Hips do lie! A position-aware mobile fall detection system

Krupitzer, Christian ; Sztyler, Timo ; Edinger, Janick ; Breitbach, Martin ; Stuckenschmidt, Heiner ; Becker, Christian

DOI:	https://doi.org/10.1109/PERCOM.2018.8444583
URL:	https://ieeexplore.ieee.org/document/8444583
Dokumenttyp:	Konferenzveröffentlichung
Erscheinungsjahr:	2018
Buchtitel:	2018 IEEE International Conference on Pervasive Computing and Communications (PerCom) : Athens, Greece, March 19-23, 2018
Seitenbereich:	1-10
Veranstaltungstitel:	PerCom 2018
Veranstaltungsort:	Athens, Greece
Veranstaltungsdatum:	19.-23.03.2018
Ort der Veröffentlichung:	Piscataway, NJ
Verlag:	IEEE Computer Society
ISBN:	978-1-5386-3228-4 , 978-1-5386-3227-7 , 978-1-5386-3226-0
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Fakultät für Wirtschaftsinformatik und Wirtschaftsmathematik > Practical Computer Science II: Artificial Intelligence (Stuckenschmidt 2009-) Fakultät für Betriebswirtschaftslehre > Wirtschaftsinformatik II (Becker 2006-2021)
Fachgebiet:	004 Informatik
Abstract:	Ambient Assisted Living using mobile device sensors is an active area of research in pervasive computing. Multiple approaches have shown that wearable sensors perform very well and distinguish falls reliably from Activities of Daily Living. However, these systems are tested in a controlled environment and are optimized for a given set of sensor types, sensor positions, and subjects. In this work, we propose a self-adaptive pervasive fall detection approach that is robust to the heterogeneity of real life situations. Therefore, we combine sensor data of four publicly available datasets, covering about 100 subjects, 5 devices, and 3 sensor placements. In a comprehensive evaluation, we show that our system is not only robust regarding the different dimensions of heterogeneity, but also adapts autonomously to spontaneous changes in the sensor's position at runtime.