Constructing Context-centric Data Objects to Enhance Logical Associations for IoT Entities

Entities in Internet of Things (IoT) need intelligent associations to allow a flexible and dynamic system reaction towards varying user situations. Purely data-oriented association methods (e.g., data-mining, machine-learning, etc.) are limited in deduction from existing associations. Also such data-oriented methods are limited in accuracy for working with small-scale datasets (e.g., working with patterns retrieved from historical data), outputting associations based on statistics rather than logic. Moreover, existing semantic technologies (ontological-oriented or rule-oriented) are facing with either flexibility or dynamicity challenges to discover and maintain the associations. This paper proposes an alternative technique of semantically constructing context-centric data objects based on service logics for logical associations, which enables an event net based on association nets adapting for the changing situations (called context-centric). A proof-of-concept implementation is carried out based on a vehicle planning scenario to validate the data construction technique. Comparing to previous work, this technique possesses advantages of flexibility and dynamicity for entity associations based on service logics