改进CNN的风力机叶片故障诊断方法

针对图像分辨率低的风力机叶片图像会导致故障诊断过程中精度和速度降低等问题,提出了一种基于小波变换、深度可分离卷积和卷积块注意力机制模块的轻量级改进VGG-19模型;使用DB4小波和基于形态学的增强技术来提高风力机叶片图像的质量,然后将VGG-19中的传统卷积层替换为深度可分离卷积层,以减少网络参数的数量并提高训练效率,最后引入卷积注意力机制模块(Convolutional Block Attention Module, CBAM)来提高风力机叶片故障诊断的准确性;研究结果表明:所提模型的准确率为93.91%,与其他传统卷积神经网络(Convolutional Neural Networks,CNN)模型LeNet、AlexNet、GoogleNet、ResNet-50和VGG-19相比分别提高了15.06%、8.57%、3.10%、-1.13%和7.13%;测试时间为每幅图像0.046秒,较传统CNN模型每幅图像分别减少了-0.004秒、-0.002秒、0.006秒、0.015秒和0.010秒的检测时间;该模型结构轻巧,相比于其他传统CNN具有更高的准确性和更快的检测速度。

Artificial intelligence promotes shared decision-making through recommending tests to febrile pediatric outpatients

BACKGROUND:To promote the shared decision-making(SDM)between patients and doctors in pediatric outpatient departments,this study was designed to validate artificial intelligence(AI)-initiated medical tests for children with fever.METHODS:We designed an AI model,named Xiaoyi,to suggest necessary tests for a febrile child before visiting a pediatric outpatient clinic.We calculated the sensitivity,specificity,and F1 score to evaluate the efficacy of Xiaoyi’s recommendations.The patients were divided into the rejection and acceptance groups.Then we analyzed the rejected examination items in order to obtain the corresponding reasons.RESULTS:We recruited a total of 11,867 children with fever who had used Xiaoyi in outpatient clinics.The recommended examinations given by Xiaoyi for 10,636(89.6%)patients were qualified.The average F1 score reached 0.94.A total of 58.4%of the patients accepted Xiaoyi’s suggestions(acceptance group),and 41.6%refused(rejection group).Imaging examinations were rejected by most patients(46.7%).The tests being time-consuming were rejected by 2,133 patients(43.2%),including rejecting pathogen studies in 1,347 patients(68.5%)and image studies in 732 patients(31.8%).The difficulty of sampling was the main reason for rejecting routine tests(41.9%).CONCLUSION:Our model has high accuracy and acceptability in recommending medical tests to febrile pediatric patients,and is worth promoting in facilitating SDM.

Normal values of shear wave velocity in liver tissue of healthy children measured using the latest acoustic radiation force impulse technology

BACKGROUND Several studies have demonstrated the feasibility and effectiveness of using ultrasound elastography to assess liver tissue stiffness.Virtual touch imaging quantification(VTIQ)based on acoustic radiation force impulse imaging has been developed as a latest and noninvasive method for assessing liver stiffness in children.AIM To determine the standard value in healthy children,and to identify possible factors that might influence the VTIQ measurement.METHODS With the ethical approval,202 children between 1 month and 15 years old were included in this study.None of them had any liver or systematic diseases.All children had a normal ultrasound scan and normal body mass index(BMI)range.The subjects were divided into four age and BMI groups.The effects of gender,age,liver lobe,measurement depth,and BMI on liver elasticity were investigated.RESULTS A significant correlation was found between age and shear wave velocity(SWV)value.At measurement depths of 1.5 cm and 2.0 cm in the left lobe,there were significant differences among the age groups.SWV values were significantly negatively correlated with the measurement depth.Gender,liver lobe,and BMI showed no significant effect on the SWV values.Age and BMI may influence the quality of the elastogram.CONCLUSION VTIQ is a noninvasive technique that is feasible to measure liver stiffness in children.The afore-mentioned velocity value obtained utilizing VTIQ method could be used as reference value for normal liver stiffness in children.

Exploring atmospheric environmental drivers of asthma among children in Shanghai, China: Evidence-informed policies are required

It is important to identify atmospheric environmental drivers of childhood asthma because asthma is the most common chronic disease in children globally.We provided an overview of the impacts of exposure to atmospheric environmental factors(e.g.,meteorological factors and air pollutants)on childhood asthma,based on a series of studies with the cutting-edge environmental epidemiological methodology in Shanghai,China.Overall,we found that the prevalence of asthma among the children aged 3–7 years had increased by approximately 7 fold,from 2.1%in 1990 to 14.6%in 2019.Most meteorological factors(i.e.daily mean temperature,temperature difference,air pressure,air pressure difference,precipitation,relative humidity,sunshine and wind speed)and air pollutants(PM10,PM2.5,NO2,SO2 and O3)were significantly associated with childhood asthma(p<0.05),but meteorological factors appeared to play more important roles than air pollutants in the occurrence of asthma exacerbations.We also found that temperature variability was significantly associated with the elevated relative risk of daily outpatient visits for childhood asthma(p<0.05).Furthermore,we conducted a systematic review on climate change adaptation measures and childhood asthma and found that there were a number of adaptation measures proposed for childhood asthma in response to climate change,including vulnerability assessment,improving ventilation and heating,enhancing community education,developing forecast models,and early warning systems.However,the effectiveness of most adaptation measures,except for improving ventilation and heating in winter,have not been explored and quantified.Since asthma is sensitive to the variation of atmospheric environmental conditions,it is critical to develop and implement appropriate climate change mitigation and adaptation strategies as global heating becomes apparent.

Increasing prevalence and influencing factors of childhood asthma: a cross-sectional study in Shanghai, China

Background Asthma has been a global problem,especially in children.We aim to evaluate the contemporary prevalence and influencing factors of asthma among children aged 3–7 years in Shanghai,China.Methods A random sample of preschool children was included in this study.The International Study of Asthma and Allergies in Childhood questionnaire was adopted to assess the childhood asthma.Multivariable logistic regression models were used to evaluate the associations between independent variables and childhood asthma.Results Of 6389 preschool children who were invited to take part in this study,6163(response rate:96.5%)completed the questionnaire and were included in the analysis.The overall prevalence of asthma was 14.6%which increased more than six folds from 2.1%in 1990.Being male,younger age,preterm delivery,being born in spring or autumn,being delivered by elective cesarean section without indication,miscarriage,high socioeconomic status,having allergy history,and exposure to passive smoking,latex paint,and dust were potential risk factors for childhood asthma.Spending more time outdoors(>30 min/day),having indoor plants,and cleaning rooms more frequently were potential protective factors.Conclusions The prevalence of childhood asthma in Shanghai has increased dramatically during the past three decades.The findings about risk and protective factors of childhood asthma could be used to develop appropriate strategies to prevent and control childhood asthma in Shanghai and in other similar metropolitan cities.