Explore the vast range of titles available.

The detection of wind turbine blades (WTBs) damage is crucial for improving power generation efficiency and extending the lifespan of turbines. However, traditional detection methods often suffer from false positives and missed detections, and they do not adequately account for complex weather conditions such as fog and snow. Therefore, this study proposes a WTBs damage detection model based on an improved YOLOv8, named AUD-YOLO. Firstly, the ADown module is integrated into the YOLOv8 backbone to replace some conventional convolutional down-sampling operations, decreasing the parameter count while boosting the model’s capability to extract image features. Secondly, the model incorporates the UniRepLKNet large convolution kernel with the C2f module, enabling it to learn complex image features more comprehensively. Thirdly, a lightweight DySample dynamic up-sampler substitutes the nearest-neighbor interpolation up-sampling method in the original model, thereby obtaining richer semantic information. Experimental results show that the AUD-YOLO model demonstrates outstanding performance in detecting WTBs damage under complex and adverse weather conditions, achieving a 3% improvement in the mAP@0.5 metric and a 6.2% improvement in the mAP@0.5–0.95 metric compared to YOLOv8. Moreover, the model has only 2.5M parameters and 7.2 GFLOPs of computational complexity, this adaptation renders it appropriate for implementation in environments with constrained computational capacity, where precise detection is critical. Lastly, a mobile application named WTBs Damage Detection system is designed and developed, enabling mobile-based detection of WTBs damage.

The efficacy of machine learning has increased exponentially over the past decade. The utilization of machine learning to predict and design materials has become a pivotal tool for accelerating materials development. High-entropy alloys are particularly intriguing candidates for exemplifying the potency of machine learning due to their superior mechanical properties, vast compositional space, and intricate chemical interactions. This review examines the general process of developing machine learning models. The advances and new algorithms of machine learning in the field of high-entropy alloys are presented in each part of the process. These advances are based on both improvements in computer algorithms and physical representations that focus on the unique ordering properties of high-entropy alloys. We also show the results of generative models, data augmentation, and transfer learning in high-entropy alloys and conclude with a summary of the challenges still faced in machine learning high-entropy alloys today.

Due to the scalability issues of transformers and the limitations of CNN’s lack of typical inductive bias, their applications in a wider range of fields are somewhat restricted. Therefore, the hybrid network architecture that combines the advantages of convolution and Transformer is gradually becoming a hot research and application direction. This article proposes an enhanced dual encoder network (EDE-Net) that integrates convolution and pyramid transformers for medical image segmentation. Specifically, we apply convolutional kernels and pyramid transformer structures in parallel in the encoder to extract features, ensuring that the network can capture local details and global semantic information. To efficiently fuse local details information and global features at each downsampling stage, we introduce the phase-based iterative feature fusion module (PIFF). The PIFF module first combines local details and global features and then assigns distinct weight coefficients to each, distinguishing their importance for foreground pixel classification. By effectively balancing the significance of local details and global features, the PIFF module enhances the network’s ability to delineate fine lesion edges. Experimental results on the GlaS and MoNuSeg datasets validate the effectiveness of this approach. On these two publicly available datasets, our EDE-Net significantly outperforms previous CNN-based (such as UNet) and transformer-based (such as Swin-UNet) algorithms.

Horticultural plants such as vegetables, fruits, and ornamental plants are crucial to human life and socioeconomic development. Gibberellins (GAs), a class of diterpenoid compounds, control numerous developmental processes of plants. The roles of GAs in regulating growth and development of horticultural plants, and in regulating significant progress have been clarified. These findings have significant implications for promoting the quality and quantity of the products of horticultural plants. Here we review recent progress in determining the roles of GAs (including biosynthesis and signaling) in regulating plant stature, axillary meristem outgrowth, compound leaf development, flowering time, and parthenocarpy. These findings will provide a solid foundation for further improving the quality and quantity of horticultural plants products.

