Catalyst Project: Indoor Moving Objects Trajectory Generation and Query Evaluation

Catalyst项目为历史上的黑人学院和大学提供支持，以建立教师的研究能力，加强科学、技术、工程和数学本科教育和研究。预计该奖项将进一步提高教师的研究能力，提高学院的研究和教学水平，并让本科生参与研究经验。塔斯基吉大学的这个项目旨在开发一个基于室内数据的跟踪框架，旨在了解室内数据管理的数学和技术基础。该计划为本科生提供了一个机会，通过研究计算机建模和数据管理技术来提高他们的教育水平。该研究人员与奥本大学的教职员工建立了强有力的合作关系。该项目将导致许多室内查询评估机制和技术的发展，以从原始错误的室内跟踪数据中获得室内移动物品的准确位置。这将提高室内空间查询的准确性，从而支持许多室内高级应用，包括室内基于位置的服务和热点查找。设计新颖的室内跟踪数据管理技术。该项目的目标是：1)实现仿真工具包和原型系统，其中将模拟许多室内环境和部署设置以进行性能评估；2)开发和比较一些基于机器学习的位置推理方法，以在室内环境中精确生成轨迹；3)针对不同类型的查询，特别是距离查询和最近邻查询等空间查询类型，设计新颖的室内查询评估算法；4)发明了一种基于误差模型的室内目标轨迹跟踪方法，这是一种非机器学习方法。研究结果将提高室内定位应用的性能，在紧急情况下可以方便地定位人员并引导人们到安全的地方。该奖项反映了美国国家科学基金会的法定使命，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。

Catalyst Projects provide support for Historically Black Colleges and Universities to work towards establishing research capacity of faculty to strengthen science, technology, engineering and mathematics undergraduate education and research. It is expected that the award will further the faculty member's research capability, improve research and teaching at the institution, and involve undergraduate students in research experiences. This project at Tuskegee University seeks to develop an indoor data-based tracking framework designed to understand the mathematical and technological foundations of indoor data management. The project provides an opportunity for undergraduate students to enhance their education through research experiences in computer modeling and data management techniques. The researcher has established a strong collaboration with faculty at Auburn University. This project will result in the development of a number of indoor query evaluation mechanisms and the techniques to derive the accurate locations of indoor moving items from raw erroneous indoor tracking data. This will improve the accuracy of indoor spatial queries, which can support many indoor high-level applications, including indoor location-based service and hotspot finding. Novel indoor tracking data management techniques will be devised. The goals of the project are to: 1) implement a simulation toolkit and a prototype system, where many indoor environments and deployment settings will be simulated for performance evaluation; 2) develop and compare a number of machine learning-based location inference methods for accurate trajectory generation in indoor environments; 3) design novel indoor query evaluation algorithms for various types of queries, in particular spatial query types such as range query and nearest neighbor query; and 4) invent an error model-based approach for indoor object trajectory tracking which is a non-machine learning approach. The results of this research will improve the performance of number of indoor location-based application which will make it easy to locate people and help to guide people to safety during emergency situations.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.