Home // HEALTHINFO 2017, The Second International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing // View article

Utilizing Smartwatches for Supporting the Wellbeing of Elderly People

Authors:
Klemens Waldhör
Rainer Lutze

Keywords: smartwatches; automatic recognition of activities, events of daily living (ADLs, EDLs); artificial neuronal networks (ANN); universal recognition model; wellbeing function

Abstract:
We present a new approach for securing the wellbeing of elderly people via a smartwatch based personal health assistant. On the smartwatch, an app featuring an artificial neuronal network (ANN) analyzes the activity patterns of the smartwatch wearer. The ANN recognizes health relevant events and activities of daily living (EDLs, ADL). Especially activities associated with body care tasks are considered. From the sequence and timing of rec-ognized EDLs, ADLs, an individual wellbeing function will be continuously calculated, summarizing the specific personal health state. If the wellbeing function value falls below a defined thresh-old, external alerts will be issued by the smartwatch. Such alert-ing will be done automatically, if the smartwatch wearer is not able to respond. It can be done autonomously via the integrated cellular radio module of the smartwatch. The system architecture of the app, the data acquisition process, the selection and design of suitable data models and the advantages of ANNs versus other recognition engines are discussed.

Pages: 1 to 9

Copyright: Copyright (c) IARIA, 2017

Publication date: October 8, 2017

Published in: conference

ISSN: 2519-8491

ISBN: 978-1-61208-597-5

Location: Athens, Greece

Dates: from October 8, 2017 to October 12, 2017