TY - GEN
T1 - Recognition of Walking Activities Using Wireless Inertial and Orientation Sensors: A Performance Evaluation
AU - Yalçin, Ç.
AU - Marin Perianu, Mihai
AU - Marin Perianu, Raluca
AU - Havinga, Paul J.M.
N1 - 10.3233/978-1-60750-795-6-734
PY - 2011/7
Y1 - 2011/7
N2 - 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%.
AB - 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%.
KW - METIS-278739
KW - EWI-20368
KW - IR-77807
U2 - 10.3233/978-1-60750-795-6-734
DO - 10.3233/978-1-60750-795-6-734
M3 - Conference contribution
SN - 978-1-60750-794-9
T3 - Ambient Intelligence and Smart Environments
SP - 734
EP - 740
BT - Workshop Proceedings of the 7th International Conference on Intelligent Environments
A2 - Augusto, J.C.
PB - IOS
CY - Netherlands
T2 - 7th International Conference on Intelligent Environments, IE 2011
Y2 - 25 July 2011 through 28 July 2011
ER -