arXiv 1403.01852014-03cs.LO

智能环境中情境感知应用的行为识别和分析

Behavior recognition and analysis in smart environments for context-aware applications

Radoslaw Klimek

备注：: Accepted conference paper: Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2015), October 9--12, 2015, Hong Kong, pp. 1949-1955. IEEE Computer Society 2015. Available at DOI:10.1109/SMC.2015.340 or http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7379472
DOI：: 10.1109/SMC.2015.340

摘要：

在情景感知和主动性至关重要的普适计算中，提供有关智能环境中行为的准确/适当信息是一项具有挑战性和关键性的任务。行为标识使得能够抽象出应用程序感兴趣的更高级别的概念。这项工作提出了统一的基于逻辑的框架来识别和分析行为规范理解为一个形式逻辑语言，避免歧义典型的自然语言。从感知数据流中自动发现行为作为形式化规范对于构建无缝的人机交互具有重要意义。因此，有关环境行为的知识表示的时间逻辑公式构成了一个基础的反应性和精确的推理过程，以支持可信的，明确的和主动的决策，智能和上下文感知的应用程序。

英文摘要：

Providing accurate/suitable information on behaviors in sma\-rt environments is a challenging and crucial task in pervasive computing where context-awareness and pro-activity are of fundamental importance. Behavioral identifications enable to abstract higher-level concepts that are interesting to applications. This work proposes the unified logical-based framework to recognize and analyze behavioral specifications understood as a formal logic language that avoids ambiguity typical for natural languages. Automatically discovering behaviors from sensory data streams as formal specifications is of fundamental importance to build seamless human-computer interactions. Thus, the knowledge about environment behaviors expressed in terms of temporal logic formulas constitutes a base for the reactive and precise reasoning processes to support trustworthy, unambiguous and pro-active decisions for applications that are smart and context-aware.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。