Search Results (402)

Object detection in unmanned aerial vehicle (UAV) imagery remains a crucial yet challenging task due to complex backgrounds, large scale variations, and the prevalence of small objects. Visible-spectrum images lack robustness under all-weather and all-illumination conditions; by contrast, multispectral sensing provides complementary cues (e.g., thermal signatures) that improve detection robustness. However, existing multispectral solutions often incur high computational costs and are therefore difficult to deploy on resource-constrained UAV platforms. To address these issues, SG-YOLO is proposed, a lightweight and efficient multispectral object detection framework that aims to balance accuracy and efficiency. First, a Spectral Gated Downsampling Stem (SGDS) is designed, in which grouped convolutions and a gating mechanism are employed at the early stage of the network to extract band-specific features, thereby maximizing spectral complementarity while minimizing redundancy. Second, a Spectral–Spatial Iterative Attention Fusion (SSIAF) module is introduced, in which spectral-wise (channel) attention and spatial-wise attention are iteratively coupled and cascaded in a multi-scale manner to jointly model cross-band dependencies and spatial saliency, thereby aggregating high-level semantic information while suppressing redundant spectral responses. Finally, a Spatial–Channel Synergistic Fusion (SCSF) module is designed to enhance multi-scale and cross-channel feature integration in the neck. Experiments on the MODA dataset show that SG-YOLOs achieves 72.4% mAP₅₀, outperforming the baseline by 3.2%. Moreover, compared with a range of mainstream one-stage detectors and multispectral detection methods, SG-YOLO delivers the best overall performance, providing an effective solution for UAV object detection while maintaining a favorable trade-off between model size and detection accuracy. Full article

Smart sensors are increasingly used in agriculture to monitor environmental conditions and support data-driven decision-making. However, traditional sensor implementations face critical challenges related to power consumption, especially in remote farms—such as pitaya plantations—where access to electricity and ongoing maintenance is limited. This paper presents a smart energy management system for agricultural sensor nodes integrating a machine learning model for adaptive sampling and a batching strategy to optimize energy usage. A lightweight Stochastic Gradient Descent (SGD) regressor trained on temperature dynamics runs on-device to predict the sampling interval ($T_s$). In parallel, the node adjusts the number of buffered samples as the battery state of charge ($SOC$) decreases, reducing Long Range (LoRa) transmissions. Field experiments show that the proposed approach reduces energy consumption by 77.8% compared with fixed-interval sampling, while maintaining good temperature fidelity with Mean Absolute Error (MAE) of 0.537 °C for temperature reconstruction. Full article

Side-scan sonar is essential to underwater target detection, yet its effectiveness is hindered by scarce annotated data and complex acoustic artifacts. This study systematically evaluates four YOLO variants, YOLOv8n, YOLOv10n, YOLOv11n, and the newly released YOLOv13n, on two public side-scan sonar datasets with limited samples and severe class imbalance. We assess detection accuracy, computational efficiency, inference speed, and transfer learning using COCO pre-trained weights, as well as the impact of optimizer choice between SGD and AdamW. The results reveal distinct strengths: YOLOv8n achieves the fastest inference at 60.98 FPS, with a competitive mAP50 of 0.906, ideal for real-time applications. YOLOv11n offers the best accuracy–efficiency balance, attaining the highest recall of 0.859 and mAP50 of 0.917. YOLOv13n demonstrates exceptional precision of 0.993 and high-IoU localization, with an mAP75 of 0.760. Transfer learning consistently boosts performance, with average mAP50:95 gains exceeding 54% on the more challenging dataset, highlighting its critical role in overcoming data scarcity. SGD generally outperforms AdamW, confirming its suitability as the default optimizer. These findings provide practical guidelines: YOLOv8 for real-time needs, YOLOv11 for balanced performance, and YOLOv13 for precision-critical tasks with ample resources. This work also establishes a benchmark for future underwater autonomous system research. Full article

