Search Results (3,523)

Accurate identification of picking points remains a critical challenge for automated marigold harvesting, primarily due to complex backgrounds and significant pose variations of the flowers. To overcome this challenge, this study proposes SCS-YOLO-Seg, a novel method based on a lightweight segmentation model. The approach enhances the baseline YOLOv8n-seg architecture by replacing its backbone with StarNet and introducing C2f-Star, a novel lightweight feature extraction module. These modifications achieve substantial model compression, significantly reducing the model size, parameter count, and computational complexity (GFLOPs). Segmentation efficiency is further optimized through a dual-path collaborative architecture (Seg-Marigold head). Following mask extraction, picking points are determined by intersecting the optimized elliptical mask fitting results with the stem skeleton. Experimental results demonstrate that SCS-YOLO-Seg effectively balances model compression with segmentation performance. Compared to YOLOv8n-seg, it maintains high accuracy while significantly reducing resource requirements, achieving a picking point identification accuracy of 93.36% with an average inference time of 28.66 ms per image. This work provides a robust and efficient solution for vision systems in automated marigold harvesting. Full article

The transportation sector, as a major source of carbon emissions, plays a crucial role in the realization of dual carbon goals worldwide. In this study, an improved least absolute shrinkage and selection operator (LASSO) is used to identify six key factors affecting transportation carbon emissions (TCEs) in China. Aiming at the spatio-temporal characteristics of transportation carbon emissions, a CNN-BiLSTM neural network model is constructed for the first time for prediction, and an improved whale optimization algorithm (EWOA) is introduced for hyperparameter optimization, finding that the prediction model combining spatio-temporal characteristics has a more significant prediction accuracy, and scenario forecasting was carried out using the prediction model. Research indicates that over the past three decades, TCEs have demonstrated a rapid growth trend. Under the baseline, green, low-carbon, and high-carbon scenarios, peak carbon emissions are expected in 2035, 2031, 2030, and 2040. The adoption of a low-carbon scenario represents the most advantageous pathway for the sustainable progression of China’s transportation sector. Consequently, it is imperative for China to accelerate the formulation and implementation of low-carbon policies, promote the application of clean energy and facilitate the green transformation of the transportation sector. These efforts will contribute to the early realization of dual-carbon goals with a positive impact on global sustainable development. Full article

Fumonisins, primarily produced by Fusarium spp. and Aspergillus section nigri, are common contaminants in maize, cereal grains, and other processed and derived products, representing a significant risk to food safety and public health. This study presents the development and optimisation of a high-performance liquid chromatography method with fluorescence detection (HPLC-FLD) for the quantification of fumonisin B1 (FB1) and B2 (FB2) in various food matrices. In contrast with conventional protocols employing potassium phosphate buffers as the mobile phase, the proposed method utilises formic acid, offering enhanced compatibility with liquid chromatography systems. An automated online precolumn derivatisation with o-phthaldialdehyde (OPA) was optimised through experimental design and response surface methodology, enabling baseline separation of FB1 and FB2 derivatives in less than 20 min. The method demonstrated high sensitivity, with limits of detection of 0.006 µg mL⁻¹ for FB1 and 0.012 µg mL⁻¹ for FB2, and excellent repeatability (intraday RSD values of 0.85% and 0.83%, respectively). Several solid-phase extraction (SPE) strategies were evaluated to enhance sample clean-up using a variety of food samples, including dried figs, raisins, dates, corn, cornmeal, wheat flour, and rice. FumoniStar Inmunoaffinity columns were the only clean-up method that provided optimal recoveries (70–120%) across all tested food matrices. However, the MultiSep™ 211 column yielded good recoveries for both fumonisins in dried figs and raisins. Additionally, the C18 cartridge achieved acceptable recoveries for both fumonisins in dried figs and wheat flour. Full article

