Abstract
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.
Highlights
In the past decades, we have seen tremendous progress in the development of bionic hands and other prosthetic devices providing multiple, self-powered degrees of freedom to restore lost dexterity for upper-limb amputees
Maybe the most advanced example nowadays, is the Luke Arm1, which is the commercial version of the Modular Prosthetic Limb (MPL) providing up to 26 articulating degrees of freedom (DOF) via 17 actuators from shoulder to hand and sensory feedback via vibrotactile sensors (Perry et al, 2018)
Electric prosthetic devices are controlled via surface electromyography, where the electrical activity of surface muscles is recorded from electrodes attached to the skin (Farina et al, 2014)
Summary
We have seen tremendous progress in the development of bionic hands and other prosthetic devices providing multiple, self-powered degrees of freedom to restore lost dexterity for upper-limb amputees. Electric prosthetic devices are controlled via surface electromyography (sEMG), where the electrical activity of surface muscles is recorded from electrodes attached to the skin (Farina et al, 2014). These electrodes are only passive sensors, which amplify the body’s own electrical activity. Non-invasive approach that promised to overcome this limitation was tactile myography: a high-resolution array of tactile force sensors, worn as a bracelet around the forearm, is measuring the bulging of muscles with up to 320 tactile cells (Kõiva et al, 2015). A limitation common to both of these approaches is their restriction to the surface
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