Accurate and real-time weld seam recognition is critical for automated welding systems in intelligent manufacturing. However, existing deep learning-based models often suffer from high computational complexity and limited real-time performance, which restrict their deployment in embedded and industrial environments. To address these challenges, this paper proposes a lightweight weld seam segmentation framework based on an optimized SGD-YOLO (Segmentation-guided Ghost Dynamic YOLO) architecture, aiming to achieve a favorable balance between accuracy and efficiency. By redesigning the network structure and enhancing feature extraction capability, the proposed model significantly reduces computational cost while maintaining high detection precision. Experiments demonstrate that the proposed method achieves a 36.5% reduction in floating-point operations and a 29.4% decrease in parameter size compared with conventional models, enabling stable real-time performance under industrial conditions. Furthermore, feature point extraction experiments show that the pixel localization error is controlled within 5 pixels and the mean depth error remains below 0.5 mm, indicating high robustness and measurement accuracy. These results confirm the effectiveness of the proposed framework in precise weld seam perception and geometric feature extraction. Overall, the proposed lightweight weld seam segmentation approach provides a practical and efficient solution for real-time welding automation, promoting the broader application of deep learning techniques in intelligent manufacturing and industrial robotics. Full article

The oxidative stability of meat products is a crucial factor determining quality, shelf life, and consumer acceptance, as lipid and protein oxidation promote undesirable changes in sensory attributes and nutritional content. Antioxidant capacity (AOC) assays such as total phenolic content (TPC), ferric reducing antioxidant power (FRAP), 2,2′-azino-bis(3-ethylbenzothiazoline-6-sulfonic acid) (ABTS^•+), and 2,2-diphenyl-1-picrylhydrazyl (DPPH^•) are commonly applied in meat systems to assess the AOC associated with both intrinsic muscle components (endogenous) and the protective effects of natural ingredients (exogenous added compounds), i.e., antioxidants. Although differences in analytical methodologies limit direct comparisons among studies, it has been demonstrated that meat products inherently contain compounds that modulate oxidative reactions, with their effectiveness influenced by meat type, processing, and storage conditions. Within this framework, natural ingredients, including plant- and fungal-derived ingredients and their by-products, have gained attention as sources of natural antioxidants, whose capacity depends on the extraction method, the solvent used, and their behavior during gastrointestinal digestion, as evaluated using simulated gastrointestinal digestion (sGD) models. Numerous studies have shown that incorporating natural extracts or powders into meat products enhances AOC during refrigerated storage, with the effect generally depending on the concentration used. Moreover, several natural antioxidant treatments maintain or even enhance their AOC when assessed under sGD conditions. Full article

Peach tree (Prunus persica L. Batsch) is a fruit species of great economic importance worldwide. Thousands of chemical leaf analyses are performed on a yearly basis to support decision-making about fertilizer application. However, traditional methods to determine nutrient content in plant tissue require a mix of strong acids, besides being time-consuming and generating polluting waste. Visible (Vis) and near-infrared (NIR) spectroscopy combined with multivariate techniques emerges as a potential solution to overcome limitations of traditional chemical analyses. The aim of the present study is to combine Vis-NIR spectral data and multivariate techniques to test strategies for the development of models to estimate nutrient content in peach leaves. The study estimated N, P, K, Ca, Mg, S, B, Cu, Fe, Mn, and Zn content in the leaves of peach trees grown in two locations, namely: Pelotas and Pinto Bandeira, in Southern Brazil. Therefore, local and regional scale prediction models were developed by combining preprocessed Vis-NIR spectral data to both Savitzky–Golay first-derivative (SGD1d) and partial least squares regression (PLSR) multivariate technique. Most of the proposed prediction models showed average accuracy (R² ≥ 0.50 and <0.75, RPIQ ≥ 1.9 and <3.0). The local-1 ‘PB’ model showed higher nutrient prediction accuracy than the regional ‘PB + Pelotas’ model and the local-2 ‘Pelotas’ model. Estimates on nutrient content in peach tree leaves subjected to local, local-1 ‘PB’ and local-2 ‘Pelotas’ models fed with data collected in the same site showed better performance than calculations based on data from other sites and/or regions. Finally, the current study allowed making updates in the refinement of more sustainable techniques to set nutrient content. Full article