Underwater friction stir welding (UFSW) achieves reliable joining between dissimilar materials and meets the welding demand for function and properties in lightweight structures of modern engineering. A defect monitoring method based on Variational Mode Decomposition optimized by Beluga Whale Optimization and Hilbert–Huang Transform (BWO–VMD–HHT) is proposed to solve the unclear feature of AE signal in UFSW due to the aqueous medium. UFSW experiments on Al alloy and carbon fiber reinforced thermoplastic (CFRTP) are carried out with AE signals measured. The time–frequency domain features of AE signals are extracted by BWO–VMD–HHT. The experimental results show that the main frequency of the AE signal is 22.5 kHz, and surface crack defects, shallow hole defects, and deep hole defects are accompanied by the transfer phenomena of different frequency components. Then, the feature vectors are built by frequency components in the BWO–VMD–HHT spectrum and reduced by principal component analysis, including 22.5 kHz, 24 kHz, 20.6 kHz, 18.4 kHz, 17.3 kHz, and 15.6 kHz. The feature vectors are divided into the train and test sets, and the welding defect prediction model (ResNet18-attention) is built by ResNet18 and trained by feature vectors. In the test set, the ResNet18-attention is compared with the BP, SVM, and RBF. Test results show that the precision of models has improved by at least 10%, which are trained by BWO–VMD–HHT features vector. Also, ResNet18-attention has achieved an average precision of 0.906 and recognizes the category of weld defect accurately, and this method can be applied to the defect monitoring of UFSW.

Groundwater sampling at 179 sites in the Guanzhong Basin, China, indicated iodine concentrations ranging from 2 to 28,620 μg/L. 7.3 % of the sites have iodine concentrations <10 μg/L and are categorized as “iodine-deficient water,” whereas 46.0 % display iodine concentrations >300 μg/L and are defined as “iodine excess water.” Sites with low groundwater iodine concentrations are mainly distributed at the edge of a piedmont alluvial–proluvial fan containing bicarbonate-rich water with a low mineral content, near-neutral pH values and low fluorine concentrations. The piedmont fan is characterized by a fast groundwater flow and active leaching of iodine from the sediments. Conversely, high groundwater iodine concentrations are principally located in silty or clayey sedimentary zones having low groundwater flow rates, weakly alkaline to alkaline pH values, and water containing HCO 3 ·SO 4 , SO 4 ·Cl and Cl·SO 4 hydrochemical types. Elevated iodine concentrations in shallow groundwater commonly occur in discharge areas where there is a high rate of solute evaporation; elevated iodine concentrations in deep groundwater are likely attributed to microbial decomposition of organic matter under anaerobic conditions. Processes of iodine enrichment lead to correlations between high iodine and high fluorine contents in shallow groundwater, and between high iodine and high arsenic concentrations in deep groundwater. Moreover, redox processes and active water recycling are important factors for groundwater iodine enrichment.

The Guanzhong Basin in central China features a booming economy and has suffered severe drought, resulting in serious groundwater depletion in the last 30 years. As a major water resource, groundwater plays a significant role in water supply. The combined impact of climate change and intensive human activities has caused a substantial decline in groundwater recharge and groundwater levels, as well as degradation of groundwater quality and associated changes in the ecosystems. Based on observational data, an integrated approach was used to assess the impact of climate change and human activities on the groundwater system and the base flow of the river basin. Methods included: river runoff records and a multivariate statistical analysis of data including historical groundwater levels and climate; hydro-chemical investigation and trend analysis of the historical hydro-chemical data; wavelet analysis of climate data; and the base flow index. The analyses indicate a clear warming trend and a decreasing trend in rainfall since the 1960s, in addition to increased human activities since the 1970s. The reduction of groundwater recharge in the past 30 years has led to a continuous depletion of groundwater levels, complex changes of the hydro-chemical environment, localized salinization, and a strong decline of the base flow to the river. It is expected that the results will contribute to a more comprehensive management plan for groundwater and the related eco-environment in the face of growing pressures from intensive human activities superimposed on climate change in this region.

