A multilevel graph approach for IoT-based complex scenario management through situation awareness and semantic approaches

Abstract

AbstractModern reality and the environments in which we live are characterized by technology components geared toward automatic management through pervasive services. Thanks to the advent of the Internet of Things, such environments can provide information such as pollution levels, public transport conditions, efficiency of energy distribution networks, and identification of suspicious activities by generating complex scenarios. The profitable management of such scenarios can be performed through context modeling and methodologies that can extract and understand environmental information by preventing certain events through artificial intelligence techniques by increasing Situation Awareness. This paper focuses on developing a methodology with predictive capabilities and context adaptability for managing complex scenarios. The use of semantic and graph-based approaches, unlike many approaches used, leads to better integration of knowledge, resulting in improved system performance. In addition, such approaches allow understanding of what is happening in the system at a given time, enabling manipulation and integration of semantic information. Graph-based approaches chosen for this purpose are Ontologies, Context Dimension Trees, and Bayesian Networks, which are able to support the end-user or expert user in handling complex scenarios. The proposed methodology has been validated and applied to real complex scenarios based on the IoT paradigm. The proposed approach validation was conducted using open data from the city of London; a practical scenario case study was conducted in the field of automated management of a Smart Home. In both cases, the system achieved promising results.