III: Small: Complex Event Analytics

III：小：复杂事件分析

• 批准号: 1018443
• 负责人: Elke Rundensteiner
• 金额: $ 49.99万
• 依托单位: Worcester Polytechnic Institute
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-09-01 至 2015-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1018443&HistoricalAwards=false
• 关键词: III; Small; Complex; Event; Analytics

Recent advances in sensor technologies and expansion of wired andwireless communication protocols enable us to continuously collectinformation about the physical world, resulting in a rich set of novelservices. The ability to infer relevant patterns from these eventstreams in real-time and at various levels of abstractions to makenear instantaneous decisions is crucial for a wide range of missioncritical applications ranging from real-time crisis management tosecurity. This project designs, implements, and evaluates a novelcomplex event processing methodology, henceforth called Complex EventAnalytics (CEA). CEA integrates the capabilities of pattern matchingfrom complex event processing with the power of multi-level analysisfrom static OLAP engines to provide multi-dimensional sequentialpattern analysis over high-speed event streams. The CEA Modelcombines CEP and OLAP techniques for efficient multi-dimensional eventpattern analysis at different abstraction levels. Based oninterrelationships in both concept and pattern refinement amongqueries, sequence queries are composed into an integrated eventpattern hierarchy. OLAP like operations enable analysts to navigatefrom one E-cuboid to another in this event analytics space. CEAoptimization strategies, including rewriting rules, physicaloperators, and cost-based search algorithms, achieve scalable eventprocessing. CEA offers high-performance analytics by maximal sharedprocessing of event pattern queries. Experimental studies compare theCEA solution to the state-of-the-art, including traditional streamquery systems and customized event engines. Intellectual merit liesin the design, development and evaluation of a novel Complex EventAnalytics technology for real-time event stream analysis, -- a perfectmiddle ground offering both the sophisticated power of patternmatching found in modern event processing systems and the capabilityof online analytic techniques at multiple levels of abstraction ofOLAP engines. CEA impacts society by facilitating a broad range ofstream-centric applications ranging from monitoring of hygienecompliance to prevent the spread of infectuous diseases in medicalsettings to business intelligence processing, and by integratingproject activities with education.For further information see the project web site at the URL:http://davis.wpi.edu/dsrg/PROJECTS/CEA

传感器技术的最新进展以及有线和无线通信协议的扩展使我们能够不断收集有关物理世界的信息，从而产生丰富的新颖服务。 从这些事件流中实时推断相关模式并在不同的抽象级别上做出近乎即时的决策的能力对于从实时危机管理到安全等各种关键任务应用程序至关重要。 该项目设计、实现和评估一种新颖的复杂事件处理方法，以下称为复杂事件分析 (CEA)。 CEA 将复杂事件处理的模式匹配功能与静态 OLAP 引擎的多级分析功能集成在一起，可对高速事件流提供多维顺序模式分析。 CEA 模型结合了 CEP 和 OLAP 技术，可在不同抽象级别进行高效的多维事件模式分析。基于查询之间概念和模式细化的相互关系，序列查询被组成一个集成的事件模式层次结构。 类似 OLAP 的操作使分析师能够在此事件分析空间中从一个 E-cuboid 导航到另一个 E-cuboid。 CEA优化策略，包括重写规则、物理运算符和基于成本的搜索算法，实现了可扩展的事件处理。 CEA 通过最大限度地共享处理事件模式查询来提供高性能分析。 实验研究将 CEA 解决方案与最先进的解决方案进行了比较，包括传统的流查询系统和定制的事件引擎。 智力价值在于设计、开发和评估用于实时事件流分析的新型复杂事件分析技术，这是一个完美的中间地带，提供现代事件处理系统中复杂的模式匹配功能和多个级别的在线分析技术的能力OLAP 引擎的抽象。 CEA 通过促进广泛的以流为中心的应用程序（从监控卫生合规性以防止医疗环境中传染病传播到商业智能处理）以及将项目活动与教育相结合来影响社会。有关更多信息，请参阅项目网站，网址为： http://davis.wpi.edu/dsrg/PROJECTS/CEA