Search Results (5,115)

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

West Nile virus (WNV) is a mosquito-borne flavivirus of growing importance for both human and equine health in Europe. Horses are highly susceptible to neurological disease and, because they share ecological exposure with humans, they represent valuable sentinels for detecting local viral circulation within a One Health framework. However, diagnosis of WNV infection in equines is complicated by the short and low-level viraemia, which limits the sensitivity of molecular assays, and by serological cross-reactivity with related flaviviruses and the confounding effects of vaccination. In this narrative review, we summarise the current diagnostic tools for WNV in horses, including direct detection methods (RT-qPCR, virus isolation, antigen detection) and indirect serological approaches (IgM and IgG ELISA, virus neutralisation tests), and discuss their practical performance and constraints in clinical and surveillance settings. We further examine equine surveillance systems, passive clinical reporting, active serosurveys and sentinel cohorts, and their integration with vector, avian and environmental monitoring. Key challenges include methodological heterogeneity, limited access to confirmatory testing and variable cross-sector data sharing. Finally, we outline future directions, highlighting the need for harmonised laboratory protocols, innovative field-deployable diagnostics, genomic surveillance and integrated, multi-source monitoring systems to strengthen early warning capacity and improve preparedness for WNV outbreaks in equine populations. Full article

Sustainable groundwater management is essential for water security and human health protection. Fluoride contamination is a serious concern for the sustainable drinking water supply in many parts of Pakistan, including Balochistan, where arid climate conditions and geological formations support the enrichment of fluoride. The toxic nature of fluoride contamination has resulted in negative health impacts on the local population. Conventional geostatistical techniques are usually ineffective to delineate the nonlinear relationships that affect the distribution of fluoride. This study aims to develop a machine learning-driven spatial modelling framework for classifying the spatial distribution of fluoride contamination in groundwater across the study area. The model will help to understand the spatial variability of fluoride contamination and its controlling factors, essential for effective mitigation and early warning systems. Physiochemical elements were used as predictive features in this study, utilizing a unified feature importance framework combining hydrogeochemical analysis, spatial distribution assessment, and ensemble SHAP-based interpretation to identify consistent predictors. Model performance was evaluated using a nested cross-validation framework, followed by validation on an independent geology-informed spatial holdout test set to ensure realistic generalization. Among machine learning models, the Logistic Regression (LR), Support Vector Classifier (SVC), XGBoost (XGB), Decision Tree (DT), Gaussian Naïve Bayes (GNB), and K-Nearest Neighbours (KNN) were evaluated. Support Vector Classifier (SVC) demonstrated a high predictive performance. On the independent spatial holdout dataset, SVC achieved an overall accuracy of 0.75 and an area under the receiver operating characteristic curve (AUC) of 0.821. In addition to classification, a human health risk assessment was conducted using chronic daily intake (CDI) and hazard quotient (HQ) calculations for children and adults, identifying several high-risk water supply schemes. The prediction maps successfully delineated high-risk fluoride points across specific areas, offering a tool for sustainable groundwater management. This study helps to achieve a Sustainable Development Goal (Clean Water and Sanitation, SDG#6) and promotes long-term sustainable planning in water-stressed areas by integrating spatial machine learning mapping and health risk assessment. Full article