Earthquakes, as one of the most destructive natural disasters, often cause significant casualties and severe economic losses. Accurate prediction of earthquake fatalities is of great importance for pre-disaster prevention and mitigation planning, as well as post-disaster emergency response deployment. To address the challenges of small sample sizes, high dimensionality, and strong nonlinearity in earthquake fatality prediction, this paper proposes an integrated modeling approach (PCA-IWOA-XGBoost) combining Principal Component Analysis (PCA), the Improved Whale Optimization Algorithm (IWOA), and Extreme Gradient Boosting (XGBoost). The method first employs PCA to reduce the dimensionality of the influencing factor data, eliminating redundant information and improving modeling efficiency. Subsequently, the IWOA is used to intelligently optimize key hyperparameters of the XGBoost model, enhancing the prediction accuracy and stability. Using 42 major earthquake events in China from 1970 to 2025 as a case study, covering regions including the west (e.g., Tonghai in Yunnan, Wenchuan, Jiuzhaigou), central (e.g., Lushan in Sichuan, Ya’an), east (e.g., Tangshan, Yingkou), north (e.g., Baotou in Inner Mongolia, Helinger), northwest (e.g., Jiashi in Xinjiang, Wushi, Yongdeng in Gansu), and southwest (e.g., Lancang in Yunnan, Lijiang, Ludian), the empirical results showed that the PCA-IWOA-XGBoost model achieved an average test set accuracy of 97.0%, a coefficient of determination (R²) of 0.996, a root mean square error (RMSE) and mean absolute error (MAE) reduced to 4.410 and 3.430, respectively, and a residual prediction deviation (RPD) of 21.090. These results significantly outperformed the baseline XGBoost, PCA-XGBoost, and IWOA-XGBoost models, providing improved technical support for earthquake disaster risk assessment and emergency response. Full article

This study applies a deep neural network (DNN) to optimize the 22.5 m pontoon hull form of a small waterplane area twin hull (SWATH) vessel with fin stabilizers, aiming to reduce calm water resistance at a Froude number of 0.8 under even keel conditions. The vessel’s resistance is simplified into three components: pontoon, strut, and fin stabilizer. Four design parameters define the pontoon geometry: fore-body length, aft-body length, fore-body angle, and aft-body angle. Computational fluid dynamics (CFD) simulations using STAR-CCM+ 2302 provide 1400 resistance data points, including fin stabilizer lift and drag forces at varying angles of attack. These are used to train a DNN in MATLAB 2018a with five hidden layers containing six, eight, nine, eight, and seven neurons. K-fold cross-validation ensures model stability and aids in identifying optimal design parameters. The optimized hull has a 7.8 m fore-body, 6.8 m aft-body, 10$°$ fore-body angle, and 35$°$ aft-body angle. It achieves a 2.2% resistance reduction compared to the baseline. The improvement is mainly due to a reduced Munk moment, which lowers the angle of attack needed by the fin stabilizer, thereby reducing drag. The optimized design provides cost-efficient construction and enhanced payload capacity. This study demonstrates the effectiveness of combining CFD and deep learning for hull form optimization. Full article

Effective management of cascade reservoir systems is essential for balancing hydropower generation, flood control, and ecological sustainability, especially under increasingly uncertain runoff conditions driven by climate change. Traditional optimization methods, while widely used, often struggle with high dimensionality and fail to adequately address inflow variability. This study introduces a novel deep reinforcement learning (DRL) framework that tightly couples probabilistic runoff forecasting with adaptive reservoir scheduling. We integrate a Long Short-Term Memory (LSTM) neural network to model runoff uncertainty and generate probabilistic inflow forecasts, which are then embedded into a Proximal Policy Optimization (PPO) algorithm via Monte Carlo sampling. This unified forecast–optimize architecture allows for dynamic policy adjustment in response to stochastic hydrological conditions. A case study on China’s Xiluodu–Xiangjiaba cascade system demonstrates that the proposed LSTM-PPO framework achieves superior performance compared to traditional baselines, notably improving power output, storage utilization, and spillage reduction. The results highlight the method’s robustness and scalability, suggesting strong potential for supporting resilient water–energy nexus management under complex environmental uncertainty. Full article

Cucumber, a high-yielding crop commonly grown in facility environments, is particularly susceptible to nitrogen (N) deficiency due to its rapid growth and high nutrient demand. This study used cucumber as its experimental subject and established a spectral dataset of leaves under four nutritional conditions, normal supply, nitrogen deficiency, phosphorus deficiency, and potassium deficiency, aiming to develop an efficient and robust method for quantifying N in cucumber leaves using Raman spectroscopy (RS). Spectral data were preprocessed using three baseline correction methods—BaselineWavelet (BW), Iteratively Improve the Moving Average (IIMA), and Iterative Polynomial Fitting (IPF)—and key spectral variables were selected using 4-Dimensional Feature Extraction (4DFE) and Competitive Adaptive Reweighted Sampling (CARS). These selected features were then used to develop a N content prediction model based on Partial Least Squares Regression (PLSR). The results indicated that baseline correction significantly enhanced model performance, with three methods outperforming unprocessed spectra. A further analysis showed that the combination of IPF, 4DFE, and CARS achieved optimal PLSR model performance, achieving determination coefficients (R²) of 0.947 and 0.847 for the calibration and prediction sets, respectively. The corresponding root mean square errors (RMSEC and RMSEP) were 0.250 and 0.368, while the residual predictive deviation (RPDC and RPDP) values reached 4.335 and 2.555. These findings confirm the feasibility of integrating RS with advanced data processing for rapid, non-destructive nitrogen assessment in cucumber leaves, offering a valuable tool for nutrient monitoring in precision agriculture. Full article

