CISE Research Infrastructure: Systems Science for Physical Geometric Algorithms

物理几何算法研究(PGA)研究物理几何算法(PGA)研究物理世界中几何或空间关系的计算过程及其在各种应用领域中的实现。这些领域包括机器人、微电子机械系统(MEMS)、计算生物学、科学和图像处理、图像分析和系统仿真。总的来说，这些技术承担了与处理与物理系统模型相关的海量数据相关的问题。PGA的研究追求的命题是，对于这样的系统，行为的预测、正确性的论证和组合精度都退化为几何分析。在有趣的规模上，这些区域具有对网络、远程数据库、局域网集群、磁盘场(本地和远程)、并行处理和图形的共同利用。该项目将开发新的系统科学技术(特别是算法、分析、建模技术和方法)，以解决这些应用程序的延迟、带宽、安全、可伸缩性、调度、访问时间变化和并行高性能计算。这项拨款提供的设备使我们的应用程序研究小组和系统研究小组能够协同开发这些关键性能问题的通用系统解决方案，并在应用程序和系统问题领域设定新的方向。

EIA-9802068Nicol, David M. Dartmouth CollegeCISE Research Infrastructure: Systems Science for Physical Geometric AlgorithmsResearch in Physical Geometric Algorithms (PGA) studies computational processes that compute or reason about geometric or spatial relationships in the physical world, and their realization in a variety of application areas. These areas include Robotics, Microelectromechanical Systems (MEMS), Computational Biology, Scientific and Image Processing, Image Analysis, and Systems Simulation. Collectively, these techniques take on the problems associated with manipulating massive amounts of data associated with a physical system model. Research in PGA pursues the proposition that, for such systems, predictions of behavior, arguments of correctness, and combinatorial precision devolve to a geometric analysis. At interesting scales these areas have in common their exploitation of networks, remote databases, local area clusters, disk farms (both local and remote), parallel processing, and graphics. This project will develop new Systems Science techniques (particularly algorithms, analysis, modeling techniques, and methodology) for addressing latency, bandwidth, security, scalability, scheduling, temporal variation in access, and parallel high-performance computing for these applications.The equipment provided by this grant enables our application research groups and systems research groups to synergistically develop common system solutions to these critical performance issues, as well as set new directions in both applications and systems problem areas.