Toward More Robust Hand Gesture Recognition on EIT Data

Leins D, Gibas C, Brück R, Haschke R (2021)
Frontiers in Neurorobotics 15: 659311.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
OA 4.26 MB
Autor*in
Leins, DavidUniBi ; Gibas, Christian; Brück, Rainer; Haschke, RobertUniBi
Abstract / Bemerkung
Striving for more robust and natural control of multi-fingered hand prostheses, we are studying electrical impedance tomography (EIT) as a method to monitor residual muscle activations. Previous work has shown promising results for hand gesture recognition, but also lacks generalization across multiple sessions and users. Thus, the present paper aims for a detailed analysis of an existing EIT dataset acquired with a 16-electrode wrist band as a prerequisite for further improvements of machine learning results on this type of signal. The performed t-SNE analysis confirms a much stronger inter-session and inter-user variance compared to the expected in-class variance. Additionally, we observe a strong drift of signals within a session. To handle these challenging problems, we propose new machine learning architectures based on deep learning, which allow to separate undesired from desired variation and thus significantly improve the classification accuracy. With these new architectures we increased cross-session classification accuracy on 12 gestures from 19.55 to 30.45%. Based on a fundamental data analysis we developed three calibration methods and thus were able to further increase cross-session classification accuracy to 39.01, 55.37, and 56.34%, respectively.
Stichworte
electrical impedance tomography; gesture recognition; artificial intelligence; neural networks; deep learning; data analysis
Erscheinungsjahr
2021
Zeitschriftentitel
Frontiers in Neurorobotics
Band
15
Art.-Nr.
659311
eISSN
1662-5218
Finanzierungs-Informationen
Open-Access-Publikationskosten wurden durch die Universität Bielefeld gefördert.
Page URI
https://pub.uni-bielefeld.de/record/2956810

Zitieren

Leins D, Gibas C, Brück R, Haschke R. Toward More Robust Hand Gesture Recognition on EIT Data. Frontiers in Neurorobotics. 2021;15: 659311.
Leins, D., Gibas, C., Brück, R., & Haschke, R. (2021). Toward More Robust Hand Gesture Recognition on EIT Data. Frontiers in Neurorobotics, 15, 659311. https://doi.org/10.3389/fnbot.2021.659311
Leins, D., Gibas, C., Brück, R., and Haschke, R. (2021). Toward More Robust Hand Gesture Recognition on EIT Data. Frontiers in Neurorobotics 15:659311.
Leins, D., et al., 2021. Toward More Robust Hand Gesture Recognition on EIT Data. Frontiers in Neurorobotics, 15: 659311.
D. Leins, et al., “Toward More Robust Hand Gesture Recognition on EIT Data”, Frontiers in Neurorobotics, vol. 15, 2021, : 659311.
Leins, D., Gibas, C., Brück, R., Haschke, R.: Toward More Robust Hand Gesture Recognition on EIT Data. Frontiers in Neurorobotics. 15, : 659311 (2021).
Leins, David, Gibas, Christian, Brück, Rainer, and Haschke, Robert. “Toward More Robust Hand Gesture Recognition on EIT Data”. Frontiers in Neurorobotics 15 (2021): 659311.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Creative Commons Namensnennung 4.0 International Public License (CC-BY 4.0):
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2021-08-19T05:46:51Z
MD5 Prüfsumme
ffe8f687da8b17bf3c4d965e4d1ad532

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 34456704
PubMed | Europe PMC

Suchen in

Google Scholar