Anticipating Health Hazards through an Ontology-Based, IoT Domotic Environment

Abstract

Embedded intelligence entails a vision of the Internet of Things oriented to "Ambient Intelligence", which can be defined as the capacity to collect and analyze the digital traces left by people when they interact with the environment and with such "intelligent things". In such a vision, the ultimate aim is to acquire knowledge about everyday life and human behavior. We apply these concepts to the automated home, in which even nowadays devices (sensors and actuators) are already Internet-capable "things" endowed with their own intelligence. This work introduces a semantic knowledge representation for domotics following the principles of the semantic Web (Web 3.0). We have implemented specific ontologies that automatically take account of distributed environmental context information. The first result was to achieve a natural abstraction of different, incompatible devices in order to support interoperability in a consistent technology-independent manner and impart awareness to the domestic environment in which "things" such as furniture and other objects, as well as the rooms themselves, take on computational significance. This goal includes leveraging the development of a comprehensive intelligent ecosystem that, by applying machine learning and artificial intelligence techniques, gains knowledge of the occupants' behaviors and habits and can thereby adapt itself to the specific setting and anticipate their needs without direct human intervention. The same modeling process serves as the basis for implementation of an e-health system that can anticipate, and thereby prevent, possible health hazards before emergency situations arise (especially for the sick and elderly).