Sensor Selection for Classification of Physical Activity in Long-Term Wearable Devices

Kirchner J, Faghih-Naini S, Bisgin P, Fischer G (2018)

Publication Language: English

Publication Status: Accepted

Publication Type: Conference contribution, Conference Contribution

Future Publication Type: Conference contribution

Publication year: 2018

Publisher: IEEE

City/Town: New York

Pages Range: 18329442

Conference Proceedings Title: 2018 IEEE SENSORS

Event location: New Delhi IN

ISBN: 978-1-5386-4707-3

DOI: 10.1109/ICSENS.2018.8589663

Abstract

Classification of physical activity based on the kNN algorithm is assessed with different combinations of sensors
(from accelerometer, gyroscope, barometer) with respect to classification accuracy, power consumption and computation time. For that purpose, a wearable sensor platform is proposed and a study with 20 subjects is conducted. The combination of accelerometer and barometer is found to provide the best trade-off for the
three criteria: It provides an F1 score of 94.96 ± 1.73 %, while computation time and power consumption are reduced by 45 % and 88 %, respectively, compared to the full sensor set.

Authors with CRIS profile

Jens Kirchner Lehrstuhl für Technische Elektronik Samira Faghih-Naini Lehrstuhl für Technische Elektronik Georg Fischer Professur für Technische Elektronik

How to cite

APA:

Kirchner, J., Faghih-Naini, S., Bisgin, P., & Fischer, G. (2018). Sensor Selection for Classification of Physical Activity in Long-Term Wearable Devices. In 2018 IEEE SENSORS (pp. 18329442). New Delhi, IN: New York: IEEE.

MLA:

Kirchner, Jens, et al. "Sensor Selection for Classification of Physical Activity in Long-Term Wearable Devices." Proceedings of the 2018 IEEE SENSORS, New Delhi New York: IEEE, 2018. 18329442.

BibTeX: Download