Automated quality control plays a critical role in modern industries, particularly in environments that handle large volumes of packaged products requiring fast, accurate, and consistent inspections. This work presents an anomaly detection system for candle jars commonly used in industrial and commercial applications, where obtaining labeled defective samples is challenging. Two anomaly detection strategies are explored: (1) a baseline model using convolutional neural networks (CNNs) as an end-to-end classifier and (2) a hybrid approach where features extracted by CNNs are fed into One-Class classification (OCC) algorithms, including One-Class SVM (OCSVM), One-Class Isolation Forest (OCIF), One-Class Local Outlier Factor (OCLOF), One-Class Elliptic Envelope (OCEE), One-Class Autoencoder (OCAutoencoder), and Support Vector Data Description (SVDD). Both strategies are trained primarily on non-defective samples, with only a limited number of anomalous examples used for evaluation. Experimental results show that both the pure CNN model and the hybrid methods achieve excellent classification performance. The end-to-end CNN reached 100% accuracy, precision, recall, F1-score, and AUC. The best-performing hybrid model CNN-based feature extraction followed by OCIF also achieved 100% across all evaluation metrics, confirming the effectiveness and robustness of the proposed approach. Other OCC algorithms consistently delivered strong results, with all metrics above 95%, indicating solid generalization from predominantly normal data. This approach demonstrates strong potential for quality inspection tasks in scenarios with scarce defective data. Its ability to generalize effectively from mostly normal samples makes it a practical and valuable solution for real-world industrial inspection systems. Future work will focus on optimizing real-time inference and exploring advanced feature extraction techniques to further enhance detection performance. Full article

The aim of the present observational study was to evaluate the early effect of free-form essential amino acid (EAA) supplementation on cardiac and muscular performance in elderly patients with chronic heart failure (HF) with reduced ejection fraction (HFrEF) and sarcopenia, as add-on to the optimized medical therapy (OMT) for HF. The present study included 60 elderly Caucasian patients suffering from HFrEF and sarcopenia. At the baseline and at follow-up, all patients underwent complete physical examination with the determination of the main anthropometric and hemodynamic parameters. After 6 months of supplementation with EAAs, we observed significant improvements in the parameters of sarcopenia. In addition, there was a significant improvement in glycol-metabolic parameters, and in inflammatory index as high sensitivity C-reactive protein (hs-CRP). In accordance with these results, significant decreases were observed in circulating levels of oxidative stress biomarkers Nox-2 (p < 0.001) and 8-Isoprostane (p < 0.001), and platelet aggregation biomarkers such as sP-Selectin (p < 0.001) and Gp-VI (p < 0.001). Of particular interest, after 6 months’ follow-up, there was a significant improvement in LVEF and global longitudinal strain (GLS). In conclusion, this study demonstrates that targeted nutritional intervention with EEAAs represents a viable therapeutic strategy for addressing the complex interplay between cardiac dysfunction and skeletal muscle wasting in elderly HF patients. Full article

The efficiency of electric motors is highly dependent on their operating temperature, with lower temperatures contributing to enhanced performance, reliability, and extended service life. This study presents a comprehensive review of state-of-the-art cooling technologies and evaluates their impact on the thermal behavior of a commercial motor–generator system in high-demand applications. A baseline model of a permanent magnet synchronous motor (PMSM) was developed using MotorCAD 2023^® software, which was supported by reverse engineering techniques to accurately replicate the motor’s physical and thermal characteristics. Subsequently, multiple cooling strategies were simulated under consistent operating conditions to assess their effectiveness. These strategies include conventional axial water jackets as well as advanced oil-based methods such as shaft cooling and direct oil spray to the windings. The integration of these systems in hybrid configurations was also explored to maximize thermal efficiency. Simulation results reveal that hybrid cooling significantly reduces the temperature of critical components such as stator windings and permanent magnets. This reduction in thermal stress improves current efficiency, power output, and torque capacity, enabling reliable motor operation across a broader range of speeds and under sustained high-load conditions. The findings highlight the effectiveness of hybrid cooling systems in optimizing both thermal management and operational performance of electric machines. Full article