In semiconductor fabrication, abnormal behavior may first appear in a small subset of serial numbers before it is reflected in lot-level yield metrics. We present a monitoring framework that detects measurement item outliers using Z-scores, aggregates them into a serial-level cumulative-risk score, provides exploratory views of lot- and site-level trends, and ranks high-risk serials for follow-up. The approach is evaluated on an industrial semiconductor manufacturing dataset comprising 14,142 unique serials (${\mathrm{N}}_{\mathrm{s}\mathrm{e}\mathrm{r}\mathrm{i}\mathrm{a}\mathrm{l}}$ = 14,142). Because most TestResult labels are PASS, label-based yield shows little variation. In this setting, label-based yield alone is not informative enough for early monitoring, so we use outlier-based yield as the primary metric, defined as the proportion of serials with cumulative risk below the threshold ($\mathrm{R}\left(\mathrm{s}\right)<\mathrm{\tau }$, where $\mathrm{\tau }=10$). A sensitivity study of the outlier threshold $\mathrm{\kappa }$ ($\mathrm{\sigma }$-multiplier) shows that yield varies widely, from 61.66% at $\mathrm{\kappa }=3$ to above 99% at $\mathrm{\kappa }\ge 7$. This result shows the trade-off between detection sensitivity and inspection workload. Case studies of top-ranked serials show two recurring patterns: cumulative risk is driven either by isolated extreme deviations or by the accumulation of moderate deviations across multiple items. These results support the use of the proposed score for inspection prioritization. Full article

The enhancement of startup and performance in a Tetradesmus obliquus-polyurethane sponge biofilm system was investigated via the regulation of the phytohormone Indole-3-acetic acid (IAA). IAA supplementation at 1 and 5 mg/L increased biofilm biomass and chlorophyll a content, with the maximum biofilm biomass reaching 48.2 mg/g, and improved nutrient removal performance under shock-loading conditions, particularly for total nitrogen (TN) and total phosphorus (TP). IAA treatment was associated with EPS remodeling, including an increase in the protein/polysaccharide ratio to 0.68 and a 16% enrichment in tryptophan-like protein components. These EPS-related changes coincided with a decrease in the absolute zeta potential to −2.49 mV, which may be relevant to enhanced initial biofilm development. The corresponding EPS-related changes were characterized by three-dimensional excitation–emission matrix (3D-EEM) and Fourier transform infrared (FTIR) analyses using representative concentrations. Furthermore, the IAA-treated biofilm showed improved resilience under low, medium, and high loading conditions, with the most favorable TN removal reaching 87% at 1 mg/L IAA. These results suggest that IAA supplementation at 1 and 5 mg/L can promote microalgal biofilm start-up and improve nutrient-removal resilience under the tested conditions, with 5 mg/L showing the strongest response in biofilm growth and structural characterization. Full article

Early detection of battery degradation is essential for ensuring the safety and reliability of electric vehicle (EV) systems under real-world operating variability. This paper proposes a physics-guided multi-sensor learning framework, termed SensorFusion-Former (SFF), for early warning of short-term EV battery performance degradation. The proposed approach integrates a physics-based baseline model for operational normalization, a multi-sensor fusion attention mechanism to model cross-modality interactions, and a lightweight transformer architecture for efficient temporal representation learning. Weak supervision is derived from physics-consistent residual analysis with temporal smoothing, enabling scalable training without dense manual annotations. To support reliable deployment, evidential uncertainty modeling and conformal calibration are incorporated to obtain statistically controlled decision thresholds. Experiments conducted on a real driving cycle dataset from IEEE DataPort demonstrate that SFF consistently outperforms classical machine learning methods, deep neural networks, and standard transformer models in terms of early-warning lead time, false alarm rate, and inference efficiency while maintaining competitive discriminative performance. Cross-scenario evaluations under diverse thermal conditions further confirm the robustness and generalization capability of the proposed framework. Full article

