RAPID: AI- and Data-driven Integrated Framework for Hierarchical Community-level Risk Assessment

RAPID：人工智能和数据驱动的分层社区级风险评估集成框架

• 批准号: 2027127
• 负责人: Yanfang Ye
• 金额: $ 8.4万
• 依托单位: Case Western Reserve University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-05-01 至 2022-04-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2027127&HistoricalAwards=false
• 关键词: RAPID; AI; Data; driven; Integrated

The fast evolving and deadly outbreak of coronavirus disease (COVID-19) has created one of the most challenging issues facing global public health. According to the Centers for Disease Control and Prevention (CDC), before a vaccine or drug becomes widely available, community mitigation, which is a set of actions that persons and communities can take to help slow the spread of respiratory virus infections, is the most readily available interventions to help slow transmission of the virus in communities. A growing number of areas are reporting community transmission of the virus, which would represent a significant turn for the worse in the battle against the novel coronavirus; this points to an urgent need for expanded surveillance so we can better understand the spread of COVID-19 and better respond with actionable strategies for community mitigation. By advancing capabilities of artificial intelligence (AI) and leveraging the large-scale and real-time data generated from heterogeneous sources, the goal of this project is to design and develop an AI- and data-driven integrated framework to provide real-time hierarchical community-level risk assessment to help combat the COVID-19 pandemic.The research will have three main parts. First, the research team will construct a novel heterogeneous graph architecture to comprehensively model the large-scale and real-time pandemic related data collected from multiple sources. Second, the team will develop conditional generative adversarial nets for graph enrichment to address the challenge of limited data that might be available for learning. Third, the team will develop algorithms to model potential community transmission routes and design an innovative heterogeneous graph auto-encoder model for hierarchical community-level risk assessment. Through the potential community transmission route modeling, the developed framework will facilitate a predictive understanding of the spread of the virus; by providing the dynamic and real-time COVID-19 risk assessment, the planned work will enable the general public to select appropriate actions for protection while minimizing disruptions to daily life to the extent possible (i.e., mitigate the negative effects of COVID-19 on public health, society, and the economy). The planned research will benefit intelligent information management where multiple data sources are involved and secure and trustworthy cyberspace with applications such as malware detection and mitigation. The project integrates research with education through curriculum development, the participation of underrepresented groups, and student mentoring activities.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.

冠状病毒病（COVID-19）的快速演变和致命爆发已成为全球公共卫生面临的最具挑战性的问题之一。根据疾病控制和预防中心（CDC）的说法，在疫苗或药物广泛使用之前，社区缓解是个人和社区可以采取的一系列行动，以帮助减缓呼吸道病毒感染的传播，是帮助减缓病毒在社区传播的最现成的干预措施。越来越多的地区报告了该病毒的社区传播，这将意味着对抗新型冠状病毒的斗争出现重大恶化;这表明迫切需要扩大监测，以便我们能够更好地了解COVID-19的传播，并更好地采取可行的社区缓解策略。该项目的目标是通过提升人工智能（AI）的能力，并利用从不同来源产生的大规模和实时数据，设计和开发一个AI和数据驱动的集成框架，以提供实时分层社区层面的风险评估，以帮助抗击COVID-19大流行。该研究将分为三个主要部分。首先，研究团队将构建一个新颖的异构图架构，以全面建模从多个来源收集的大规模和实时流行病相关数据。其次，该团队将开发用于图形丰富的条件生成对抗网络，以解决可能用于学习的有限数据的挑战。第三，该团队将开发算法来模拟潜在的社区传播路线，并设计一个创新的异构图形自动编码器模型，用于分层社区级风险评估。通过潜在的社区传播途径建模，已开发的框架将有助于对病毒传播的预测性了解;通过提供动态和实时的COVID-19风险评估，计划中的工作将使公众能够选择适当的保护行动，同时尽可能减少对日常生活的干扰（即，减轻COVID-19对公共卫生、社会和经济的负面影响）。计划中的研究将有利于涉及多个数据源的智能信息管理，以及通过恶意软件检测和缓解等应用程序保护和可靠的网络空间。该项目通过课程开发、代表性不足群体的参与和学生辅导活动将研究与教育结合起来。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

Joint Demosaicing and Super-Resolution (JDSR): Network Design and Perceptual Optimization

• DOI: 10.1109/tci.2020.2999819
• 发表时间: 2019-11
• 期刊: IEEE Transactions on Computational Imaging
• 影响因子: 5.4
• 作者: Xuan Xu;Yanfang Ye;Xin Li

Detection of Illicit Drug Trafficking Events on Instagram: A Deep Multimodal Multilabel Learning Approach

• DOI: 10.1145/3459637.3481908
• 发表时间: 2021-08
• 期刊: Proceedings of the 30th ACM International Conference on Information & Knowledge Management
• 作者: Chuanbo Hu;Minglei Yin;Bing Liu;Xin Li;Yanfang Ye

RxNet: Rx-refill Graph Neural Network for Overprescribing Detection

• DOI: 10.1145/3459637.3482465
• 发表时间: 2021-10
• 期刊: Proceedings of the 30th ACM International Conference on Information & Knowledge Management
• 作者: Jianfei Zhang;Ai-Te Kuo;Jianan Zhao;Qianlong Wen;E. Winstanley;Chuxu Zhang;Yanfang Ye

Heterogeneous Graph Structure Learning for Graph Neural Networks

• DOI: 10.1609/aaai.v35i5.16600
• 发表时间: 2021-05
• 作者: Jianan Zhao;Xiao Wang;C. Shi;Binbin Hu;Guojie Song;Yanfang Ye

WebEvo: taming web application evolution via detecting semantic structure changes

• DOI: 10.1145/3460319.3464800
• 发表时间: 2021-07
• 期刊: Proceedings of the 30th ACM SIGSOFT International Symposium on Software Testing and Analysis
• 作者: Fei Shao;Ruiwen Xu;W. Haque;Jingwei Xu;Ying Zhang;Wei Yang;Yanfang Ye;Xusheng Xiao