Unconfined coastal karst aquifers are highly susceptible to contamination from anthropogenic activities, particularly in regions lacking adequate wastewater treatment. Their open hydrological structure facilitates the input and dispersion of contaminants from both point and non-point sources. Furthermore, groundwater exerts a significant influence on coastal water quality through submarine discharge that could impact vulnerable ecosystems like seagrasses, mangroves, and coral reefs. Seasonal hydrological variability—especially between dry and rainy periods—affects contaminant transport, with increased groundwater flux potentially enhancing spatial dispersion. Additionally, the balance between the contributions from the coastal karst aquifer and the hydrodynamics of the coastal zone determines the extent and degree of salinization occurring at the interface between these two systems, which in turn influences aquifer water quality. This study presents a five-year dataset of metal and nutrient concentrations measured during dry and rainy seasons in surface waters (0.5 m depth) from 24 cenotes within the Ring of Cenotes (RC), Yucatán Peninsula, Mexico. The RC functions as a preferential groundwater flow path from inland to the coast via underwater conduits and submarine groundwater discharge (SGD), transporting contaminants present in groundwater into highly vulnerable coastal ecosystems. While most parameters remained below regulatory thresholds, concentrations of total Al, Cr, Pb, and N-NH₃ exceeded limits established by NOM-127-SSA1-2021 at several sites measured within the RC. Spatial heterogeneity was observed across seasons and years, driven by groundwater flux dynamics, land use, and individual sinkhole characteristics. Notably, N-NH₃ concentrations were higher during the dry season, particularly near agricultural and peri-urban zones. These findings underscore the need for mandatory wastewater treatment and integrated coastal karstic aquifer management to protect the region’s sole freshwater resource and the vulnerable ecosystems in the coastal area. Full article

To address the one-class collaborative filtering (OCCF) issue in e-commerce recommendation with only positive implicit feedback, mainstream methods adopt pairwise preference learning represented by Bayesian Personalized Ranking (BPR). However, BPR relies on an invalid assumption and suffers from severe data sparsity. This paper proposes Multi-pairwise Ranking with Heterogeneous Implicit Feedback (MPIF), which exploits heterogeneous implicit and auxiliary information to mine deep user preferences, constructs six pairwise preferences for classified items, and optimizes the model via stochastic gradient descent (SGD). Experiments on three real-world datasets verify that MPIF+ outperforms all state-of-the-art baselines on Normalized Discounted Cumulative Gain at rank 5 (NDCG@5), Precision at rank 5 (Pre@5), Recall at rank 5 (Rec@5), and Area Under Curve (AUC). It yields maximum improvements of 34.2%, 5.5%, and 32.9% on NDCG@5 for the Sobazaar, Retailrocket, and REES46 datasets, respectively, achieving significant and stable recommendation gains. Full article

Accurate and early detection of bone cancer is critical for improving patient outcomes, yet conventional radiographic interpretation remains limited by subjectivity and variability. Conventional AI models often struggle with complex multi-modal noise distributions, non-convex and topologically entangled latent manifolds, extreme class imbalance in rare oncological conditions, and heterogeneous data fusion constraints. To address these challenges, we present a Quantum-Inspired Classical Convolutional Neural Network (QC-CNN) inspired by quantum analogies for automated bone cancer detection in radiographic images. The proposed architecture integrates classical convolutional layers for hierarchical feature extraction with a classical variational layer motivated by high-dimensional Hilbert space analogies for enhanced pattern discrimination. A curated and annotated dataset of bone X-ray images was utilized, partitioned into training, validation, and independent test cohorts. The QC-CNN was optimized using stochastic gradient descent (SGD) with adaptive learning rate scheduling, and regularization strategies were applied to mitigate overfitting. Quantitative evaluation demonstrated superior diagnostic performance, achieving high accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Results highlight the ability of classical CNN with quantum-inspired design to capture non-linear correlations and subtle radiographic biomarkers that classical CNNs may overlook. This study establishes QC-CNN as a promising framework for quantum-analogy motivated medical image analysis, providing evidence of its utility in oncology and underscoring its potential for translation into clinical decision-support systems for early bone cancer diagnosis. All computations in the present study are performed using classical algorithms, with quantum-inspired concepts serving as a conceptual framework for model design and motivating future extensions. Full article

