[17a-A33-1~11] FS.1 Focused Session "AI Electronics"

10:45 AM - 11:00 AM JST(1:45 AM - 2:00 AM UTC)

[17a-A33-7] Analysis on Surface Myoelectric Signal and Motion Inference Utilizing Reservoir Computing Framework

〇Yusuke Hoshika¹, Seiya Kasai¹ (1.Hokkaido Univ.)

Keywords:

Myoelectric prosthesis hand,Surface myoelectric signal analysis,Reservoir computing

An big issue in a myoelectric prosthetic hand is poor controllability, which is attributed to the difficulty in readout of the intended motion from complicated surface myoelectric signals. Here, we consider that the complicated signals correspond to the output signal from the reservoir layer in a reservoir computing system. Then, the intended motion could be reproduced by linear combination of the myoelectric signals induced from multiple electrode positions. We made a setup for verification of our hypothesis by integrating eight surface myoelectric signal detectors on the forearm and an accelerometer on the back of a hand. We could demonstrate reasonable inference of the hand motion in our system.