The Community for Technology Leaders
Ninth IEEE International Symposium on Wearable Computers (ISWC'05) (2005)
Osaka, Japan
Oct. 18, 2005 to Oct. 21, 2005
ISBN: 0-7695-2419-2
pp: 194-195
Nagendra B. Bharatula , Wearable Computing Lab, ETH Z?urich, Switzerland
Mathias Stager , Wearable Computing Lab, ETH Z?urich, Switzerland
Paul Lukowicz , Institute for Computer Systems and Networks, UMIT Hall, Austria
Gerhard Troster , Wearable Computing Lab, ETH Z?urich, Switzerland
ABSTRACT
<p>This paper presents a miniaturized low-power platform for real-time activity recognition. The wearable sensor system comprises of accelerometers, a microphone, a light sensor and signal processing units. The recognition is performed with low-power features and a decision tree classi- fier. Power measurements show that our 4.15?2.75 cm2, 9 gram platform consumes less than 3mW and can perform continuous classification and result transmission for 129 hours on a small lithium-polymer battery.</p>
INDEX TERMS
null
CITATION

P. Lukowicz, N. B. Bharatula, M. Stager and G. Troster, "Power and Size Optimized Multi-Sensor Context Recognition Platform," Ninth IEEE International Symposium on Wearable Computers (ISWC'05)(ISWC), Osaka, Japan, 2005, pp. 194-195.
doi:10.1109/ISWC.2005.42
88 ms
(Ver 3.3 (11022016))