RAPID: Big Geospatial Data for Decision Support in Ebola Triage

提案#：15-07611PI(S)：Rishe，Naphtali研究所：佛罗里达国际大学标题：RAPID：用于埃博拉分流项目决策支持的大地理空间数据建议：该项目旨在制定一种方法，用于在与确定埃博拉疑似病例有关的分流和热线行动中利用地理空间数据提供决策支持，旨在进一步在TerraFly仪器(目前由美国国家科学基金会资助)的基础上开发一个原型模块。该原型是一个决策支持应用程序，向响应热线电话和患者遇到分诊的操作员提供数据混搭。此外，这项工作还利用了模糊逻辑方面的工作来预测流行病。此外，与密歇根大学生物医学中心合作，金融情报院的研究人员将：-通过对推特帖子中的引用进行地理定位来识别埃博拉病毒的位置，利用金融情报院S正在申请专利的社交媒体地理定位技术，-生成近乎实时的危机地图，展示埃博拉病毒现有数据的传播，并评估其对目前参与缓解的利益相关者的效用，-将从社交媒体数据流派生的地图与疾控中心地图进行比较。更广泛的影响：这项工作与FAU、UMBC和UMN的联盟成员协调并与各自的快速提案并行提交，旨在共同解决具有国家和全球意义的公共卫生问题。特别是，提倡者将与FAU合作，通过使用创新的大数据分析技术对埃博拉传播进行建模，并与UMBC合作，将Twitter上的可量化社交媒体数据整合到我们的数据混搭中。除了目前的埃博拉问题，拟议的方法和联盟建设努力的目的是支持一系列公共卫生问题的解决方案。

Proposal #: 15-07611PI(s): Rishe, NaphtaliInstitution: Florida International University Title: RAPID: Big Geospatial Data for Decision Support in Ebola Triage Project Proposed:This project, developing a methodology for utilization of geospatial data for decision support in triage and hotline operations related to identification of suspected cases of Ebola aims to further, develop a prototype module, on the base of the TerraFly instrument (presently funded by NSF). The prototype, a decision support application, presents data mashup to operators responding to hotline calls and patient encounter triage. Additionally, the effort leverages work on Fuzzy Logic for epidemics prediction. Furthermore, in collaboration with UMBC, FIU researchers will:- Identify locations of Ebola by geolocating references in Twitter Posts, utilizing the FIU?s patent-pending technology of geolocating social media,- Generate near real time Crisis maps demonstrating the spread of Ebola available data and assess their utility to stakeholders presently involved in mitigation,- Compare maps derived from social media data streams to CDC maps. Broader Impacts:This work, coordinated with and submitted in parallel with respective RAPID proposals, with coalition members at FAU, UMBC, and UMN, aims to jointly address public health problems of national and global significance. In particular the proposers will work with FAU on modeling Ebola spread through use of innovative big data analytics techniques and with UMBC on integrating quantifiable social media data from Twitter into our data mashups. Beyond the present issue of Ebola, the proposed methodology and the coalition-building effort aims to support solutions in a wide range of public health issues.