REDICTION OF JOINT ANGLE FROM MUSCLE ACTIVITIES DECODED FROM ELECTROCORTICOGRAMS

Duk Shin, Chao Chen, Yasuhiko Nakanishi, Hiroyuki Kambara, Natsue Yoshimura, Hidenori Watanabe, Atsushi Nambu, Tadashi Isa, Yukio Nishimura, Yasuharu Koike

Abstract

Electrocorticogram (ECoG) has drawn attention as an effective recording approach for less invasive brain-machine interfaces (BMI). Previous studies succeeded in classifying the movement direction or velocity from ECoGs. Despite such successful studies, there still remain considerable works for the purpose of realizing an ECoG-based BMI robot. Our previous study suggested and verified the method to predict multiple muscle activities from ECoG measurements. In this article, we predicted 4 DOF angle of arm from muscle activities decoded from ECoG signals. We also controlled 4 DOF robot arm using the predicted angle. Consequently, this study shows that it could derive online prediction of angle of arm from ECoG signals.

Keywords

brain machine interface, electrocorticogram, EMG

Download

IMEKO-TC18-2013-013.pdf.pdf

DOI

-

IMEKO TC

TC18 - Measurement of Human Functions

Back to the proceedings