Multi-grip classification-based prosthesis control with two sensors
Agamemnon Krasoulis, Sethu Vijayakumar, and Kianoush Nazarpour
Received Date: 3rd April 19
In the field of upper-limb myoelectric prosthesis control, the use of statistical and machine learning methods has been long proposed as a means of enabling intuitive grip selection and activation; yet, clinical adoption remains rather limited. One of the main causes hindering clinical translation of machine learning-based prosthesis control is the requirement for a large number of electromyography (EMG) sensors. Here, we propose an end-to-end strategy for multi-grip, classification-based prosthesis control using only two sensors, comprising EMG electrodes and inertial measurement units (IMUs). We emphasisethe importance of accurately estimating posterior class probabilities and rejecting predictions made with low confidence, so as to minimise the rate of unintended prosthesis activations. To that end, we propose a confidence-based error rejection strategy using grip-specific thresholds. We evaluate the efficacy of the proposed system with real-time pick and place experiments using a commercial multi-articulated prosthetic hand and involving 12 able-bodied and two transradial (i.e., below-elbow) amputee participants. Results promise the potential for deploying intuitive, classification-based multi-grip control in existing upper-limb prosthetic systems.
Read in full at bioRxiv.
This is an abstract of a preprint hosted on an independent third party site. It has not been peer reviewed but is currently under consideration at Nature Communications.