The exponential growth of autonomous systems demands robust security mechanisms that can operate within the extreme constraints of real-time embedded environments. This paper introduces SMART DShot, a groundbreaking machine learning-enhanced framework that transforms the security landscape of unmanned aerial vehicle motor control systems through seamless integration of adaptive timing correction and real-time anomaly detection within Digital Shot (DShot) communication protocols. Our approach addresses critical vulnerabilities in Electronic Speed Controller (ESC) interfaces by deploying four synergistic algorithms—Kalman Filter Timing Correction (KFTC), Recursive Least Squares Timing Correction (RLSTC), Fuzzy Logic Timing Correction (FLTC), and Hybrid Adaptive Timing Correction (HATC)—each optimized for specific error characteristics and attack scenarios. Through comprehensive evaluation encompassing 32,000 Monte Carlo test iterations (500 per scenario × 16 scenarios × 4 algorithms) across 16 distinct operational scenarios and PolarFire SoC Field-Programmable Gate Array (FPGA) implementation, we demonstrate exceptional performance with 88.3% attack detection rate, only 2.3% false positive incidence, and substantial vulnerability mitigation reducing Common Vulnerability Scoring System (CVSS) severity from High (7.3) to Low (3.1). Hardware validation on PolarFire SoC confirms practical viability with minimal resource overhead (2.16% Look-Up Table utilization, 16.57 mW per channel) and deterministic sub-10 microsecond execution latency. The Hybrid Adaptive Timing Correction algorithm achieves 31.01% success rate (95% CI: [30.2%, 31.8%]), representing a 26.5% improvement over baseline approaches through intelligent meta-learning-based algorithm selection. Statistical validation using Analysis of Variance confirms significant performance differences (F(3,1996) = 30.30, p < 0.001) with large effect sizes (Cohen’s d up to 4.57), where 64.6% of algorithm comparisons showed large practical significance. SMART DShot establishes a paradigmatic shift from reactive to proactive embedded security, demonstrating that sophisticated artificial intelligence can operate effectively within microsecond-scale real-time constraints while providing comprehensive protection against timing manipulation, de-synchronization, burst interference, replay attacks, coordinated multi-channel attacks, and firmware-level compromises. This work provides essential foundations for trustworthy autonomous systems across critical domains including aerospace, automotive, industrial automation, and cyber–physical infrastructure. These results conclusively demonstrate that ML-enhanced motor control systems can achieve both superior security (88.3% attack detection rate with 2.3% false positives) and operational performance (31.01% timing correction success rate, 26.5% improvement over baseline) simultaneously, establishing SMART DShot as a practical, deployable solution for next-generation autonomous systems. Full article

Autonomous navigation in dynamic, multi-vessel maritime environments presents a formidable challenge, demanding strict adherence to the International Regulations for Preventing Collisions at Sea (COLREGs). Conventional approaches often struggle with the dual imperatives of global path optimality and local reactive safety, and they frequently rely on simplistic state representations that fail to capture complex spatio-temporal interactions among vessels. We introduce a novel hybrid reinforcement learning framework, D* Lite + Transformer-Enhanced Soft Actor-Critic (TE-SAC), to overcome these limitations. This hierarchical framework synergizes the strengths of global and local planning. An enhanced D* Lite algorithm generates efficient, long-horizon reference paths at the global level. At the local level, the TE-SAC agent performs COLREGs-compliant tactical maneuvering. The core innovation resides in TE-SAC’s synergistic state encoder, which uniquely combines a Graph Neural Network (GNN) to model the instantaneous spatial topology of vessel encounters with a Transformer encoder to capture long-range temporal dependencies and infer vessel intent. Comprehensive simulations demonstrate the framework’s superior performance, validating the strengths of both planning layers. At the local level, our TE-SAC agent exhibits remarkable tactical intelligence, achieving an exceptional 98.7% COLREGs compliance rate and reducing energy consumption by 15–20% through smoother, more decisive maneuvers. This high-quality local control, guided by the efficient global paths from the enhanced D* Lite algorithm, culminates in a 10–32 percentage point improvement in overall task success rates compared to state-of-the-art baselines. This work presents a robust, verifiable, and efficient framework. By demonstrating superior performance and compliance with rules in high-fidelity simulations, it lays a crucial foundation for advancing the practical application of intelligent autonomous navigation systems. Full article

