Search Results (1,166)

Rational agronomic practice enhances crop productivity and resource use efficiency. Plastic film mulching and phosphorus (P) fertilization are widely applied in alpine agriculture to improve soil water content, temperature, and P availability. However, their effects on soil P transformation and nutrient uptake in faba bean (Vicia faba L.) remain unclear. This study conducted a field experiment to explore the effects of mulching methods and P levels on soil P fractions and nitrogen (N), P uptake in faba bean. The experiment followed a randomized block design with three film mulching treatments—no-mulching with flat planting (NMF), double ridges and furrows mulched with one film (DRM), and three ridges and furrows mulched with one film (TRM) and three P levels—P0 (0 kg P ha⁻¹), P1 (9.10 kg P ha⁻¹), and P2 (18.2 kg P ha⁻¹). The results showed that soil medium- and highly active P increased, while low-active P decreased with increasing P levels. Compared with DRM and TRM, NMF had lower low-active P and higher medium- and highly active P, particularly under P2. These changes contributed to increases in soil total P and available P. The aboveground N, P uptake and N/P ratio under NMF were significantly higher than under DRM and TRM. As P levels increased, the aboveground N, P uptake and N/P ratio increased in NMF and DRM, but decreased in TRM. In all treatments, the aboveground N/P ratio was below 14, indicating N limitation. NMF, especially with P2, alleviated N limitation to faba bean growth. Overall, NMF combined with about 18.2 kg P ha⁻¹ P fertilizer is a sustainable practice for faba bean cultivation in alpine regions. However, attention should be paid to achieving a balanced supply of N and P fertilizers. Full article

Recently, music generation models based on deep learning have made remarkable progress in the field of symbolic music generation. However, the existing methods often have problems of violating musical rules, especially since the control of harmonic structure is relatively weak. To address these limitations, this paper proposes a novel framework, the Entropy-Regularized Latent Diffusion for Harmony-Constrained (ERLD-HC), which combines a variational autoencoder (VAE) and latent diffusion models with an entropy-regularized conditional random field (CRF). Our model first encodes symbolic music into latent representations through VAE, and then introduces the entropy-based CRF module into the cross-attention layer of UNet during the diffusion process, achieving harmonic conditioning. The proposed model balances two key limitations in symbolic music generation: the lack of theoretical correctness of pure algorithm-driven methods and the lack of flexibility of rule-based methods. In particular, the CRF module learns classic harmony rules through learnable feature functions, significantly improving the harmony quality of the generated Musical Instrument Digital Interface (MIDI). Experiments on the Lakh MIDI dataset show that compared with the baseline VAE+Diffusion, the violation rates of harmony rules of the ERLD-HC model under self-generated and controlled inputs have decreased by 2.35% and 1.4% respectively. Meanwhile, the MIDI generated by the model maintains a high degree of melodic naturalness. Importantly, the harmonic guidance in ERLD-HC is derived from an internal CRF inference module, which enforces consistency with music-theoretic priors. While this does not yet provide direct external chord conditioning, it introduces a form of learned harmonic controllability that balances flexibility and theoretical rigor. Full article

Burned area (BA) mapping and fire severity assessment are essential for understanding fire occurrence patterns, formulating post-fire restoration strategies and evaluating vegetation recovery processes. However, existing BA datasets are primarily derived from coarse-resolution satellite imagery and often lack sufficient consideration of fire severity. To address these limitations, this study utilized dense time-series Landsat imagery available on the Google Earth Engine, applying the qualityMosaic method to generate annual composites of minimum normalized burn ratio values. These composites imagery enabled the rapid identification of fire sample points, which were subsequently used to train a random forest classifier for estimating per-pixel burn probability. Pixels with a burned probability greater than 0.9 were selected as the core of the BA, and used as candidate seeds for region growing to further expand the core and extract complete BA. This two-stage extraction method effectively balances omission and commission errors. To avoid the repeated detection of unrecovered BA, this study developed distinct correction rules based on the differing post-fire recovery characteristics of forests and grasslands. The extracted BA were further categorized into four fire severity levels using the delta normalized burn ratio. In addition, we conducted a quantitative validation of the BA mapping accuracy based on Sentinel-2 data between 2015 and 2023. The results indicated that the BA mapping achieved an overall accuracy of 93.90%, with a Dice coefficient of 82.04%, and omission and commission error rates of 26.32% and 5.25%, respectively. The BA dataset generated in this study exhibited good spatiotemporal consistency with existing products, including MCD64A1, FireCCI51, and GABAM. The BA fluctuated significantly between 1985 and 2010, with the highest value recorded in 1987 (13,315 km²). The overall trend of BA showed a decline, with annual burned areas remaining below 2000 km² after 2010 and reaching a minimum of 92.8 km² in 2020. There was no significant temporal variation across different fire severity levels. The area of high-severity burns showed a positive correlation with the annual total BA. High-severity fire-prone zones were primarily concentrated in the northeastern, southeastern, and western parts of the study area, predominantly within grasslands and forest–grassland ecotone regions. Full article

