Expeditions: Collaborative Research: Global Pervasive Computational Epidemiology

探险：合作研究：全球普适计算流行病学

• 批准号: 2151597
• 负责人: Judy Fox
• 金额: $ 37.5万
• 依托单位: University of Virginia Main Campus
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-11-01 至 2025-04-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2151597&HistoricalAwards=false
• 关键词: Expeditions; Collaborative; Research; Global; Pervasive

Infectious diseases cause more than 13 million deaths per year worldwide. Rapid growth in human population and its ability to adapt to a variety of environmental conditions has resulted in unprecedented levels of interaction between humans and other species. This rise in interaction combined with emerging trends in globalization, anti-microbial resistance, urbanization, climate change, and ecological pressures has increased the risk of a global pandemic. Computation and data sciences can capture the complexities underlying these disease determinants and revolutionize real-time epidemiology --- leading to fundamentally new ways to reduce the global burden of infectious diseases that has plagued humanity for thousands of years. This Expeditions project will enable novel implementations of global infectious disease computational epidemiology by advancing computational foundations, engineering principles, theoretical understanding, and novel technologies. The innovative tools developed will provide new analytical capabilities to decision makers and result in improved science-based decision making for epidemic planning and response. They will facilitate enhanced inter-agency and inter-government coordination and outbreak response. The team will work closely with many local, regional, national, and international public health agencies and universities to apply and deploy powerful technologies during epidemic outbreaks that can be expected to occur during the course of the project. International scientific networks linked to a comprehensive postdoctoral, graduate and undergraduate student training program will be established. Educational programs to foster interest in and increase understanding of computational science in addressing the complex societal challenges due to pandemics will also be developed. The team, with partners in Asia, Africa, Europe, and Latin America, will produce multidisciplinary scientists with diverse skills related to public health. The novel implementations of this project will be enabled by the development of a rigorous computational theory of spreading and control processes on dynamic multi-scale, multi-layer (MSML) networks, along with tools from AI, machine learning, and social sciences. New techniques resulting from this research will make it possible to develop and apply large-scale simulations of epidemics and social interactions over MSML networks. These simulations, in turn, will provide fundamentally new insights into how to control epidemics. Pervasive computing technologies will be developed to support disease surveillance and real-time response. The computational advances will also be generalizable; that is, they will be applicable to other areas such as cybersecurity, ecology, economics and social sciences. The project will take into account emerging concerns and constraints that include: preserving privacy of individuals and vulnerable groups, enabling model predictions to be interpreted and explained, developing effective interventions under uncertain and unknown network data, understanding strategic and adversarial behaviors of individual agents, and ensuring fairness of the process across the entire population. The research team includes experts from multiple disciplines and will address these societal concerns and constraints in practical, impactful, and novel ways, including the development of computational tools and techniques to support sound, ethical science-based policy pertaining to public health infectious disease epidemiology. Center for Computational Research in Epidemiology (CoRE) at the University of Virginia will be established as a part of the project. CoRE will develop transformative ways to support real-time epidemiology and facilitate improved outbreak response to benefit the society.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.