Background and Aim: Type 2 diabetes (T2D) continues to pose a significant public health challenge worldwide. Among therapeutic options, glucagon-like peptide-1 receptor agonists (GLP-1 RAs) have proven effective in optimizing glycemic control and improving cardiometabolic profiles. Semaglutide, now available in an oral formulation, represents a modern strategy to improve patient adherence while supporting glucose and weight regulation. This study primarily investigated the effects of oral semaglutide on key metabolic indicators and secondary endpoints included cardiovascular risk markers (blood pressure and lipid profile) and patient-reported quality of life (QoL). Study Design and Methods: A longitudinal, prospective observational study was conducted involving patients with T2D across two Italian healthcare facilities. Participants were assessed at baseline (T0) and at three subsequent intervals—6 months (T1), 12 months (T2), and 18 months (T3)—following the initiation of oral semaglutide use. Key Findings: Out of 116 participants enrolled, 97 had complete and analyzable data. Across the 18-month follow-up, significant improvements were observed in glycemic parameters, with a notable reduction in HbA1c levels (T0 vs. T3, p = 0.0028; p ≤ 0.05, statistically significant). Self-reported outcomes showed enhanced quality of life, especially in treatment satisfaction and perceived flexibility (T0 vs. T3, p < 0.001). Conclusions: Daily administration of 14 mg oral semaglutide in individuals with T2D resulted in substantial benefits in glycemic regulation, weight reduction, cardiovascular risk management, and overall patient satisfaction. These findings reinforce its potential role as a sustainable and effective option in long-term diabetes care from both a clinical and public health perspective. Full article

As large language models (LLMs) increasingly enter specialized domains, inference without external resources often leads to knowledge gaps, opaque reasoning, and hallucinations. To address these challenges in power equipment defect grading, we propose a zero-shot question-answering framework that requires no task-specific examples. Our system performs two-stage retrieval—first using a Sentence-BERT model fine-tuned on power equipment maintenance texts for coarse filtering, then combining TF-IDF and semantic re-ranking for fine-grained selection of the most relevant knowledge snippets. We embed both the user query and the retrieved evidence into a Chain-of-Thought (CoT) prompt, guiding the pre-trained LLM through multi-step reasoning with self-validation and without any model fine-tuning. Experimental results show that on a held-out test set of 218 inspection records, our method achieves a grading accuracy of 54.2%, which is 6.0 percentage points higher than the fine-tuned BERT baseline at 48.2%; an Explanation Coherence Score (ECS) of 4.2 compared to 3.1 for the baseline; a mean retrieval latency of 28.3 ms; and an average LLM inference time of 5.46 s. Ablation and sensitivity analyses demonstrate that a fine-stage retrieval pool size of k = 30 offers the optimal trade-off between accuracy and latency; human expert evaluation by six senior engineers yields average Usefulness and Trustworthiness scores of 4.1 and 4.3, respectively. Case studies across representative defect scenarios further highlight the system’s robust zero-shot performance. Full article

Knowledge tracing (KT), a core educational data mining task, models students’ evolving knowledge states to predict future learning. In online education systems, the exercises are numerous, but they are typically associated with only a few concepts. However, existing models rarely integrate exercise information with high-order exercise–concept correlations, focusing solely on optimizing models’ final predictive performance. To address these limitations, we propose the Hypergraph-Driven High-Order Knowledge Tracing with a Dual-Gated Dynamic Mechanism (HGKT), a novel framework that (1) captures correlations between exercises and concepts through a two-layer hypergraph convolution; (2) integrates hypergraph-driven exercise embedding and temporal features (answer time and interval time) to characterize learning behavioral dynamics; and (3) designs a learning layer and a forgetting layer, with the dual-gating mechanism dynamically balancing their impacts on the knowledge state. Experiments on three public datasets demonstrate that the proposed HGKT model achieves superior predictive performance compared to all baselines. On the longest interaction sequence dataset, ASSISChall, HGKT improves prediction AUC by least 1.8%. On the biggest interaction records dataset, EdNet-KT1, it maintains a state-of-the-art AUC of 0.78372. Visualization analyses confirm its interpretability in tracing knowledge state evolution. These results validate HGKT’s effectiveness in modeling high-order exercise–concept correlations while ensuring practical adaptability in real-world online education platforms. Full article