Abstract:

A context-aware Internet of Things system must be able to observe, interpret and reason the dynamic situations of the environment to provide pertinent information and services to the user. This article proposes an approach which is structured around the three following contributions: the semantic representation of IoT data, the detection of context situations and the dissemination of contextual information for consumers. The main contribution of this article is represented by a hybrid system for the intelligent detection of the context situation in an IoT environment, which combines between machine learning algorithms and approximate logic, more precisely, the artificial neural network, the Case-based reasoning and fuzzy logic. In order to validate this approach, the authors chose a use case in the intelligent transportation sector.