earticle

영어

Context fusion is a very important aspect in a system that has to adequately simplify a required task in achieving context awareness in the Internet of things (IoT). IoT generates a large amount of data, which are massive, multi-source, heterogeneous, dynamic and sparse. Context information fusion is an important tool in the manipulation and management of these data in order to improve processing efficiency, provide advanced intelligence and increase reliability. Context information fusion can reduce the amount of data traffic, filter noisy measurements, and make predictions and inferences in any stages of data processing in IoT. As such when context is acquired from this domain, it has low confidence level due to reliability factors. In this paper Context information’s reliability has been addressed through the use quality of context (QoC) by determining the combined confidence for acquired context from multiple sources. Particle Swarm Optimization selects the context information with the highest level of confidence and Dempster Shafer rule of combination fuses this context into more reliable information that can be used by the system to effectively adapt to changing context. From the obtained results the proposed solution indicates an improved fusion process with increased confidence.