Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning

Prahm C, Schulz A, Paaßen B, Schoisswohl J, Kaniusas E, Dorffner G, Hammer B, Aszmann O (2019)
IEEE Transactions on Neural Systems and Rehabilitation Engineering 27(5): 956-962.

Zeitschriftenaufsatz | E-Veröff. vor dem Druck| Englisch
 
Download
OA 2.35 MB
Autor/in
Prahm, Cosima; Schulz, AlexanderUniBi ; Paaßen, BenjaminUniBi ; Schoisswohl, Johannes; Kaniusas, Eugenius; Dorffner, Georg; Hammer, BarbaraUniBi; Aszmann, Oskar
Abstract / Bemerkung
Research on machine learning approaches for upper limb prosthesis control has shown impressive progress. However, translating these results from the lab to patient's everyday lives remains a challenge, because advanced control schemes tend to break down under everyday disturbances, such as electrode shifts. Recently, it has been suggested to apply adaptive transfer learning to counteract electrode shifts using as little newly recorded training data as possible.

In this paper, we present a novel, simple version of transfer learning and provide the first user study demonstrating the effectiveness of transfer learning to counteract electrode shifts. For this purpose, we introduce the novel Box and Beans test to evaluate prosthesis proficiency and compare user performance with an initial simple pattern recognition system, the system under electrode shifts, and the system after transfer learning. Our results show that transfer learning could significantly alleviate the impact of electrode shifts on user performance in the Box and Beans test.
Stichworte
transfer learning; upper-limb prostheses; box and beans test; electromyography
Erscheinungsjahr
2019
Zeitschriftentitel
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Band
27
Ausgabe
5
Seite(n)
956-962
Page URI
https://pub.uni-bielefeld.de/record/2934458

Zitieren

Prahm C, Schulz A, Paaßen B, et al. Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2019;27(5):956-962.
Prahm, C., Schulz, A., Paaßen, B., Schoisswohl, J., Kaniusas, E., Dorffner, G., Hammer, B., et al. (2019). Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(5), 956-962. doi:10.1109/TNSRE.2019.2907200
Prahm, C., Schulz, A., Paaßen, B., Schoisswohl, J., Kaniusas, E., Dorffner, G., Hammer, B., and Aszmann, O. (2019). Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering 27, 956-962.
Prahm, C., et al., 2019. Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(5), p 956-962.
C. Prahm, et al., “Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 27, 2019, pp. 956-962.
Prahm, C., Schulz, A., Paaßen, B., Schoisswohl, J., Kaniusas, E., Dorffner, G., Hammer, B., Aszmann, O.: Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 27, 956-962 (2019).
Prahm, Cosima, Schulz, Alexander, Paaßen, Benjamin, Schoisswohl, Johannes, Kaniusas, Eugenius, Dorffner, Georg, Hammer, Barbara, and Aszmann, Oskar. “Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning”. IEEE Transactions on Neural Systems and Rehabilitation Engineering 27.5 (2019): 956-962.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:19:06Z
MD5 Prüfsumme
dd9ff62f447e0ddbb15285179644e896

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 30908234
PubMed | Europe PMC

Suchen in

Google Scholar