Transfer Learning for Rapid Re-calibration of a Myoelectric Prosthesis After Electrode Shift

Abstract

For decades, researchers have attempted to provide patients with an intuitive method to control upper limb prostheses, enabling them to manipulate multiple degrees of freedom continuously and simultaneously using only simple myoelectric signals. However, such controlling schemes are still highly vulnerable to disturbances in the myoelectric signal, due to electrode shifts, posture changes, sweat, fatigue etc. Recent research has demonstrated that such robustness problems can be alleviated by rapid re-calibration of the prosthesis once a day, using only very small amounts of training data (less than one minute of training time). In this contribution, we propose such a re-calibration scheme for a pattern recognition controller based on transfer learning. In a pilot study with able-bodied subjects we demonstrate that high controller accuracy can be re-obtained after strong electrode shift, even for simultaneous movements in multiple degrees of freedom.

Funding by the DFG under grant numbers HA2719/6-2 and HA2719/7-1, the CITEC center of excellence (EXC 277), as well as the Christian Doppler Research Foundation of the Austrian Federal Ministry of Science, Research and Economy is gratefully acknowledged.