期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
基于神经网络的裂纹扩展过程预测 被引量:2
1
作者 郑国君 杜超群 +1 位作者 申国哲 夏阳 《计算机辅助工程》 2021年第4期32-40,共9页
提出基于神经网络的裂纹扩展过程实时预测方法,其计算效率比近场动力学(peridynamic,PD)模型提高。使用PD算法获取裂纹扩展过程中的损伤云图,构建裂纹扩展数据集。基于数据集构建生成对抗网络(generative adversarial networks,GAN)模型... 提出基于神经网络的裂纹扩展过程实时预测方法,其计算效率比近场动力学(peridynamic,PD)模型提高。使用PD算法获取裂纹扩展过程中的损伤云图,构建裂纹扩展数据集。基于数据集构建生成对抗网络(generative adversarial networks,GAN)模型,根据不同加载条件实时生成损伤云图,从而快速预测裂纹的扩展过程。将PD模型计算得到的损伤云图中的RGB值与相应位置处的损伤值结合,构建多层前馈神经网络模型的数据库,并使用多层前馈神经网络模型分析GAN模型产生的损伤云图,得到相应的损伤值。通过数值算例证明该方法的效率和准确性。 展开更多
关键词 近场动力学 计算时间 生成对抗网络 裂纹扩展 裂纹预测 损伤云图 前馈神经网络 损伤值预测
下载PDF
Cerebral state index versus Glasgow coma scale as a predictor for in-hospital mortality in brain-injured patients 被引量:3
2
作者 Mehrdad Mahdian Mohammad Reza Fazel +2 位作者 Esmaeil Fakharian Hossein Akbari Soroush Mahdian 《Chinese Journal of Traumatology》 CAS CSCD 2014年第4期220-224,共5页
Objective:To compare the value of Glasgow coma scale (GCS) and cerebral state index (CSI)on predicting hospital discharge status of acute braininjured patients.Methods:In 60 brain-injured patients who did not re... Objective:To compare the value of Glasgow coma scale (GCS) and cerebral state index (CSI)on predicting hospital discharge status of acute braininjured patients.Methods:In 60 brain-injured patients who did not receive sedatives,GCS and CSI were measured daily during the first 10 days of hospitalization.The outcome of prognostic cut-off points was calculated by GCS and CSI using receiver operating characteristic (ROC) curve regarding the time of admission and third day of hospitalization.Sensitivity,specificity and other predictive values for both indices were calculated.Results:Of the 60 assessed patients,14 patients had mild,13 patients had moderate and 33 patients had severe injuries.During the course of the study,17 patients (28.3%) deteriorated in their situation and died.The mean GCS and CSI in patients who deceased during hospitalization was significantly lower than those who were discharged from the hospital.GCS<4.5 and CSI<64.5 at the time of admission was associated with higher mortality risk in traumatic brain injury patients and GCS was more sensitive than CSI to predict in-hospital death in these patients.For the first day of hospitalization,the area under ROC curve was 0.947 for GCS and 0.732 for CSI.Conclusion:GCS score at ICU admission is a good predictor of in-hospital mortality.GCS<4.5 and CSI<64.5 at the time of admission is associated with higher mortality risk in traumatic brain injury patients and GCS is more sensitive than CSI in predicting death in these patients. 展开更多
关键词 Brain injuries Glasgow coma scale Outcome assessment
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部