检索结果-南通市图书馆

A study of real-world micrograph data quality and machine learning model robustness

npj Computational Materials 2021年第1期7卷 1463-1473页

作者： Xiaoting Zhong Brian Gallagher Keenan Eves emily robertson T.Nathan Mundhenk T.Yong-Jin Han Materials Science Division Lawrence Livermore National LaboratoryLivermoreCAUSA Center for Applied Scientific Computing Lawrence Livermore National LaboratoryLivermoreCAUSA Defense Technologies Engineering Division Lawrence Livermore National LaboratoryLivermoreCAUSA Computational Engineering Division Lawrence Livermore National LaboratoryLivermoreCAUSA

Machine-learning(ML)techniques hold the potential of enabling efficient quantitative micrograph analysis,but the robustness of ML models with respect to real-world micrograph quality variations has not been carefully *** collected thousands of scanning electron microscopy(SEM)micrographs for molecular solid materials,in which image pixel intensities vary due to both the microstructure content and microscope instrument *** then built ML models to predict the ultimate compressive strength(UCS)of consolidated molecular solids,by encoding micrographs with different image feature descriptors and training a random forest regressor,and by training an end-to-end deep-learning(DL)*** show that instrument-induced pixel intensity signals can affect ML model predictions in a consistently negative *** a remedy,we explored intensity normalization *** is seen that intensity normalization helps to improve micrograph data quality and ML model robustness,but microscope-induced intensity variations can be difficult to eliminate.

关键词： instrument image eliminate

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Recall of past activity levels in young adults is predictive of adolescent activity levels

引用

Open Journal of Preventive Medicine 2013年第3期3卷 280-284页

作者： Kristi L. Storti emily R. Lawrentz Vincent C. Arena Robert J. robertson Elizabeth F. Nagle Andrea M. Kriska Department of Biostatistics University of Pittsburgh Graduate School of Public Health Pittsburgh USA Department of Epidemiology University of Pittsburgh Graduate School of Public Health Pittsburgh USA Department of Physical Activity and Health University of Pittsburgh Pittsburgh USA

Purpose: To determine whether a global physical activity question (GPAq) administered in young adulthood can be used to accurately rank former physical activity levels (PA) relative to peers of the same age and sex during adolescence. Methods: Data were obtained from the Physical Activity in Young Adults Study, a 10- year follow-up study of 12 - 16 year old adolescents. Five hundred twenty-eight young adults, mean age 24.5 (±1.0) years, completed a GPAq regarding current and past (adolescent) PA. GPAq answers were used to determine whether young adults could accurately rank their past (adolescent) PA levels relative to peers of the same age and sex. GPAq responses were compared with actual self-reported PA levels assessed by the Modifiable Activity Questionnaire for Adolescents (MAQ-A;collected during adolescence). For adolescent PA, an average of 4 years of activity from the MAQ-A 1990-1993, was used. Results: Regardless of gender, Jonckheere-Terpstra tests for trend (p < 0.0001) suggest significant linear trends across categories of PA level for the MAQ-A. Higher perceived PA tracked with greater past PA activity and lower perceived PA tracked with lower past PA activity. Conclusions: Young adults who classified themselves as more active as an adolescent were found to be relatively more active based upon self-reported activity from recall questionnaires collected during that time. These findings suggest that young adults can reasonably estimate relative PA levels during their adolescent years with GPAq. Global physical activity questions may be valid for the assessment and classification of previous PA levels.

关键词： Recall Adolescent Self-Report Modifiable Activity Questionnaire for Adolescents

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：