Home // eTELEMED 2020, The Twelfth International Conference on eHealth, Telemedicine, and Social Medicine // View article


Detection of Health-Related Problems of People with Dementia from Lifestyle Wearables: A Rule-Based Approach

Authors:
Antonios Pliatsios
Thanos Stavropoulos
Dimitris Strantsalis
Vasileios Kassiano
Spiros Nikolopoulos
Ioannis Kompatsiaris

Keywords: Ontology; Event Detection; Semantic Web; SPIN; Reasoning; Rule-Based Systems; Dementia

Abstract:
In this paper, we describe a rule-based framework for the detection of health-related problems of people with dementia. The framework combines a novel ontology for lifestyle data (steps, sleep duration and heart rate measurements) and health-related problem representation and a novel set of SPARQL Inferencing Notation (SPIN) Rules to infer problems from lifestyle data. Both the ontology and the rule set are designed based on clinical expert knowledge in the field of dementia. More specifically, lifestyle data is acquired from lifestyle wearable devices in the market, making the system affordable and convenient. A model based on Semantic Web technology, Web Ontology Language (OWL), is used to formally represent and integrate sensor measurements, which promotes interoperability with other models and data exchange. SPIN rules offer the benefit of simplicity and flexibility as opposed to other rule representations in the domain. A proof-of-concept scenario is realized, showing data gathered from a real subject and the generation of expected problems by the framework.

Pages: 172 to 177

Copyright: Copyright (c) IARIA, 2020

Publication date: March 22, 2020

Published in: conference

ISSN: 2308-4359

ISBN: 978-1-61208-763-4

Location: Valencia, Spain

Dates: from November 21, 2020 to November 25, 2020