Abstract
This paper presents an approach for early recognition of gait initiation and termination using wearable inertial measurement units and pressure-sensitive insoles. Body joint angles, ground reaction force and center of plantar pressure of each foot are obtained from these sensors and input into a supervised learning algorithm. For gait initiation, the algorithm detects two events: gait onset (the first detectable change from the baseline state) and toe-off. For gait termination, the algorithm segments gait into different steps, measures the signals over a window at the beginning of each step, and determines whether the measurement belongs to the final step. The approach is validated with 10 subjects at two different gait speeds, with both within-subject and subject-independent crossvalidation. Results show that the inertial measurement units are generally more useful than insoles during both gait initiation and termination, though combining both types of sensors results in better onset detection and easier segmentation of gait into different steps. However, for best performance the algorithms should be trained for each subject separately, and the gait termination recognition algorithm is not very robust with regard to gait speed.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics |
| Pages | 1937-1942 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2012 |
| Event | 2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012 - Rome, Italy Duration: Jun 24 2012 → Jun 27 2012 |
Other
| Other | 2012 4th IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics, BioRob 2012 |
|---|---|
| Country | Italy |
| City | Rome |
| Period | 6/24/12 → 6/27/12 |
Fingerprint
Keywords
- gait
- intention detection
- wearable computing
ASJC Scopus subject areas
- Artificial Intelligence
- Biomedical Engineering
- Mechanical Engineering
Cite this
Early recognition of gait initiation and termination using wearable sensors. / Novak, Domen; Rebersek, Peter; Beravs, Tadej; Podobnik, Janez; Munih, Marko; De Rossi, Stefano Marco Maria; Donati, Marco; Lenzi, Tommaso; Vitiello, Nicola; Carrozza, Maria Chiara.
Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics. 2012. p. 1937-1942 6290277.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Early recognition of gait initiation and termination using wearable sensors
AU - Novak, Domen
AU - Rebersek, Peter
AU - Beravs, Tadej
AU - Podobnik, Janez
AU - Munih, Marko
AU - De Rossi, Stefano Marco Maria
AU - Donati, Marco
AU - Lenzi, Tommaso
AU - Vitiello, Nicola
AU - Carrozza, Maria Chiara
PY - 2012
Y1 - 2012
N2 - This paper presents an approach for early recognition of gait initiation and termination using wearable inertial measurement units and pressure-sensitive insoles. Body joint angles, ground reaction force and center of plantar pressure of each foot are obtained from these sensors and input into a supervised learning algorithm. For gait initiation, the algorithm detects two events: gait onset (the first detectable change from the baseline state) and toe-off. For gait termination, the algorithm segments gait into different steps, measures the signals over a window at the beginning of each step, and determines whether the measurement belongs to the final step. The approach is validated with 10 subjects at two different gait speeds, with both within-subject and subject-independent crossvalidation. Results show that the inertial measurement units are generally more useful than insoles during both gait initiation and termination, though combining both types of sensors results in better onset detection and easier segmentation of gait into different steps. However, for best performance the algorithms should be trained for each subject separately, and the gait termination recognition algorithm is not very robust with regard to gait speed.
AB - This paper presents an approach for early recognition of gait initiation and termination using wearable inertial measurement units and pressure-sensitive insoles. Body joint angles, ground reaction force and center of plantar pressure of each foot are obtained from these sensors and input into a supervised learning algorithm. For gait initiation, the algorithm detects two events: gait onset (the first detectable change from the baseline state) and toe-off. For gait termination, the algorithm segments gait into different steps, measures the signals over a window at the beginning of each step, and determines whether the measurement belongs to the final step. The approach is validated with 10 subjects at two different gait speeds, with both within-subject and subject-independent crossvalidation. Results show that the inertial measurement units are generally more useful than insoles during both gait initiation and termination, though combining both types of sensors results in better onset detection and easier segmentation of gait into different steps. However, for best performance the algorithms should be trained for each subject separately, and the gait termination recognition algorithm is not very robust with regard to gait speed.
KW - gait
KW - intention detection
KW - wearable computing
UR - http://www.scopus.com/inward/record.url?scp=84867426239&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867426239&partnerID=8YFLogxK
U2 - 10.1109/BioRob.2012.6290277
DO - 10.1109/BioRob.2012.6290277
M3 - Conference contribution
AN - SCOPUS:84867426239
SN - 9781457711992
SP - 1937
EP - 1942
BT - Proceedings of the IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics
ER -