Elements: Data: Integrating Human and Machine for Post-Disaster Visual Data Analytics: A Modern Media-Oriented Approach

要素：数据：整合人机进行灾后可视化数据分析：现代媒体导向方法

• 批准号: 1835473
• 负责人: Shirley Dyke
• 金额: $ 59.8万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-01-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1835473&HistoricalAwards=false
• 关键词: Elements; Data; Integrating; Human; Machine

This project creates a science-oriented visual data service that facilitates the query of datasets based on visual content. The approach allows a user to search for data based on visual similarity, even in cases where a term for the failure or observation does not yet have a scientific name. The visual analysis data and application services will be deployed on a cloud-based platform. The results will produce a framework enabling access to and analysis of a large amount of imagery from diverse sources. The research team creates VISER (Visual Structural Expertise Replicator), which will serve as a comprehensive cloud-based data analytics service and will facilitate the use of and integrate data and applications most needed by the user. The framework will implement two novel concepts: data-as-a-service and applications-as-a-service, which will bring data and applications to the user without the need to configure software systems or packages. The approach also employs artificial intelligence to interpret the contents of the images. VISER will use convolutional neural networks (CNNs) to train custom classifiers for new categories. Three applications will be developed and deployed within VISER: App1 will extract relevant visual context, App2 will facilitate similarity-based visual searching (through the use of a Siamese CNN), and App3 will help perform automatic extraction of pre-event/pre-disaster images based on Google Street View. The application of these tools would advance both the science of automated pattern recognition and of more effective construction techniques.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目创建了一个面向科学的视觉数据服务，方便基于视觉内容的数据集查询。该方法允许用户基于视觉相似性搜索数据，即使在失败或观察的术语尚未有科学名称的情况下也是如此。 可视化分析数据和应用服务将部署在基于云的平台上。 研究结果将产生一个框架，能够访问和分析来自不同来源的大量图像。 研究团队创建了 VISER（视觉结构专业知识复制器），它将作为基于云的综合数据分析服务，并将促进用户最需要的数据和应用程序的使用和集成。 该框架将实现两个新颖的概念：数据即服务和应用程序即服务，这将为用户带来数据和应用程序，而无需配置软件系统或软件包。 该方法还采用人工智能来解释图像的内容。 VISER 将使用卷积神经网络 (CNN) 来训练新类别的自定义分类器。 将在 VISER 中开发和部署三个应用程序：App1 将提取相关的视觉上下文，App2 将促进基于相似性的视觉搜索（通过使用 Siamese CNN），App3 将帮助执行事件前/灾难前的自动提取基于谷歌街景的图像。 这些工具的应用将推进自动模式识别科学和更有效的施工技术。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Automated Indoor Image Localization to Support a Post-Event Building Assessment

自动室内图像定位支持活动后建筑评估

• DOI: 10.3390/s20061610
• 发表时间: 2020-03-01
• 期刊: Sensors (Basel, Switzerland)
• 作者: Xiaoyu Liu;S. Dyke;C. Yeum;Ilias Bilionis;A. Lenjani;Jongseong Choi
• 通讯作者: Jongseong Choi

Towards rapid and automated vulnerability classification of concrete buildings

实现混凝土建筑的快速、自动化脆弱性分类

• DOI: 10.1007/s11803-023-2171-2
• 发表时间: 2023-04-25
• 期刊: Earthquake Engineering and Engineering Vibration
• 影响因子: 2.8
• 作者: Lissette Iturburu;Jean Kwann;ar;ar;S. Dyke;Xiaoyu Liu;Xin Zhang;J. Ramirez
• 通讯作者: J. Ramirez

EL2W: Extended Layer 2 Services for Bare-Metal Provisioning Over WAN

EL2W：通过 WAN 进行裸机配置的扩展第 2 层服务

• DOI: 10.1109/cloudsummit57601.2023.00017
• 发表时间: 2023-07
• 期刊: 2023 IEEE Cloud Summit
• 作者: Hacker, Thomas J.;Kaushal, Deepika;Chu, Zhiwei
• 通讯作者: Chu, Zhiwei

Similarity learning to enable building searches in post‐event image data

相似性学习可在事件后图像数据中构建搜索

• DOI: 10.1111/mice.12698
• 发表时间: 2021-04
• 期刊: Computer-Aided Civil and Infrastructure Engineering
• 影响因子: 9.6
• 作者: Choi, Jongseong;Park, Ju An;Dyke, Shirley J.;Yeum, Chul Min;Liu, Xiaoyu;Lenjani, Ali;Bilionis, Ilias
• 通讯作者: Bilionis, Ilias

Multioutput Image Classification to Support Postearthquake Reconnaissance

支持震后勘察的多输出图像分类

• DOI: 10.1061/(asce)cf.1943-5509.0001755
• 发表时间: 2022-12-01
• 期刊: Journal of Performance of Constructed Facilities
• 影响因子: 2.5
• 作者: Ju An Park;Xiaoyu Liu;C. Yeum;S. Dyke;Max Midwinter;Jongseong Choi;Zhiwei Chu;T. Hacker;Bedrich Benes
• 通讯作者: Bedrich Benes