Severe Fever with Thrombocytopenia Syndrome (SFTS) is caused by the SFTS virus (SFTSV) and is associated with a high mortality rate. Although previous studies have reported RNA modifications such as m6A on SFTSV RNA, an integrated analysis of native viral transcript architecture and multiple RNA modification types within infected cells remains lacking. Here, we used Oxford Nanopore direct RNA sequencing (DRS) to analyze native SFTSV RNA in infected cells, combining strand-specific alignment, isoform reconstruction through read endpoint clustering, isoform-level quantification, and signal-level modification identification using unmodified in vitro transcripts as a baseline. This approach allowed us to construct detailed maps of the L, M, and bidirectionally encoded S segments at single-molecule, isoform-level resolution. The results reveal a “length-layering” pattern in SFTSV transcription, anchored by recurrent 3′ termination hotspots: only a few full-length transcripts dominate expression, whereas multiple reproducible truncated isoforms were associated with discrete termination windows, a pattern less consistent with random degradation alone and suggestive of regulated transcript termination. At the single-nucleotide level, the modification landscape is predominantly Ψ (pseudouridine), followed by m⁵C (5-methylcytosine), with sparse m⁶A (N6-methyladenosine). Modification hotspots are co-located across isoforms at the same genomic coordinates, exhibiting segmental/strand asymmetry, with sharper peaks on (−) RNA. These patterns provide a testable framework and raise the possibility that transcript-boundary organization and site-constrained Ψ/m5C signals may be associated with variation in viral RNA output. More broadly, isoform proportions around termination hotspots and Ψ/m5C-enriched regions at conserved sites may serve as quantitative features for characterizing viral RNA organization and prioritizing targets for future functional investigation. Our single-molecule integrated map establishes a reproducible methodological framework for studying SFTSV RNA regulation and provides a resource for future work aimed at assessing how transcript boundaries and RNA modification patterns may relate to polymerase activity and virus–host interaction. Full article

Student retention has become a major challenge for higher education institutions due to the influence that academic, socioeconomic, family, and motivational factors exert on students’ academic continuity. In this context, understanding the determinants that explain university persistence is essential for designing effective retention strategies. Based on the analysis of factors related to motivation, commitment, attitude, academic integration, and social and economic conditions, retention patterns were examined in a population of 532 university students, of whom 57.7% showed high retention, 38.2% medium retention, and 4.1% low retention. To identify the factors with the greatest influence on academic continuity, educational data mining techniques and supervised classification models were applied and evaluated using stratified 10-fold cross-validation. Tree-based ensemble models showed the most consistent predictive performance, with Random Forest achieving the best results (accuracy = 0.729 ± 0.058; F1-macro = 0.636 ± 0.136). Model interpretability was examined through SHAP analysis, which revealed that transportation conditions (0.249), task completion (0.170), absence of work obligations (0.168), and course completion (0.164) were the most influential predictors in the classification of retention levels. In addition, sensitivity analysis indicated that academic commitment accounts for 41.6% of the predictive impact, followed by motivation (23.5%). These findings demonstrate that student retention is shaped by the interaction of academic, motivational, and contextual factors and provide practical implications for the development of **early warning systems, personalized tutoring programs, psychosocial support initiatives, and financial assistance policies aimed at strengthening university retention. Full article

Against the backdrop of climate change, forest fires increasingly undermine ecosystem stability and reshape species distributions in Heilongjiang Province. Therefore, quantifying the drivers of fire occurrence and conducting long-term fire risk forecasting holds critical value for regional ecological security. Centered on the forested regions of Heilongjiang Province, this study systematically assessed the relative contributions of multi-source factors—including topography, vegetation, and meteorological conditions—to fire occurrence and compared the predictive performance of three models: Deep Neural Network with Residual Connections (ResDNN), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Modeling results based on historical fire records indicated that the ResDNN model achieved the highest accuracy (85.6%). Owing to its robust nonlinear mapping capability, it performed better in capturing complex feature interactions than ANN and SVM. These results demonstrate its strong applicability to forest fire prediction in Heilongjiang Province. Building on these findings, the study employed the best-performing ResDNN model in conjunction with CMIP6 multi-model climate projections to simulate and map the spatiotemporal probability of forest fire occurrence from 2030 to 2070. The results provide an intuitive representation of long-term fire-risk trajectories under future climate scenarios and offer scientific support for regional fire prevention, monitoring, early-warning systems, and forest management under climate change. Full article