Background/Objectives: While antibiotic prophylaxis is crucial for preventing infections, its impact on the development of antibiotic-resistant infections and clinical outcomes remains underexplored. We aimed to systematically assess the impact of medical and surgical antibiotic prophylaxis (SAP) on the development of antibiotic-resistant infections, clinical outcomes, and costs. Methods: A systematic review and meta-analysis of the effect of antibiotic prophylaxis on antibiotic-resistant infections, mortality, length of hospital stay, and/or costs was conducted in hemato-oncological or surgical patient populations. Pooled estimates of the relative risk (RR) or weighted mean difference (WMD) were derived using random-effect meta-analysis. Results: Of 10,409 screened studies, 109 (30%) comprising 131,519 patients were included. In 55 hemato-oncological studies, prophylaxis significantly reduced Gram-negative infections (RR: 0.51; 95% CI: 0.45 to 0.59) without an effect on mortality (RR = 1.01; 95% CI: 0.89 to 1.15), while the risk of developing an infection resistant to prophylactic antibiotics during hospitalization was doubled (RR: 2.05; 95% CI: 1.88 to 2.23). The length of hospitalization was reduced by 1.85 days. Among 54 surgical studies, SAP lowered surgical-site infections (RR: 0.58; 95% CI: 0.49 to 0.69). Extending prophylaxis beyond the recommended duration did not improve infection rates (RR: 1.10; 95% CI: 0.98 to 1.24). No association was demonstrated between prophylaxis adjusted by colonization status and the development of resistant infections. Conclusion: Though proven beneficial, our results highlight the critical need for targeted antibiotic stewardship programs (ASPs) in both settings. A meticulous risk assessment balancing the benefits of preventing life-threatening infections against the risk of driving antimicrobial resistance, and a tailored ASP, is urgently needed for hemato-oncological patients. Full article

Background/Objectives: Motor difficulties are commonly reported in autistic individuals, but they are not currently part of the diagnostic criteria. A better understanding of how motor impairments are assessed in this population is critical to inform clinical practice and intervention. This systematic review aims to evaluate the existing literature on motor skill assessment in autistic children and adolescents, focusing specifically on studies that employed standardized and validated clinical motor assessment tools. Methods: Registered on PROSPERO (CRD42025637880), a systematic search was conducted on PubMed, Science Direct, and Web of Science until 31 December 2024. The review includes: (a) studies published in peer-reviewed journals; (b) randomized controlled trials (RCTs) and observational studies; (c) evaluations of motor difficulties using standardized and validated clinical assessments specifically designed to measure motor skills or coordination abilities; (d) participants diagnosed with ASD based on the Diagnostic and Statistical Manual of Mental Disorders (DSM-IV or DSM-5) or the International Classification of Diseases (ICD-9 or ICD-10); and (e) participants aged ≤18 years; Results: Twenty-two studies met the inclusion criteria. Most studies reported significant motor impairments across various domains, including balance, manual dexterity, and coordination. However, there was substantial variability in the severity of motor deficits and in the assessment tools used. Methodological heterogeneity limited direct comparison across studies. Conclusions: Motor impairments are common in autistic children and adolescents; however, current assessment tools show limitations and require adaptations. The findings underscore the need for autism-specific motor assessments to improve diagnostic accuracy and guide personalized interventions. Full article

