A Platform for Detecting Height-Level Contexts from Complex Event Streams in Pervasive Environment

Abstract

A Pervasive-computing-enriched smart environment, which contains hundreds of embedded devices coordinated by service management mechanisms, is capable of anticipating intensions of occupants and providing appropriate services accordingly. To acquire high-level contexts, such as human activities, usually involves analyzing and identifying causality and temporal ordering relationships among a bulk stream of sensor readings. However, there are relatively few works investigating this issue. We notice that Complex Event Processing (CEP) is useful for dealing with the issue mentioned above. In this work, we propose a platform for integrating CEP concepts with Per SAM, a service application model for pervasive environments. Applications and experiments are performed to verify the effectiveness of the proposed platform.