Home // eTELEMED 2019, The Eleventh International Conference on eHealth, Telemedicine, and Social Medicine // View article


Evaluation of Machine Learning Algorithms to Detect Irregular Health States in Wearable Sensor Generated Data

Authors:
Reto Wettstein
Christian Fegeler

Keywords: Algorithm Evaluation; Anomaly Detection; Health State; Wearable Generated Data.

Abstract:
Wearable devices facilitate continuous monitoring of personal health data. However, automated health state analysis based on this data is challenging in various aspects. This work presents preliminary algorithm evaluation results for health state irregularity detection based on a continuous data sample collected by an in-ear heart rate and body temperature sensor. The results show that a One-Class Support Vector Machine could be suitable for the task.

Pages: 116 to 117

Copyright: Copyright (c) IARIA, 2019

Publication date: February 24, 2019

Published in: conference

ISSN: 2308-4359

ISBN: 978-1-61208-688-0

Location: Athens, Greece

Dates: from February 24, 2019 to February 28, 2019