loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Eighth IEEE International Symposium on Wearable Computers (ISWC'04)
Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System
Arlington, Virginia
October 31-November 03
ISBN: 0-7695-2186-X
ASCII Text
x 
 
Mathias St?ger, Paul Lukowicz, Gerhard Tr?ster, "Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System," Wearable Computers, IEEE International Symposium, pp. 138-141, Eighth IEEE International Symposium on Wearable Computers (ISWC'04), 2004.
 
 
BibTex
x
 
@article{ 10.1109/ISWC.2004.25,
author = {Mathias St?ger and Paul Lukowicz and Gerhard Tr?ster},
title = {Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System},
journal ={Wearable Computers, IEEE International Symposium},
volume = {0},
year = {2004},
issn = {1530-0811},
pages = {138-141},
doi = {http://doi.ieeecomputersociety.org/10.1109/ISWC.2004.25},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Wearable Computers, IEEE International Symposium
TI - Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System
SN - 1530-0811
SP138
EP141
A1 - Mathias St?ger,
A1 - Paul Lukowicz,
A1 - Gerhard Tr?ster,
PY - 2004
KW - null
VL - 0
JA - Wearable Computers, IEEE International Symposium
ER -
 
Mathias St?ger, ETH Z?rich, Switzerland
Paul Lukowicz, ETH Z?rich, Switzerland; UMIT Innsbruck, Austria
Gerhard Tr?ster, ETH Z?rich, Switzerland
The paper presents a prototype of a wearable, sound-analysis based, user activity recognition device. It focuses on low-power realization suitable for a miniaturized implementation. We describe a tradeoff analysis between recognition performance and computation complexity. Furthermore, we present the hardware prototype and the experimental evaluation of its recognition performance. This includes frame by frame recognition, event detection in a continuous data stream and the influence of background noise.
Citation:
Mathias St?ger, Paul Lukowicz, Gerhard Tr?ster, "Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System," iswc, pp.138-141, Eighth IEEE International Symposium on Wearable Computers (ISWC'04), 2004
Usage of this product signifies your acceptance of the Terms of Use.