Title :
Using rhythm awareness in long-term activity recognition
Author :
Van Laerhoven, Kristof ; Kilian, David ; Schiele, Bernt
Author_Institution :
Tech. Univ. Darmstadt, Darmstadt
fDate :
Sept. 28 2008-Oct. 1 2008
Abstract :
This paper reports on research where users´ activities are logged for extended periods by wrist-worn sensors. These devices operated for up to 27 consecutive days, day and night, while logging features from motion, light, and temperature. This data, labeled via 24-hour self-recall annotation, is explored for occurrences of daily activities. An evaluation shows that using a model of the users´ rhythms can improve recognition of daily activities significantly within the logged data, compared to models that exclusively use the sensor data for activity recognition.
Keywords :
sensors; wearable computers; activity recognition; rhythm awareness; sensor data; wrist-worn sensors; Accelerometers; Bicycles; Biomedical monitoring; In vivo; Patient monitoring; Rhythm; Switches; Temperature sensors; Wearable sensors; Wrist;
Conference_Titel :
Wearable Computers, 2008. ISWC 2008. 12th IEEE International Symposium on
Conference_Location :
Pittsburgh, PA
Print_ISBN :
978-1-4244-2637-9
DOI :
10.1109/ISWC.2008.4911586