Medical image segmentation, particularly for pathological diagnosis, faces challenges in leveraging patient clinical metadata that could enhance diagnostic accuracy. This study presents MMY-Net (Multimodal Y-shaped Network), a novel deep learning framework that effectively fuses patient metadata with pathological images for improved tumor segmentation performance. The proposed architecture incorporates a Text Processing Block (TPB) utilizing BERT for metadata feature extraction and a Text Encoding Block (TEB) for multi-scale fusion of textual and visual information. The network employs an Interlaced Sparse Self-Attention (ISSA) mechanism to capture both local and global dependencies while maintaining computational efficiency. Experiments were conducted on two open/public eyelid tumor datasets (Dataset 1: 112 WSIs for training/validation; Dataset 2: 107 WSIs as an independent test set) and the public Dataset 3 gland segmentation benchmark. For Dataset 1, 7989 H&E-stained patches (1024 × 1024, resized to 224 × 224) were extracted and split 7:2:1 (train:val:test); Dataset 2 was used exclusively for external validation. All images underwent Vahadane stain normalization. Training employed SGD (lr = 0.001), 1000 epochs, and a hybrid loss (cross-entropy + MS-SSIM + Lovász). Results show that integrating metadata—such as age and gender—significantly improves segmentation accuracy, even when metadata does not directly describe tumor characteristics. Ablation studies confirm the superiority of the proposed text feature extraction and fusion strategy. MMY-Net achieves state-of-the-art performance across all datasets, establishing a generalizable framework for multimodal medical image analysis. Full article

This paper introduces AdamN, a nested-momentum adaptive optimizer that replaces the single Exponential Moving Average (EMA) numerator in Adam/AdamW with a compounded EMA of gradients plus an EMA of that EMA, paired with an exact double-EMA bias correction. This yields a smoother, curvature-aware search direction at essentially first-order cost, with longer, more faithful gradient-history memory and a stable, warmup-free start. Under comparable wall-clock time per epoch, AdamN matches AdamW’s final accuracy on ResNet-18/CIFAR-100, while reaching 80% and 90% training-accuracy milestones ~127 s and ~165 s earlier, respectively. On pre-benchmarking workloads (toy problems and CIFAR-10), AdamN shows the same pattern: faster early-phase convergence with similar or slightly better final accuracy. On language modeling with token-frequency imbalance—Wikitext-2-style data with training-only token corruption and a 10% low-resource variant—AdamN lowers rare-token perplexity versus AdamW without warmup while matching head and mid-frequency performance. In full fine-tuning of Llama 3.1–8B on a small dataset, AdamN reaches AdamW’s final perplexity in roughly half the steps (≈$2.25\times$ faster time-to-quality). Finally, on a ViT-Base/16 transferred to CIFAR-100 (batch size 256), AdamN achieves 88.8% test accuracy vs. 84.2% for AdamW and reaches 40–80% validation-accuracy milestones in the first epoch (AdamW reaches 80% by epoch 59), reducing epochs, energy use, and cost. Full article

Power-line presence recognition technology for unmanned aerial vehicles (UAVs) is one of the key research directions in the field of UAV remote sensing. With the rapid development of UAV technology, the application of UAVs in various fields has become increasingly widespread. However, when flying in urban and rural areas, UAVs often face the danger of obstacles such as power lines, posing challenges to flight safety and stability. To address this issue, this study proposes a novel method for presence recognition in UAVs for power lines using an improved GhostNet v2 knowledge distillation dual-attention mechanism convolutional neural network. The construction of a real-time UAV power-line presence recognition system involves three aspects: dataset acquisition, a novel network model, and real-time presence recognition. First, by cleaning, enhancing, and segmenting the power-line data collected by UAVs, a UAV power-line presence recognition image dataset is obtained. Second, through comparative experiments with multi-attention modules, the dual-attention mechanism is selected to construct the CNN, and the UAV real-time power-line presence recognition training is conducted using the SGD optimiser and Hard-Swish activation function. Finally, knowledge distillation is employed to transfer the knowledge from the dual-attention mechanism-based CNN to the nonlinear function and Mamba-enhanced GhostNet v2 network, thereby reducing the model’s parameter count and achieving real-time recognition performance suitable for mobile device deployment. Experiments demonstrate that the UAV-based real-time power-line presence recognition method proposed in this paper achieves real-time recognition accuracy rates of over 91.4% across all regions, providing a technical foundation for advancing the development and progress of UAV-based real-time power-line presence recognition. Full article

