III: Large: Collaborative Research: Moving Objects Databases for Exploration of Virtual and Real Environments

III：大型：协作研究：用于探索虚拟和现实环境的移动对象数据库

• 批准号: 1823267
• 负责人: Goce Trajcevski
• 金额: $ 10.93万
• 依托单位: Iowa State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-08-16 至 2019-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1823267&HistoricalAwards=false
• 关键词: III; Large; Collaborative; Research; Moving

Researchers at Florida International University (IIS-1213026), University of Illinois at Chicago (IIS-1213013), Brown University (IIS-1212508), and Northwestern University (IIS-1213038) are developing a high-performance model for information processing and fusion in mobile environments, providing a collaborative integration between the real and virtual worlds. This model, applicable to the fields of computational transportation and mobile sensing, enables querying and visualization of moving objects data (MOD) and their relationship to static and dynamic geospatial data. Research project addresses the issues of: balancing the processing of location-based data streams coming into MOD servers with efficient processing of visualization-related queries; determining optimal distribution of queries/tasks among multiple regional servers; maximizing the scalability of prediction techniques in terms of efficient management of objects' data and queries; modeling data uncertainty; coupling map generalization with trajectories' data reduction when zooming across different scales; resolving issues of privacy and security; and enabling semantic querying. A demonstration of the outcomes is available within the TerraFly testbed (http://TerraFly.fiu.edu) -- a public Geographic Information System (GIS) mapping engine and location-based data repository.This work explores the novel steps towards combining the real and virtual worlds, an emerging research frontier. The virtual world is relatively well understood, but the combination of the real and virtual poses great challenges and promises transformative results with high potential payoff, including in-car navigation systems, massive fleets of mobile sensors, self-navigating vehicles, situation command, and location-based services. While advancing Computer Science, the project also leverages prior investment of, and provides direct benefit to, NSF, NASA, DoI, DoT, DHS, and other stakeholders such as the NSF EarthCube project. By improving the efficiency of spatial, temporal, and moving object data management and making these results available to constituencies via TerraFly, EarthCube and other venues, the project will produce societal benefits. This project provides a foundation for improving the quality of services in multiple applications such as disaster management, environmental monitoring, transportation, education, and logistics. The resulting technologies may serve as a base to advance research on self-navigating vehicles, robots, and mobile sensors. In particular, this work facilitates the technologies of Informed Traveler Programs, dynamic navigation, situation control, and airborne observational systems. The project provides rich educational and research opportunities for students from the collaborating institutions -- including underrepresented students. In addition, educational modules are developed, and research results will be incorporated in curriculum expansions. Further information is available at the project's website (http://CAKE.fiu.edu/MOD).

佛罗里达国际大学（IIS-1213026）的研究人员，伊利诺伊大学的芝加哥大学（IIS-1213013），布朗大学（IIS-1212508）和西北大学（IIS-1212508）和西北大学（IIS-1213038）正在开发一个在移动环境中提供信息处理和融合的高度性能模型，以提供一个合作的整合和真实的整合。该模型适用于计算传输和移动传感的领域，可以对移动对象数据（MOD）进行查询和可视化及其与静态和动态的地理空间数据的关系。研究项目解决了以下问题：通过有效处理与可视化相关的查询的有效处理，平衡将基于位置的数据流处理进入MOD服务器的问题；确定多个区域服务器之间查询/任务的最佳分布；根据对象的数据和查询有效管理预测技术的可扩展性；建模数据不确定性；在跨不同尺度放大时，将映射概括与轨迹的数据减少相结合；解决隐私和安全问题；并启用语义查询。在Terrafly TestBED（http://terrafly.fiu.edu）中提供了结果的证明 - 公共地理信息系统（GIS）映射引擎和基于位置的数据存储库。这项工作探讨了结合真实和虚拟世界的新颖步骤，这是一个真正的研究，这是一个新兴的研究。虚拟世界已经相对良好地理解，但是真实和虚拟的结合构成了巨大的挑战，并承诺具有高潜在的回报，包括车内导航系统，大量移动传感器机队，自动化的车辆，情况命令和基于位置的服务。在推进计算机科学的同时，该项目还利用了NSF，NASA，DOI，DOT，DHS和其他利益相关者（例如NSF EarthCube Project）的先前投资，并为NSF，NASA，DOI，DOT，DHS和其他利益提供了直接利益。通过提高空间，时间和移动对象数据管理的效率，并通过Terrafly，EarthCube和其他场所为选区提供这些结果，该项目将产生社会利益。该项目为改善灾难管理，环境监测，运输，教育和物流等多个应用程序的服务质量提供了基础。最终的技术可以作为推进对自动化车辆，机器人和移动传感器的研究的基础。特别是，这项工作促进了知情旅行者计划，动态导航，情况控制和空降观察系统的技术。该项目为合作机构的学生提供了丰富的教育和研究机会，包括代表性不足的学生。此外，开发了教育模块，研究结果将纳入课程扩展中。更多信息可在项目网站（http://cake.fiu.edu/mod）上获得。

项目成果

Information Diffusion Prediction via Recurrent Cascades Convolution

• DOI: 10.1109/icde.2019.00074
• 发表时间: 2019-01-01
• 期刊: 2019 IEEE 35TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2019)
• 作者: Chen, Xueqin;Zhou, Fan;Zhang, Fengli
• 通讯作者: Zhang, Fengli

LaCAVR: Load and Constraints Aware Vehicle Rerouting

LaCAVR：负载和约束感知车辆重新路由

• DOI: 10.1109/mdm.2019.00-32
• 发表时间: 2019
• 作者: Bis, David;Bix, Noah;Gruman, Benjamin;Guenette, Sam;Hauge, Adam;Moser, Hannah;Paul, Jimmy;Trajcevski, Goce
• 通讯作者: Trajcevski, Goce

Adversarial Point-of-Interest Recommendation

• DOI: 10.1145/3308558.3313609
• 发表时间: 2019-05
• 期刊: The World Wide Web Conference
• 作者: Fan Zhou;Ruiyang Yin;Kunpeng Zhang;Goce Trajcevski;Ting Zhong;Jin Wu

Disentangled Network Alignment with Matching Explainability

• DOI: 10.1109/infocom.2019.8737411
• 发表时间: 2019-04
• 期刊: IEEE INFOCOM 2019 - IEEE Conference on Computer Communications
• 作者: Fan Zhou;Zijing Wen;Goce Trajcevski;Kunpeng Zhang;Ting Zhong;Fang Liu

Variational Session-based Recommendation Using Normalizing Flows

• DOI: 10.1145/3308558.3313615
• 发表时间: 2019-05
• 期刊: The World Wide Web Conference
• 作者: Fan Zhou;Zijing Wen;Kunpeng Zhang;Goce Trajcevski;Ting Zhong