Purpose: This study aimed to develop and validate a new machine learning (ML)-based screening tool for a two-step prediction of the need for and type of nutritional therapy (enteral, parenteral, or combined) using Nutrition Risk Screening 2002 (NRS-2002) and other demographic parameters from the Optimal Nutrition Care for All (ONCA) national cohort data. Methods: This multicenter retrospective cohort study included 191,028 patients, with data on age, gender, body mass index (BMI), NRS-2002 score, presence of cancer, and hospital unit type. In the first step, classification models estimated whether patients required nutritional therapy, while the second step predicted the type of therapy. The dataset was divided into 60% training, 20% validation, and 20% test sets. Random Forest (RF), Artificial Neural Network (ANN), deep learning (DL), Elastic Net (EN), and Naive Bayes (NB) algorithms were used for classification. Performance was evaluated using AUC, accuracy, balanced accuracy, MCC, sensitivity, specificity, PPV, NPV, and F₁-score. Results: Of the patients, 54.6% were male, 9.2% had cancer, and 49.9% were hospitalized in internal medicine units. According to NRS-2002, 11.6% were at risk of malnutrition (≥3 points). The DL algorithm performed best in both classification steps. The top three variables for determining the need for nutritional therapy were severe illness, reduced dietary intake in the last week, and mild impaired nutritional status (AUC = 0.933). For determining the type of nutritional therapy, the most important variables were severe illness, severely impaired nutritional status, and ICU admission (AUC = 0.741). Adding gender, cancer status, and ward type to NRS-2002 improved AUC by 0.6% and 3.27% for steps 1 and 2, respectively. Conclusions: Incorporating gender, cancer status, and ward type into the widely used and validated NRS-2002 led to the development of a new scale that accurately classifies nutritional therapy type. This ML-enhanced model has the potential to be integrated into clinical workflows as a decision support system to guide nutritional therapy, although further external validation with larger multinational cohorts is needed. Full article

Aim of the Study: To determine whether adding a lateral extra-articular tenodesis (LET) to primary anterior cruciate ligament reconstruction (ACLR) lowers graft-failure risk and improves functional recovery in competitive athletes with high-grade pivot-shift. Methods: Multicentre retrospective cohort with 1:1 propensity-score matching (age, sex, sport, graft, centre). Competitive athletes with pivot-shift grade ≥ 2 who underwent primary ACLR with hamstring or bone–patellar tendon–bone (BPTB) autografts (2018–2024) were eligible. The primary outcome was graft failure within 24 months (composite of revision ACLR, symptomatic rotatory laxity with pivot-shift ≥ 2 plus KT-1000 > 5 mm, or MRI-confirmed rupture). Time-to-event was summarised with Kaplan–Meier (KM) curves and log-rank tests. Secondary outcomes included residual rotatory laxity and functional performance (single-leg hop, side hop, Y-Balance) analysed as the proportion achieving Limb Symmetry Index ≥ 90% at 6 and 24 months and as continuous LSI means. Two-sided α = 0.05; secondary outcomes were prespecified without multiplicity adjustment. Results: Of 1368 ACL reconstructions screened, 97 eligible athletes were identified; 92 were analysed after matching (46 isolated ACLR; 46 ACLR + LET; mean follow-up 30.0 ± 4.2 months). KM survival at 24 months was 95.7% after ACLR + LET versus 82.6% after isolated ACLR (log-rank p = 0.046). The absolute risk reduction was 13.0% (Number Needed to Treat 8; 95% CI 4→∞). In graft-type subgroups, failures were 6/32 vs. 1/30 for hamstring and 2/14 vs. 1/16 for BPTB (ACLR vs. ACLR + LET, respectively); there was no evidence of interaction (Breslow–Day p = 0.56). At 6 months, a higher proportion of ACLR + LET athletes achieved LSI ≥ 90% across tests—single-leg hop 77.8% vs. 40.9% (p = 0.0005), side hop 62.2% vs. 34.9% (p = 0.012), Y-Balance 84.4% vs. 59.1% (p = 0.010), with a larger mean LSI (between-group differences +8.2 to +9.1, all p < 0.001). By 24 months, threshold attainment largely converged (all p ≥ 0.06), while mean LSI differences persisted but were smaller (+3.9 to +4.9, all p ≤ 0.001). Conclusion: In competitive athletes with high-grade pivot-shift undergoing accelerated, criteria-based rehabilitation, adding LET to primary ACLR was associated with lower graft-failure risk and earlier functional symmetry, with consistent effects across hamstring and BPTB autografts. Given the observational design, causal inference is limited; confirmation in randomized and longer-term studies is warranted. Full article

