Toward More Robust Hand Gesture Recognition on EIT Data

Frontiers in Neurorobotics

Rainer Brück¹  Christian Gibas¹  Robert Haschke²  David P. Leins² 

[1] Medical Informatics and Microsytems Engineering, Faculty of Life Sciences, University of Siegen, Siegen, Germany;Research Institute Cognitive Interaction Technology, Bielefeld University, Bielefeld, Germany;

关键词: electrical impedance tomography;    gesture recognition;    artificial intelligence;    neural networks;    deep learning;    data analysis;   

DOI  :  10.3389/fnbot.2021.659311

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown