Energy Efficient On-Sensor Processing for Online Activity Recognition

Florian Grützmacher, Albert Hein, Benjamin Beichler, Polichronis Lepidis, Rainer Dorsch, Thomas Kirste, Christian Haubelt

2018

Abstract

In sensor-based online activity recognition, the communication of sensor samples at high data rates has a great impact on the energy consumptions of wearables. In our work we investigate the idea of calculating data reducing stages of activity recognition systems on wireless sensor nodes in order to reduce the amount of transmitted data and thus the overall energy consumption. In our experiments, this approach could reduce the energy consumption of a wireless sensor node by up to 27%. Since the benefit of this approach highly depends on design parameters of the activity recognition, we introduce an energy trade-off model for wireless sensor nodes to estimate energy-savings of application specific configurations at design time. By calibrating this model for our wireless sensor node, we could achieve an accuracy of more than 99% in our experiments.

Download


Paper Citation


in Harvard Style

Grützmacher F., Hein A., Beichler B., Lepidis P., Dorsch R., Kirste T. and Haubelt C. (2018). Energy Efficient On-Sensor Processing for Online Activity Recognition.In Proceedings of the 8th International Joint Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PEC, ISBN 978-989-758-322-3, pages 85-92. DOI: 10.5220/0006860100850092


in Bibtex Style

@conference{pec18,
author={Florian Grützmacher and Albert Hein and Benjamin Beichler and Polichronis Lepidis and Rainer Dorsch and Thomas Kirste and Christian Haubelt},
title={Energy Efficient On-Sensor Processing for Online Activity Recognition},
booktitle={Proceedings of the 8th International Joint Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PEC,},
year={2018},
pages={85-92},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006860100850092},
isbn={978-989-758-322-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Joint Conference on Pervasive and Embedded Computing and Communication Systems - Volume 1: PEC,
TI - Energy Efficient On-Sensor Processing for Online Activity Recognition
SN - 978-989-758-322-3
AU - Grützmacher F.
AU - Hein A.
AU - Beichler B.
AU - Lepidis P.
AU - Dorsch R.
AU - Kirste T.
AU - Haubelt C.
PY - 2018
SP - 85
EP - 92
DO - 10.5220/0006860100850092