Traditional chemical analysis of plant tissue is time-consuming, costly, and poses risks due to exposure to toxic gases, highlighting the need for faster, low-cost, and safer alternatives. Vis-NIR spectroscopy, combined with machine learning, offers a promising method for estimating leaf nutrient levels without chemical reagents. This study evaluated the potential of Vis-NIR spectroscopy for nutrient estimation in leaf samples of banana (n = 363), mango (n = 239), and grapevine (n = 336) by applying spectral pre-processing techniques—smoothing (SMO) and first derivative Savitzky–Golay (SGD1d) alongside two machine learning methods: Partial Least Squares Regression (PLSR) and Random Forest (RF). Plant tissue samples were analyzed using sulfuric and nitroperchloric wet digestion and hyperspectral sensors. The prediction models were assessed using concordance correlation coefficient (CCC) and mean squared error (MSE). The highest accuracy (CCC > 0.80 and MSE < 2 g kg⁻¹) was achieved for Ca in banana, P in mango, and N and Ca in grapevine across both machine learning methods and pre-processing techniques. The predictive models calibrated for ‘Grapevine’ exhibited the highest accuracy—characterized by higher CCC values and lower MSE values—when compared with the models developed for ‘Mango’ and ‘Banana’. Models using SMO and SGD1d showed better performance than those using raw spectra (RAW). The high amplitudes and variations in nutrient levels, combined with large standard deviations, negatively affected the predictive performance of the models. Full article

This study examines the rapid growth of energy demand in Paraguay, primarily driven by intensive air conditioning use and reduced hydroelectric output due to adverse Paraná River conditions. Employing a Vector Autoregressive (VAR) model, we quantify how temperature shocks significantly elevate peak electricity demand within the National Interconnected System. Our findings reveal that air conditioning accounts for 34–36% of the peak demand, pushing the hydroelectric system towards its operational limits. To address this challenge, we propose a technological transition strategy focused on energy efficiency improvements and labeling programs aimed at reducing peak demand, delaying system saturation, and achieving substantial power savings. These measures offer a practical approach to climate adaptation while supporting Paraguay’s international commitments and Sustainable Development Goals (SGDs) 7 (affordable and clean energy) and 13 (climate action). This work represents the first pioneering effort in Paraguay to quantify the influence of the SIN’s AC at the national level. This research provides policymakers with an evidence-based framework for energy planning, marking a pioneering effort in Paraguay to quantify cooling loads and set actionable efficiency targets. Full article

Security requirements play a critical role in ensuring the trustworthiness and resilience of software systems; however, their automatic classification remains challenging due to limited labeled data, confidentiality constraints, and the heterogeneous nature of requirements across organizations. Existing approaches typically assume centralized access to training data and rely on costly manual annotation, making them unsuitable for distributed industrial settings. To address these challenges, we propose SeqFAL, a communication-efficient and privacy-preserving Federated Active Learning framework for natural language–based security requirements classification. SeqFAL integrates frozen pre-trained sentence embeddings, margin-based active learning, and lightweight federated aggregation of linear classifiers, enabling collaborative model training without sharing raw requirement text. We evaluate SeqFAL on a combined dataset of SeqReq dataset and the PROMISE-NFR dataset under varying federation sizes, query budgets, and communication rounds, and compare it against three baselines: centralized learning, active learning without federated aggregation, and federated learning without active querying. In addition to the proposed margin-based sampling strategy, we investigate alternative query strategies, including least-confidence and random sampling, as well as multiple linear classifiers such as LinearSVC and SGD-based classifiers with logistic and hinge losses. Results show that SeqFAL consistently outperforms FL-only and achieves performance comparable to AL-only centralized baselines, while approaching the optimal upper bound using significantly fewer labeled samples. These findings demonstrate that the joint integration of federated learning and active learning provides an effective and privacy-preserving strategy for security requirements classification in distributed software engineering environments. Full article