end, back-end, and database. The front-end focuses on the user interface, allowing users to interact with the application’s features. It communicates with the back-end through Hypertext Transfer Protocol requests for data processing and retrieval. The back-end handles the server-side operations, processes requests, and provides responses by retrieving data from the database. The database stores and manages the application’s data, ensuring integrity and efficient access. This modular architecture ensures a user-friendly interface, seamless data processing, and reliable data storage. Visualizations can include different types of data, such as satellite imagery, weather data, and terrain data, and can be displayed using various techniques, such as heat maps, contour maps, and 3D models, by providing easy-to-understand visualizations. ClimInonda is an application developed to expand upon existing platforms by providing a suite of exploratory data analysis features, including the ability to calculate the total precipitation depth recorded for any period, interpolate the annual recurrence interval for rainfall events, etc. A simple evaluation of the platform was performed to assess the usefulness and user satisfaction of the tool by professional users, and positive feedback was received. There is clear evidence that ClimInonda would provide the necessary basis for informed decision making by stakeholders and development agencies in arid and semi-arid Tunisia. Full article

Robust maritime obstacle detection is critical for safe navigation of autonomous boats and timely collision avoidance. The current state-of-the-art is based on deep segmentation networks trained on large datasets. However, per-pixel ground truth labeling of such datasets is labor-intensive and expensive. We propose a new scaffolding learning regime (SLR) that leverages weak annotations consisting of water edges, the horizon location, and obstacle bounding boxes to train segmentation-based obstacle detection networks, thereby reducing the required ground truth labeling effort by a factor of twenty. SLR trains an initial model from weak annotations and then alternates between re-estimating the segmentation pseudo-labels and improving the network parameters. Experiments show that maritime obstacle segmentation networks trained using SLR on weak annotations not only match but outperform the same networks trained with dense ground truth labels, which is a remarkable result. In addition to the increased accuracy, SLR also increases domain generalization and can be used for domain adaptation with a low manual annotation load. The SLR code and pre-trained models are freely available online. Full article

We present a combination of micromachined optofluidic platforms equipped with a fiber-optic sensing configuration based on a three-path Mach–Zehnder interferometer (MZI) for simultaneous measurement of the refractive index of liquids and the autocalibration in dynamic regime. The sensing principle is based on the low-coherence interferometry, characterized by a generation of Gaussian enveloped interferograms, for which the position of its maximum depends on the optical path difference (OPD) between the sensing and reference arm of the MZI. When liquid flows through the central microchannel of the optofluidic platform it crosses the light beam between the two optical fibers in the sensing arm causing the OPD change. An algorithm has been applied for the calculation of the refractive index of liquids out of the raw interference signals. We obtained a very good agreement between the experimental results and literature data of refractive indices of subjected fluids. The accuracy of refractive index measurement is approximately 1%, predominantly determined by the accuracy of reading the position of the mechanical scanner. The proposed sensor is attractive for the label-free biological, biochemical, and chemical sensing owing autocalibration and high sensitivity yet consuming a very small sample volume of 1 µL. It is capable to measure the refractive index of various liquids and/or gases simultaneously in the process. Full article

Cross-domain fault diagnosis methods have been successfully and widely developed in the past years, which focus on practical industrial scenarios with training and testing data from numerous machinery working regimes. Due to the remarkable effectiveness in such problems, deep learning-based domain adaptation approaches have been attracting increasing attention. However, the existing methods in the literature are generally lower compared to environmental noise and data availability, and it is difficult to achieve promising performance under harsh practical conditions. This paper proposes a new cross-domain fault diagnosis method with enhanced robustness. Noisy labels are introduced to significantly increase the generalization ability of the data-driven model. Promising diagnosis performance can be obtained with strong noise interference in testing, as well as in practical cases with low-quality data. Experiments on two rotating machinery datasets are carried out for validation. The results indicate that the proposed algorithm is well suited to be applied in real industrial environments to achieve promising performance with variations of working conditions. Full article

Automatic catheter and guidewire segmentation plays an important role in robot-assisted interventions that are guided by fluoroscopy. Existing learning based methods addressing the task of segmentation or tracking are often limited by the scarcity of annotated samples and difficulty in data collection. In the case of deep learning based methods, the demand for large amounts of labeled data further impedes successful application. We propose a synthesize and segment approach with plug in possibilities for segmentation to address this. We show that an adversarially learned image-to-image translation network can synthesize catheters in X-ray fluoroscopy enabling data augmentation in order to alleviate a low data regime. To make realistic synthesized images, we train the translation network via a perceptual loss coupled with similarity constraints. Then existing segmentation networks are used to learn accurate localization of catheters in a semi-supervised setting with the generated images. The empirical results on collected medical datasets show the value of our approach with significant improvements over existing translation baseline methods. Full article