Prevalence and associated factors of myocardial involvement in Duchenne muscular dystrophy patients in the first decade of life

To the Editor:Duchenne muscular dystrophy(DMD)is a rare X-linked inherited disorder caused by dystrophin deficiency,which results in sarcolemmal fragility and degeneration of skeletal and cardiac myocytes.[1]Cardiac involvement ismanifested asDMDcardiomyopathy,which is the leading cause of disease-related morbidity and mortality among DMD patients.

化工过程预警的CNN-LSTM耦合模型研究

针对化工过程参数的实时性、多维性、非线性,以及化工流程复杂、互相干扰项多、预警方法单一等情况,本工作提出了一种针对化工过程异常工况的深度学习回归预测与ADF(Augmented Dickey-Fuller)检验相耦合的预警模型。在对缩合反应的超温异常工况监测预警分析中,使用卷积神经网络和长短期记忆网络(Convolution Neural Network-Long Short-Term Memory,CNN-LSTM)模型实现了对未来400 s内过程重要参数的预测。同时利用ADF检验,对该时段的重要参数进行趋势检验。当结果为趋势不稳定,并且CNN-LSTM模型预测到某时刻重要参数超过警戒线,再对安全人员发出警报。结果表明,本工作所提出的方法在检测到过程参数不平稳后,分别以模型拟合优度(R^(2))为0.9827和0.9882的情况下提前18和16 s预测到异常工况的发生,从而实现化工过程异常工况的提前预警,对实现化工过程安全运行进行了有利探索。