The prevalence of pulmonary embolism (PE) in the acute exacerbation of chronic obstructive pulmonary disease (AE-COPD) is highly controversial. We conducted a systematic review and meta-analysis to summarize the epidemiology and characteristics of PE with AE-COPD for current studies. We searched the PubMed, EMBASE, Cochrane Library and Web of Science databases for studies published prior to October 21, 2020. Pooled proportions with 95% confidence intervals (95% CIs) were calculated using a random effects model. Odds ratios (ORs) and mean differences (MDs) with 95% confidence intervals were used as effect measures for dichotomous and continuous variables, respectively. A total of 17 studies involving 3170 patients were included. The prevalence of PE and deep vein thrombosis (DVT) in AE-COPD patients was 17.2% (95% CI: 13.4%-21.3%) and 7.1% (95% CI: 3.7%-11.4%%), respectively. Dyspnea (OR = 6.77, 95% CI: 1.97-23.22), pleuritic chest pain (OR = 3.25, 95% CI: 2.06-5.12), lower limb asymmetry or edema (OR = 2.46, 95% CI:1.51-4.00), higher heart rates (MD = 20.51, 95% CI: 4.95-36.08), longer hospital stays (MD = 3.66, 95% CI: 3.01-4.31) were associated with the PE in the AE-COPD patients. Levels of D-dimer (MD = 1.51, 95% CI: 0.80-2.23), WBC counts (MD = 1.42, 95% CI: 0.14-2.70) were significantly higher and levels of PaO.sub.2 was lower (MD = -17.20, 95% CI: -33.94- -0.45, P<0.05) in the AE-COPD with PE group. The AE-COPD with PE group had increased risk of fatal outcome than the AE-COPD group (OR = 2.23, 95% CI: 1.43-3.50). The prevalence of PE during AE-COPD varies considerably among the studies. AE-COPD patients with PE experienced an increased risk of death, especially among the ICU patients. Understanding the potential risk factors for PE may help clinicians identify AE-COPD patients at increased risk of PE.

Background This study aimed to explore associations and causality between excessive daytime sleepiness (EDS), narcolepsy, and hypertension. Methods Publicly available data from the National Health and Nutrition Examination Survey (NHANES), genome-wide association studies (GWAS), and protein quantitative trait locus (pQTL) data sets were used for analysis. Logistic regression models assessed the association between different frequencies of EDS and hypertension, and sex-stratified subgroup analyses were also performed. Bi-directional Mendelian randomization (MR) evaluated the causal effect of narcolepsy on hypertension. Proteome-wide MR and colocalization analyses were conducted to identify potential protein biomarkers and shared genetic variants. Results EDS with different frequencies is associated with hypertension after adjusting for the covariates (rarely: OR = 1.383, 95% CI 1.013–1.889, P  = 0.041; sometimes: OR = 1.487, 95% CI 1.105–1.999, P  = 0.009; often: OR = 2.041, 95% CI 1.468–2.839, P  < 0.001; almost always: OR = 1.581, 95% CI 1.076–2.323, P  = 0.020). Subgroup analysis suggested that this effect is significant in males. MR analysis revealed a causal association between narcolepsy and hypertension (OR = 1.038, 95% CI 1.006–1.071, P  = 0.019), with no evidence of reverse causality. The protein OLFML3 was causally associated with the increased risk of both narcolepsy (OR = 2.412, 95% CI 1.070–5.436, P  = 0.034) and hypertension (OR = 1.237, 95% CI 1.106–1.384, P  < 0.001) in proteome-wide MR analysis. Conclusions This study provides integrative evidence of a causal relationship between narcolepsy and hypertension, highlighting OLFML3 as a potential biomarker for both conditions.

Wind turbine blades (WTBs) are prone to damage from their working environment, including surface peeling and cracks. Early and effective detection of surface defects on WTBs can avoid complex and costly repairs and serious safety hazards. Traditional object detection methods have disadvantages of insufficient detection capabilities, extended model inference times, low recognition accuracy for small objects, and elongated strip defects within WTB datasets. In light of these challenges, a novel model named DCW-YOLO for surface damage detection of WTBs is proposed in this research, which leverages image data collected by unmanned aerial vehicles (UAVs) and the YOLOv8 algorithm for image analysis. Firstly, Dynamic Separable Convolution (DSConv) is introduced into the C2f module of YOLOv8, allowing the model to more effectively focus on the geometric structural details associated with damage on WTBs. Secondly, the upsampling method is replaced with the content-aware reassembly of features (CARAFE), which significantly minimizes the degradation of image characteristics throughout the upsampling process and boosts the network’s ability to extract features. Finally, the loss function is substituted with the WIoU (Wise-IoU) strategy. This strategy allows for a more accurate regression of the target bounding boxes and helps to improve the reliability in the localization of WTBs damages, especially for low-quality examples. This model demonstrates a notable superiority in surface damage detection of WTBs compared to the original YOLOv8n and has achieved a substantial improvement in the mAP@0.5 metric, rising from 91.4% to 93.8%. Furthermore, in the more rigorous mAP@0.5–0.95 metric, it has also seen an increase from 68.9% to 71.2%.