Recognition of Walking Activities Using Wireless Inertial and Orientation Sensors: A Performance Evaluation

Yalcin, Cagri and Marin-Perianu, Mihai and Marin-Perianu, Raluca and Havinga, Paul (2011) Recognition of Walking Activities Using Wireless Inertial and Orientation Sensors: A Performance Evaluation. In: 7th International Conference on Intelligent Environments, IE 2011, 25-28 July 2011, Nottingham, UK.

PDF
Restricted to UT campus only: Request a copy
2377Kb

Abstract:	In this paper, we evaluate experimentally several methods for recognizing walking activities using on-body wireless nodes equipped with inertial and orientation sensors. The walking activities (walking on flat surfaces, uphill and downhill, upstairs and downstairs) are selected by healthcare experts as being relevant for elderly patients suffering from Chronic Obstructive Pulmonary Disease (COPD). We target specifically recognition methods that operate with time-domain features only, due to the limitations of sensor nodes in terms of computational power, memory and energy. The results show that among all sensors the compass sensor performs best regardless of the classification method. Both the compass and gyroscope sensors outperform significantly the accelerometer sensor, which is typically used in previous related work. The best trade-off in performance vs. time complexity is obtained by fusing the gyroscope and compass information, with an overall accuracy of 91%.
Item Type:	Conference or Workshop Item
Copyright:	© 2011 IOS Press
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Pervasive Systems (PS)
Link to this item:	http://purl.utwente.nl/publications/77807
Official URL:	http://dx.doi.org/10.3233/978-1-60750-795-6-734
Conference URL:	http://ie11.org/
Publisher URL:	http://www.iospress.cn/html/9781607507949.php
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page