传染病每年在全世界造成1 300多万人死亡。人类人口的快速增长及其适应各种环境条件的能力导致了人类与其他物种之间前所未有的相互作用。这种相互作用的增加，加上全球化、抗微生物耐药性、城市化、气候变化和生态压力的新趋势，增加了全球大流行的风险。计算和数据科学可以捕捉这些疾病决定因素背后的复杂性，并彻底改变实时流行病学，从而从根本上找到新的方法来减轻困扰人类数千年的传染病的全球负担。该远征项目将通过推进计算基础，工程原理，理论理解和新技术，实现全球传染病计算流行病学的新实现。所开发的创新工具将为决策者提供新的分析能力，并改进流行病规划和应对方面的科学决策。它们将促进加强机构间和政府间的协调和疫情应对。该团队将与许多地方、区域、国家和国际公共卫生机构和大学密切合作，在项目期间可能发生的流行病爆发期间应用和部署强大的技术。将建立与综合博士后、研究生和本科生培训计划相联系的国际科学网络。还将制定教育计划，以培养对计算科学的兴趣并增加对计算科学的理解，以应对流行病带来的复杂社会挑战。该团队与亚洲、非洲、欧洲和拉丁美洲的合作伙伴一起，将培养具有公共卫生相关技能的多学科科学家。 该项目的新实现将通过开发动态多尺度多层（MSML）网络上传播和控制过程的严格计算理论沿着人工智能，机器学习和社会科学的工具来实现。这项研究产生的新技术将使开发和应用MSML网络上流行病和社会互动的大规模模拟成为可能。反过来，这些模拟将为如何控制流行病提供全新的见解。将开发普及计算技术，以支持疾病监测和实时反应。 计算技术的进步也将是可推广的;也就是说，它们将适用于网络安全、生态、经济和社会科学等其他领域。该项目将考虑到新出现的问题和限制，包括：保护个人和弱势群体的隐私，使模型预测能够被解释和解释，在不确定和未知的网络数据下制定有效的干预措施，了解个体代理的战略和对抗行为，并确保整个人口的公平性。该研究团队包括来自多个学科的专家，并将以实用，有效和新颖的方式解决这些社会问题和限制，包括开发计算工具和技术，以支持与公共卫生传染病流行病学有关的合理，基于伦理科学的政策。弗吉尼亚大学的流行病学计算研究中心（Center for Computational Research in Epidemiology，CoRE）将作为该项目的一部分建立。该奖项反映了NSF的法定使命，并通过使用基金会的知识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

Rank Position Forecasting in Car Racing

• DOI: 10.1109/ipdps49936.2021.00082
• 发表时间: 2020-10
• 期刊: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS)
• 作者: Bo Peng;Jiayu Li;Selahattin Akkas;Fugang Wang;Takuya Araki;Ohno Yoshiyuki;J. Qiu

Twister2 Cross‐platform resource scheduler for big data

Twister2 大数据跨平台资源调度器

• DOI: 10.1002/cpe.6502
• 发表时间: 2021
• 期刊: Concurrency and Computation: Practice and Experience
• 作者: Uyar, Ahmet;Gunduz, Gurhan;Kamburugamuve, Supun;Wickramasinghe, Pulasthi;Widanage, Chathura;Govindarajan, Kannan;Perera, Niranda;Abeykoon, Vibhatha;Akkas, Selahattin;Fox, Geoffrey
• 通讯作者: Fox, Geoffrey

Opportunities for enhancing MLCommons efforts while leveraging insights from educational MLCommons earthquake benchmarks efforts

加强 MLCommons 工作的机会，同时利用教育 MLCommons 地震基准工作的见解

• DOI: 10.3389/fhpcp.2023.1233877
• 发表时间: 2023
• 期刊: Frontiers in High Performance Computing
• 作者: von Laszewski, Gregor;Fleischer, J. P.;Knuuti, Robert;Fox, Geoffrey C.;Kolessar, Jake;Butler, Thomas S.;Fox, Judy
• 通讯作者: Fox, Judy

Interpreting County-Level COVID-19 Infections using Transformer and Deep Learning Time Series Models

使用 Transformer 和深度学习时间序列模型解释县级 COVID-19 感染

• DOI: 10.1109/icdh60066.2023.00046
• 发表时间: 2023
• 期刊: IEEE
• 作者: Islam, Md Khairul;Liu, Yingzheng;Erkelens, Andrej;Daniello, Nick;Marathe, Aparna;Fox, Judy
• 通讯作者: Fox, Judy

High Performance Data Engineering Everywhere

• DOI: 10.1109/smds49396.2020.00022
• 发表时间: 2020-07
• 期刊: 2020 IEEE International Conference on Smart Data Services (SMDS)
• 作者: Chathura Widanage;Niranda Perera;V. Abeykoon;Supun Kamburugamuve;Thejaka Amila Kanewala;Hasara Maithree;P. Wickramasinghe;A. Uyar;Gurhan Gunduz;G. Fox