Background: Older adults with mild cognitive impairment are at increased risk for physical decline and falls due to decreased strength, flexibility, balance, and gait. Dance-based aerobic training has emerged as a promising and enjoyable intervention to promote physical function and cognitive stimulation. This study aimed to evaluate the efficacy of a 12-week structured dance-based aerobic program, based on line dancing and Latin rhythms (e.g., salsa, merengue, and bachata), in improving functional capacity and reducing the risk of falls in older adults with mild cognitive impairment. Methods: A randomized controlled trial was conducted with 92 participants aged ≥65 years diagnosed with mild cognitive impairment. The participants were randomly assigned to an experimental group (dance-based training, twice weekly for 12 weeks) or a control group (usual activity). Outcomes included muscle strength (grip dynamometry), flexibility (back scratch and chair sit-and-reach tests), gait speed (Timed Up and Go test), balance (Tinetti scale), and total falls risk score (Tinetti). Mixed ANOVA and Cohen’s d were used for statistical analysis. Results: Significant improvements were observed in the experimental group on all variables compared to the control group. Muscle strength (p < 0.001, d = 0.86), gait speed (p = 0.026, d = 0.48), and upper and lower extremity flexibility (d = 0.43–0.79) improved significantly. The balance and gait components of the Tinetti scale also increased (p = 0.007 and p = 0.048, respectively), as did the total Tinetti score (p = 0.002, d = 0.67), indicating a reduction in the risk of falls. Conclusions: These findings suggest that, under structured conditions, dance-based aerobic training may serve as a promising non-pharmacological strategy to support healthy aging in older adults with mild cognitive impairment, although further validation in larger cohorts is needed. Full article

Background: Antithrombotic therapy plays an important role in acute coronary syndrome (ACS). The combination of anticoagulant and antiplatelet therapy resulted in fewer complications and stronger potency compared to traditional monotherapy. Our net meta-analysis aimed to compare and rank the safety of different treatments used in patients with ACS. Method: We conducted a search for trials in three prominent databases. The main objective of our investigation was to assess hemorrhage. Additional outcomes included mortality, myocardial infarction, stroke, and embolism. We used a frequentist network meta-analysis with a random-effects model to, directly and indirectly, compare safety across different antithrombotic strategies. Result: A total of 30 randomized clinical trials were included in this net meta-analysis with 135,471 ACS patients. In these eight different antithrombotic therapies, SAPT (single-agent platelet inhibitor therapy) showed the lowest risk of bleeding (SUCRA = 0.5%). The highest risk of bleeding was observed in VKA (vitamin K antagonists) + DAPT (dual antiplatelet therapy) (SUCRA = 99.8%). Bleeding among NOAC (non-vitamin K antagonist oral anticoagulants) + DAPT was found to be higher than DAPT (OR = 1.94, 95% CI = 1.42–2.65). NOAC + SAPT significantly reduced the embolism (OR = 1.50, 95% CI = 1.16–1.94) and myocardial infarction (OR = 1.22, 95% CI = 1.08–1.37) events compared with SAPT. In addition, VKA significantly reduced the rate of stroke compared with SAPT (OR = 3.45, 95% CI = 1.17–10.18). However, no significant difference was observed in death events among these eight antithrombotic therapies. Conclusions: We advise against the use of SAPT in ACS due to its elevated risk of embolism, myocardial infarction, and stroke. It is important to mention that the combination of NOAC and SAPT has a lower incidence of myocardial infarction, bleeding and embolism problems. Therefore, the combination of NOAC and SAPT may be the optimal approach to achieve a balance between the risks of bleeding and embolism. This meta-analysis was registered in PROSPERO with the registration number CRD42024542826. Full article

