Echo State Networks as Novel Approach for Low-Cost Myoelectric Control

Prahm C, Schulz A, Paaßen B, Aszmann O, Hammer B, Dorffner G (2017)
In: Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017). ten Telje A, Popow C, Holmes JH, Sacchi L (Eds); Lecture Notes in Computer Science, 10259. Springer: 338--342.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
OA 317.32 KB
OA prahm_schulz_paassen_aszmann_hammer_dorffner_echo_state_networks.pdf 319.69 KB
Autor*in
Prahm, Cosima; Schulz, AlexanderUniBi ; Paaßen, BenjaminUniBi ; Aszmann, Oskar; Hammer, BarbaraUniBi; Dorffner, Georg
Herausgeber*in
ten Telje, Annette; Popow, Christian; Holmes, John H.; Sacchi, Lucia
Abstract / Bemerkung
Myoelectric signals or muscle signals provide an intuitive and rapid interface for controlling technical devices, in particular bionic arm prostheses. However, inferring the intended movement from a surface myoelectric recording is a non-trivial pattern recognition task, especially if myoelectric data stems from low-cost sensors. At the same time, overly complex models are prohibited by strict speed, data parsimonity and robustness requirements. As a compromise between high accuracy and strict requirements we propose to apply Echo State Networks (ESNs), which can be seen as an extension of standard linear regression with 1) a memory and 2) nonlinearity. We find that both features, memory and nonlinearity, independently as well as in conjunction, improve the prediction accuracy on simultaneous movements in two degrees of freedom (hand opening/closing as well as pronation/supination) recorded from four able-bodied participants using a low-cost myoelectric sensor. However, we also find that the model is still not sufficiently resistant to external disturbances such as electrode shift.
Stichworte
Myoelectric Data; Echo-State Networks; Bionic Prostheses
Erscheinungsjahr
2017
Titel des Konferenzbandes
Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017)
Band
10259
Seite(n)
338--342
Konferenz
16th Conference on Artificial Intelligence in Medicine (AIME 2017)
Konferenzort
Vienna, Austria
Konferenzdatum
2017-06-22 – 2017-06-23
Page URI
https://pub.uni-bielefeld.de/record/2909037

Zitieren

Prahm C, Schulz A, Paaßen B, Aszmann O, Hammer B, Dorffner G. Echo State Networks as Novel Approach for Low-Cost Myoelectric Control. In: ten Telje A, Popow C, Holmes JH, Sacchi L, eds. Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017). Lecture Notes in Computer Science. Vol 10259. Springer; 2017: 338--342.
Prahm, C., Schulz, A., Paaßen, B., Aszmann, O., Hammer, B., & Dorffner, G. (2017). Echo State Networks as Novel Approach for Low-Cost Myoelectric Control. In A. ten Telje, C. Popow, J. H. Holmes, & L. Sacchi (Eds.), Lecture Notes in Computer Science: Vol. 10259. Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017) (pp. 338--342). Springer. doi:10.1007/978-3-319-59758-4_40
Prahm, C., Schulz, A., Paaßen, B., Aszmann, O., Hammer, B., and Dorffner, G. (2017). “Echo State Networks as Novel Approach for Low-Cost Myoelectric Control” in Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017), ten Telje, A., Popow, C., Holmes, J. H., and Sacchi, L. eds. Lecture Notes in Computer Science, vol. 10259, (Springer), 338--342.
Prahm, C., et al., 2017. Echo State Networks as Novel Approach for Low-Cost Myoelectric Control. In A. ten Telje, et al., eds. Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017). Lecture Notes in Computer Science. no.10259 Springer, pp. 338--342.
C. Prahm, et al., “Echo State Networks as Novel Approach for Low-Cost Myoelectric Control”, Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017), A. ten Telje, et al., eds., Lecture Notes in Computer Science, vol. 10259, Springer, 2017, pp.338--342.
Prahm, C., Schulz, A., Paaßen, B., Aszmann, O., Hammer, B., Dorffner, G.: Echo State Networks as Novel Approach for Low-Cost Myoelectric Control. In: ten Telje, A., Popow, C., Holmes, J.H., and Sacchi, L. (eds.) Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017). Lecture Notes in Computer Science. 10259, p. 338--342. Springer (2017).
Prahm, Cosima, Schulz, Alexander, Paaßen, Benjamin, Aszmann, Oskar, Hammer, Barbara, and Dorffner, Georg. “Echo State Networks as Novel Approach for Low-Cost Myoelectric Control”. Proceedings of the 16th Conference on Artificial Intelligence in Medicine (AIME 2017). Ed. Annette ten Telje, Christian Popow, John H. Holmes, and Lucia Sacchi. Springer, 2017.Vol. 10259. Lecture Notes in Computer Science. 338--342.
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
2019-09-06T09:18:43Z
MD5 Prüfsumme
1439c996265a483aaa19fd05e108fab4
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:43Z
MD5 Prüfsumme
1439c996265a483aaa19fd05e108fab4

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar