检索结果-南通市图书馆

An Approach to Share Architectural Drawing Information and Document Information for Automated Code Checking System

Tsinghua Science and Technology 2008年第S1期13卷 171-178页

作者： jungsik choi Inhan Kim Department of Architectural Engineering Kyung-Hee University College of Architecture and Civil Engineering Kyung-Hee University

The purpose of this study is to suggest a way of optimized managing and sharing information between standard architectural drawings and construction documents in Korea architectural industry for automated code checking system by linked STEP and XML. To archive this purpose, the authors have analyzed current research and technical development for STEP and XML link and developed a prototype system for sharing information between model based drawings and XML based construction documents. Finally, the authors have suggested practical use scenario of sharing information through linked STEP and XML using test case of automatic code checking. In the paper, the possibility of constructing integrated architectural computing environment through exchange and sharing of drawing information and external data for the whole building life-cycle, from the conceptual design stage to the construction and maintenance stage has been examined. Automated code checking through linked STEP and XML could be enhanced through col-laboration business, more completed code, improved building performance, and reduced construction costs.

关键词： STEP XML sharing and exchange architectural drawing information construction document information

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Visualization for Explanation of Deep Learning-Based Defect Detection Model Using Class Activation Map

引用

Computers, Materials & Continua 2023年第6期75卷 4753-4766页

作者： Hyunkyu Shin Yonghan Ahn Mihwa Song Heungbae Gil jungsik choi Sanghyo Lee Center for AI Technology in Construction Hanyang University ERICAAnsan15588Korea School of Architecture and Architectural Engineering Hanyang University ERICAAnsan15588Korea ICT Convergence Research Division Korea Expressway Corporation Research InstituteHwaseong18489Korea Department of Architecture College of EngineeringKangwon National UniversitySamcheok25913Korea Division of Smart Convergence Engineering Hanyang University ERICAAnsan15588Korea

Recently,convolutional neural network(CNN)-based visual inspec-tion has been developed to detect defects on building surfaces *** CNN model demonstrates remarkable accuracy in image data analysis;however,the predicted results have uncertainty in providing accurate informa-tion to users because of the“black box”problem in the deep learning ***,this study proposes a visual explanation method to overcome the uncertainty limitation of CNN-based defect *** visual repre-sentative gradient-weights class activation mapping(Grad-CAM)method is adopted to provide visually explainable information.A visualizing evaluation index is proposed to quantitatively analyze visual representations;this index reflects a rough estimate of the concordance rate between the visualized heat map and intended *** addition,an ablation study,adopting three-branch combinations with the VGG16,is implemented to identify perfor-mance variations by visualizing predicted *** reveal that the proposed model,combined with hybrid pooling,batch normalization,and multi-attention modules,achieves the best performance with an accuracy of 97.77%,corresponding to an improvement of 2.49%compared with the baseline ***,this study demonstrates that reliable results from an automatic defect classification model can be provided to an inspector through the visual representation of the predicted results using CNN models.

关键词： Defect detection visualization class activation map deep learning explanation visualizing evaluation index

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：