Frequent flash floods threaten human well-being, hydropower infrastructure, and ecosystems. However, the long-term evolution of flash flood patterns over recent decades remains insufficiently understood, particularly in data-scarce high-altitude regions. Using multi-source remote sensing data integrated with historical disaster records and field investigations, this study examined the spatiotemporal evolution and driving factors of flash floods across the Qinghai–Tibet Plateau (QTP). The results indicate that flash floods have increased exponentially, which may be influenced by disaster management policies, with peaks in July–August and frequent occurrences from April to September. The seasonal trajectory of the center of gravity of flash floods from April to September exhibited a clear directional pattern. Regions with the highest disaster density were concentrated in the headwaters of five major rivers, including the Yarlung Zangbo, Jinsha, Nu, Lancang, and Yellow Rivers. Shapley Additive Explanation (SHAP) and Random Forest analyses reveal that soil moisture, anthropogenic intensity, and seasonal runoff variability are the dominant driving factors. With ongoing socioeconomic development, intensified human activities have become a key contributor to the increasing frequency of flash floods. These findings highlight the value of remote sensing-based assessments for flash flood monitoring and early warning and provide scientific support for risk mitigation, loss reduction, and the advancement of water-related targets under the United Nations’ Sustainable Development Goals. Full article

The nonlinearity and the extreme variability of seismic signals makes the detection of earthquakes difficult. Although the conventional deep-learning models can be used to extract useful features, they cannot be used in early-warning systems due to their non-interpretability. In this study, a Bidirectional Long Short-Memory network with an attention system (Bi-LSTM-Attn) is proposed to detect seismic events using the ConvNetQuake dataset. To improve the quality of data, the entire preprocessing pipeline, such as signal filtering, segmentation, normalization, and noise reduction is employed. The model was optimized using hyperparameter tuning of sequence length, learning rates, and attention weighting to achieve the best number of true-positive detections and a minimum number of false alarms. The accuracy, precision and recall, F1-score, MSE, and ROC curves were used to assess the performance and the attention weight visualization allowed interpreting the model. It is proven through experiments that the Bi-LSTM-Attn model provides more credible and comprehensible forecasting in relation to baseline LSTM and GRU models. Making the high-accuracy classification and the transparent decision behavior, the approach will increase the level of trust to the automated seismic surveillance, as well as help to build the reliable global networks of earthquake early-warnings. Full article

Global climate change and increasingly complex geological conditions have led to more frequent landslides in the red-bed sedimentary layers of western Sichuan, China, posing severe threats to human safety and hindering progress toward regional Sustainable Development Goals (SDGs), particularly those related to disaster risk reduction and ecological protection. To address this challenge and advance sustainable disaster management, this study proposes a lightweight hybrid model, termed Transformer–Attention–LSTM, which integrates the global attention mechanism of Transformers with the local time-series modeling capabilities of Long Short-Term Memory networks. Focusing on the Kuyaogou landslide, the model achieves an optimal balance between parameter scale, sequence length, and prediction accuracy. The mean Coefficient of Determination (R²) values for the test samples in the X, Y, and Z directions reached 0.948, representing enhancements of 9.9%, 4.2%, and 2.3%, respectively, compared to the suboptimal Attention–LSTM model. Concurrently, the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were reduced to 9.23 mm and 7.17 mm, respectively. Based on these displacement predictions, the landslide evolution stage was determined by calculating the tangent angle, indicating that the Kuyaogou landslide will remain in a stable creep phase over the ensuing ten-day period with low overall risk of rapid movement, though localized instability requires continued monitoring. This research provides a ‘small, fast, and accurate’ paradigm for red-bed landslide displacement prediction, offering scientific support for disaster prevention and emergency decision-making. The framework demonstrates potential for broader application in monitoring other geological hazards, thereby contributing to the implementation of sustainable development strategies in geohazard-prone regions. Full article

