Power and Size Optimized Multi-Sensor Context Recognition Platform

Authors:
Nagendra B. Bharatula;Mathias Stager;Paul Lukowicz;Gerhard Troster
Affiliations:
Wearable Computing Lab, ETH Zürich, Switzerland;Wearable Computing Lab, ETH Zürich, Switzerland;Institute for Computer Systems and Networks, UMIT Hall, Austria;Wearable Computing Lab, ETH Zürich, Switzerland
Venue:
ISWC '05 Proceedings of the Ninth IEEE International Symposium on Wearable Computers
Year:
2005

Citing 0
Cited 6

Power and accuracy trade-offs in sound-based context recognition systems

Pervasive and Mobile Computing
Wearable electromyography measurement system using cable-free network system on conductive fabric

Artificial Intelligence in Medicine
Functionality-power-packaging considerations in context aware wearable systems

Personal and Ubiquitous Computing - Special Issue: Selected Papers of the ARCS06 Conference
Architectural tradeoffs in wearable systems

ARCS'06 Proceedings of the 19th international conference on Architecture of Computing Systems
Location and activity recognition using ewatch: a wearable sensor platform

Ambient Intelligence in Everyday Life
Activity recognition for creatures of habit

Personal and Ubiquitous Computing

Quantified Score

Hi-index	0.00

Visualization

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 classi- fier. Power measurements show that our 4.15脳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.