Automatic Facial Expression Recognition (AFER) is a key component of affective computing, enabling machines to recognize and interpret human emotions across various applications such as human–computer interaction, healthcare, entertainment, and social robotics. Dynamic AFER systems, which exploit image sequences, can capture the temporal evolution of facial expressions but often suffer from high computational costs, limiting their suitability for real-time use. In this paper, we propose an efficient dynamic AFER approach based on a novel spatio-temporal representation. Facial landmarks are extracted, and all possible Euclidean distances are computed to model the spatial structure. To capture temporal variations, three statistical metrics are applied to each distance sequence. A feature selection stage based on the Extremely Randomized Trees (ExtRa-Trees) algorithm is then performed to reduce dimensionality and enhance classification performance. Finally, the emotions are classified using a linear multi-class Support Vector Machine (SVM) and compared against the k-Nearest Neighbors (k-NN) method. The proposed approach is evaluated on three benchmark datasets: CK+, MUG, and MMI, achieving recognition rates of 94.65%, 93.98%, and 75.59%, respectively. Our results demonstrate that the proposed method achieves a strong balance between accuracy and computational efficiency, making it well-suited for real-time facial expression recognition applications. Full article

To address the negative sample selection bias and limited interpretability of traditional debris-flow event susceptibility models, this study proposes a framework that enhances generalization by integrating negative sample screening via a stacking ensemble model with an interpretable random forest. Using Wenchuan County, Sichuan Province, as the study area, 19 influencing factors were selected, encompassing topographic, geological, environmental, and anthropogenic variables. First, a stacking ensemble—comprising logistic regression (LR), decision tree (DT), gradient boosting decision tree (GBDT), and random forest (RF)—was employed as a preliminary classifier to identify very low-susceptibility areas as reliable negative samples, achieving a balanced 1:1 ratio of positive to negative instances. Subsequently, a stacking–random forest model (Stacking-RF) was trained for susceptibility zonation, and SHAP (Shapley additive explanations) was applied to quantify each factor’s contribution. The results show that: (1) the stacking ensemble achieved a test-set AUC (area under the receiver operating characteristic curve) of 0.9044, confirming its effectiveness in screening dependable negative samples; (2) the random forest model attained a test-set AUC of 0.9931, with very high-susceptibility zones—covering 15.86% of the study area—encompassing 92.3% of historical debris-flow events; (3) SHAP analysis identified the distance to a road and point-of-interest (POI) kernel density as the primary drivers of debris-flow susceptibility. The method quantified nonlinear impact thresholds, revealing significant susceptibility increases when road distance was less than 500 m or POI kernel density ranged between 50 and 200 units/km²; and (4) cross-regional validation in Qingchuan County demonstrated that the proposed model improved the capture rate for high/very high susceptibility areas by 48.86%, improving it from 4.55% to 53.41%, with a site density of 0.0469 events/km² in very high-susceptibility zones. Overall, this framework offers a high-precision and interpretable debris-flow risk management tool, highlights the substantial influence of anthropogenic factors such as roads and land development, and introduces a “negative-sample screening with cross-regional generalization” strategy to support land-use planning and disaster prevention in mountainous regions. Full article

As smart cities continue to generate vast quantities of data, data integrity is increasingly threatened by instances of fraud. Anomalous or fake data deteriorate the process and have impacts on decision-making systems and predictive analytics. Hence, an effective and intelligent fake data detection model was designed by combining an advanced feature selection method with a robust ensemble classification framework. Initially, the raw data are eliminated by performing normalization, feature transformation, and noise filtering that enhances the reliability of the model. The dimensionality issues are mitigated by eliminating redundant features via the proposed Elite Tuning Strategy-Enhanced Polar Bear Optimization algorithm. It simulates the hunting behavior of polar bears, balancing exploration and exploitation features. The proposed Stacking Ensemble-based Random AdaBoost Quadratic Discriminant model leverages the merits of diverse base learners, including AdaBoost, Quadratic Discriminant Analysis, and Random Forest, that classify the feature subset and the integration of prediction processes with a meta-feature vector-processed meta-classifier such as a multilayer perceptron or logistic regression model that predicts the final outcome. This hierarchical architecture validates resilience against noise and improves generalization and prediction accuracy. Thus, the experimental results show that the proposed method outperforms existing approaches in terms of accuracy, precision, and latency, yielding values of 98.78%, 98.75%, and 16 ms, respectively, using the UNSW-NB15 dataset. Full article