Dual-band weather radar networks enable complementary multi-radar observations, improving the accuracy, three-dimensional characterization, and early warning capability for severe convective weather. S-band radar provides strong penetration and long detection range but suffers from limited spatial resolution, whereas X-band radar offers high resolution with weaker penetration, posing challenges for dual-frequency data fusion. To address the resolution mismatch and fusion modeling issues between dual-band radars, this study proposes a super-resolution reconstruction method for S-band reflectivity based on dual-frequency radar observations. S-band and X-band radar data, together with key polarimetric parameters, are jointly incorporated into a deep neural network-based fusion model to enhance the spatial resolution of S-band reflectivity. Experimental results under typical severe weather conditions demonstrate that the proposed method achieves improved detail recovery and structural reconstruction, with the model achieving PSNR 30.84, SSIM 0.8755, and MAE 0.24178, which shows obvious advantages compared with other models and effectively enhances radar network data quality, and it outperforms single S-band super-resolution approaches in both objective metrics and subjective evaluations. Full article

Long-distance coal gangue slurry transportation pipelines are critical components of underground coal mine green backfilling systems, yet blockage failures severely threaten their safe and efficient operation. Existing distributed acoustic sensing (DAS)-based monitoring methods for such pipelines suffer from three key limitations: insufficient fixed-point quantitative accuracy, lack of verified blockage-specific characteristic indicators, and limited quantitative severity assessment capability. To address these gaps, this paper proposes a novel feature-level fusion monitoring method integrating DAS, fiber Bragg grating (FBG), and piezoelectric accelerometers for accurate blockage identification and quantitative evaluation in coal gangue slurry pipelines. A slurry pipeline circulation test platform with gradient blockage simulation (0% to 76.42%) and a synchronous multi-sensor monitoring system were developed. Through multi-domain signal analysis, three blockage-correlated characteristic frequencies were identified and cross-validated by synchronous multi-sensor data: 1.5 Hz (system background vibration), 26 Hz (blockage-induced fluid–structure resonance, verified by the Euler–Bernoulli beam theory with a theoretical value of 25.7 Hz), and 174 Hz (transient flow impact). The DAS phase change rate exhibited a unimodal nonlinear response to blockage degree, with the peak occurring at 40.94% blockage. On this basis, a sine-fitting quantitative inversion model was developed, achieving a high goodness of fit (R² = 0.985), and leave-one-out cross-validation confirmed its excellent robustness with a mean relative prediction error of 3.77%. Finally, a collaborative monitoring framework was built to fully leverage the complementary advantages of each sensor, realizing full-process blockage monitoring covering global blockage localization, precise quantitative severity calibration, and high-frequency transient risk early warning. The proposed method provides a robust experimental and technical foundation for real-time early warning, precise localization, and quantitative diagnosis of long-distance slurry pipeline blockages and holds important engineering application value for the safe and efficient operation of underground coal mine green backfilling systems. Full article

Charge transport underpins essential biological processes, including cellular respiration, photosynthesis, and enzymatic catalysis. Advances in molecular electronics have enabled single-molecule measurements that unequivocally establish redox-active proteins as efficient electron conductors, with their metal cofactors serving as intrinsic redox relays. By contrast, ubiquitous non-redox proteins lacking such redox centers have long been considered poor conductors. However, recent research has challenged this view, demonstrating that efficient charge transport in non-redox proteins can be mediated through polypeptide backbones, aromatic side-chain arrays, and hydrogen bond networks. This review surveys progress in understanding the single-molecule conductance of non-redox proteins. Firstly, we elucidate the fundamental transport mechanisms, highlighting the interplay between coherent tunneling and thermally activated hopping. We then provide an overview of state-of-the-art experimental techniques for single-molecule characterization. Through analysis of diverse systems spanning short peptides to large enzymes, we illustrate how aromatic amino acid networks and dynamic conformational fluctuations govern conductance, enabling emerging applications in label-free biosensing and single-molecule protein/DNA sequencing. Finally, we discuss persistent challenges and outline future opportunities for integrating protein-based conductors into bioelectronic devices. This review aims to stimulate further research and pave the way for novel applications harnessing protein conductance. Full article