Detecting situations of importance with Stream Reasoning on live health IoT data

Tracking #: 2914-4128

This paper is currently under review
Mathieu Bourgais
Franco Giustozzi
Laurent Vercouter

Responsible editor: 
Armin Haller

Submission type: 
Full Paper
he development of Internet of Things (IoT) creates large amount of data which may be used by decision making systems in a variety of domains. In particular, in the field of health monitoring, it enables to follow the medical state of a patient hospitalized at home in real-time. An important challenge is to represent and interpret these data with a high-level model in order to have a better understanding of the overall medical state of a patient, taking into account the context of these data. This article overcomes this challenge by using Stream Reasoning techniques associated to an ontological representation of the medical context of a patient to understand her situation. This permits to combine in real time static knowledge stored in an ontology and dynamic information provided by smart sensors. To facilitate this process, constraints and situations concepts are introduced to ease the translation of expert knowledge into logical queries. The paper concludes with a discussion on the coverage of the proposed ontology and an experimental analysis of real body temperature data to illustrate how situations may be detected.
Full PDF Version: 
Under Review