Blockchain sharding has emerged as a promising solution to address scalability and performance challenges in distributed ledger systems. In the sharded blockchain, yanking can reduce the communication overhead of smart contracts between shards. However, the existing smart contract yanking methods are inefficient, increasing the latency and reducing the throughput. In this paper, we propose a novel DRL-Based Cross-Shard Smart Contract Yanking (DCSCY) framework which intelligently balances three critical factors: the number of smart contracts processed, node waiting time, and yanking costs. The proposed framework dynamically optimizes the relocation trajectory of smart contracts across shards. This reduces the communication overhead and enables adaptive, function-level migrations to enhance the execution efficiency. The experimental results demonstrate that the proposed approach reduces the cross-shard transaction latency and enhances smart contract utilization. Compared to random-based and order-based methods, the DCSCY approach achieves a performance improvement of more than 95%. Full article

Precise forecasting of rockburst intensity categories is vital to safeguarding operational safety and refining design protocols in deep underground engineering. This study proposes an intelligent forecasting framework through the integration of k-medoids-SMOTE and the BSLO-optimized Random Forest (BSLO-RF) algorithm. A curated dataset encompassing 351 rockburst instances, stratified into four intensity grades, was compiled via systematic literature synthesis. To mitigate data imbalance and outlier interference, z-score normalization and k-medoids-SMOTE oversampling were implemented, with t-SNE visualization confirming improved inter-class distinguishability. Notably, the BSLO algorithm was utilized for hyperparameter tuning of the Random Forest model, thereby strengthening its global search and local refinement capabilities. Comparative analyses revealed that the optimized BSLO-RF framework outperformed conventional machine learning methods (e.g., BSLO-SVM, BSLO-BP), achieving an average prediction accuracy of 89.16% on the balanced dataset—accompanied by a recall of 87.5% and F1-score of 0.88. It exhibited superior performance in predicting extreme grades: 93.3% accuracy for Level I (no rockburst) and 87.9% for Level IV (severe rockburst), exceeding BSLO-SVM (75.8% for Level IV) and BSLO-BP (72.7% for Level IV). Field validation via the Zhongnanshan Tunnel project further corroborated its reliability, yielding an 80% prediction accuracy (four out of five cases correctly classified) and verifying its adaptability to complex geological settings. This research introduces a robust intelligent classification approach for rockburst intensity, offering actionable insights for risk assessment and mitigation in deep mining and tunneling initiatives. Full article

Camera tracking plays a pivotal role in augmented reality geographic information systems (AR-GIS) and location-based services (LBS), serving as a crucial component for accurate spatial awareness and navigation. Current learning-based camera tracking techniques, while achieving superior accuracy in pose estimation, often overlook changes in scale. This oversight results in less stable localization performance and challenges in coping with dynamic environments. To address these tasks, we propose a pyramid convolution-based scene coordinate regression network (PSN). Our approach leverages a pyramidal convolutional structure, integrating kernels of varying sizes and depths, alongside grouped convolutions that alleviate computational demands while capturing multi-scale features from the input imagery. Subsequently, the network incorporates a novel randomization strategy, effectively diminishing correlated gradients and markedly bolstering the training process’s efficiency. The culmination lies in a regression layer that maps the 2D pixel coordinates to their corresponding 3D scene coordinates with precision. The experimental outcomes show that our proposed method achieves centimeter-level accuracy in small-scale scenes and decimeter-level accuracy in large-scale scenes after only a few minutes of training. It offers a favorable balance between localization accuracy and efficiency, and effectively supports augmented reality visualization in dynamic environments. Full article