Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units
Losing V, Yoshikawa T, Hasenjaeger M, Hammer B, Wersing H (2019)
In: 2019 International Conference on Robotics and Automation (ICRA). IEEE: 9530-9536.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Losing, ViktorUniBi;
Yoshikawa, Taizo;
Hasenjaeger, Martina;
Hammer, BarbaraUniBi
;
Wersing, HeikoUniBi
![](https://pub.uni-bielefeld.de/images/icon_orcid.png)
Abstract / Bemerkung
Online action classification is an important field of research, enabling the particularly interesting application scenario of controlling wearable devices which actively support the user's motions. The majority of machine learning applications of real-world systems are based on pre-trained average-user models without any personalization. Our long-term goal is to provide a system that adapts to its user's personal behavior patterns on the fly and in real-time. Ideally, we want to initiate a continuous collaboration between the system and the user where both alternatively adjust to each other to maximize the system's utility. Such tasks are not feasible with static models. In this paper, we investigate the potential and benefits of personalized online learning in the task of online action classification. We record motion sequences of different subjects wearing the Xsens bodysuit, which incorporates multiple inertial measuring units, enabling a fine-grained discrimination of motions. On this basis, we first perform a feature selection, showing that only a few sensors are necessary to achieve a high classification performance. Subsequently, we compare the recognition capabilities of offline average user models against personalized models trained in an online way. Our experiments conclude that personalized models require only few data to outperform average user systems and are particularly valuable for applications with limited computational hardware which rely on the raw sensor inputs only.
Erscheinungsjahr
2019
Titel des Konferenzbandes
2019 International Conference on Robotics and Automation (ICRA)
Seite(n)
9530-9536
Konferenz
2019 International Conference on Robotics and Automation (ICRA)
Konferenzort
Montreal, QC, Canada
eISBN
978-1-5386-6027-0
Page URI
https://pub.uni-bielefeld.de/record/2982084
Zitieren
Losing V, Yoshikawa T, Hasenjaeger M, Hammer B, Wersing H. Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units. In: 2019 International Conference on Robotics and Automation (ICRA). IEEE; 2019: 9530-9536.
Losing, V., Yoshikawa, T., Hasenjaeger, M., Hammer, B., & Wersing, H. (2019). Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units. 2019 International Conference on Robotics and Automation (ICRA), 9530-9536. IEEE. https://doi.org/10.1109/ICRA.2019.8794251
Losing, Viktor, Yoshikawa, Taizo, Hasenjaeger, Martina, Hammer, Barbara, and Wersing, Heiko. 2019. “Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units”. In 2019 International Conference on Robotics and Automation (ICRA), 9530-9536. IEEE.
Losing, V., Yoshikawa, T., Hasenjaeger, M., Hammer, B., and Wersing, H. (2019). “Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units” in 2019 International Conference on Robotics and Automation (ICRA) (IEEE), 9530-9536.
Losing, V., et al., 2019. Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units. In 2019 International Conference on Robotics and Automation (ICRA). IEEE, pp. 9530-9536.
V. Losing, et al., “Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units”, 2019 International Conference on Robotics and Automation (ICRA), IEEE, 2019, pp.9530-9536.
Losing, V., Yoshikawa, T., Hasenjaeger, M., Hammer, B., Wersing, H.: Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units. 2019 International Conference on Robotics and Automation (ICRA). p. 9530-9536. IEEE (2019).
Losing, Viktor, Yoshikawa, Taizo, Hasenjaeger, Martina, Hammer, Barbara, and Wersing, Heiko. “Personalized Online Learning of Whole-Body Motion Classes using Multiple Inertial Measurement Units”. 2019 International Conference on Robotics and Automation (ICRA). IEEE, 2019. 9530-9536.