Title :
Power and size optimized multi-sensor context recognition platform
Author :
Bharatula, Nagendra B. ; Stäger, Mathias ; Lukowicz, Paul ; Tröster, Gerhard
Author_Institution :
Wearable Comput. Lab., Eidgenossische Tech. Hochschule, Zurich, Switzerland
Abstract :
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 classifier. Power measurements show that our 4.15×2.75 cm2, 9 gram platform consumes less than 3 mW and can perform continuous classification and result transmission for 129 hours on a small lithium-polymer battery.
Keywords :
mobile computing; optimisation; pattern recognition; power consumption; sensor fusion; decision tree classifier; lithium-polymer battery; miniaturized low-power platform; multisensor context recognition; power measurement; real-time activity recognition; wearable sensor system; Accelerometers; Batteries; Classification tree analysis; Decision trees; Microphones; Performance evaluation; Power measurement; Sensor systems; Signal processing; Wearable sensors;
Conference_Titel :
Wearable Computers, 2005. Proceedings. Ninth IEEE International Symposium on
Print_ISBN :
0-7695-2419-2
DOI :
10.1109/ISWC.2005.42
