Recurrent Convolutional Neural Networks as an Approach to Position-Aware Myoelectric Prosthesis Control

• Published in: IEEE transactions on biomedical engineering 2022-07, Vol.69 (7), p.2243-2255
• Main Authors: Williams, Heather, Shehata, Ahmed W., Dawson, Michael, Scheme, Erik, Hebert, Jacqueline, Pilarski, Patrick
• Format: Article
• Language: English
• Subjects: Amputation; Arm; Artificial neural networks; Classifiers; Data models; Data transmission; Discriminant analysis; Electrodes; Electromyography; Feature extraction; Forearm; inertial measurement units; Inertial platforms; limb position effect; Limbs; myoelectric; Myoelectricity; Neural networks; pattern recognition; Predictive models; Prostheses; prosthesis; prosthesis control; Prosthetics; Recurrent convolutional neural networks; Regression analysis; Regression models; Support vector machines; Wrist
• ISSN: 0018-9294; 1558-2531
• DOI: 10.1109/TBME.2022.3140269

Objective: Persons with normal arm function can perform complex wrist and hand movements over a wide range of limb positions. However, for those with transradial amputation who use myoelectric prostheses, control across multiple limb positions can be challenging, frustrating, and can increase the likelihood of device abandonment. In response, the goal of this research was to investigate convolutional neural network (RCNN)-based position-aware myoelectric prosthesis control strategies. Methods: Surface electromyographic (EMG) and inertial measurement unit (IMU) signals, obtained from 16 non-disabled participants wearing two Myo armbands, served as inputs to RCNN classification and regression models. Such models predicted movements (wrist flexion/extension and forearm pronation/supination), based on a multi-limb-position training routine. RCNN classifiers and RCNN regressors were compared to linear discriminant analysis (LDA) classifiers and support vector regression (SVR) regressors, respectively. Outcomes were examined to determine whether RCNN-based control strategies could yield accurate movement predictions, while using the fewest number of available Myo armband data streams. Results: An RCNN classifier (trained with forearm EMG data, and forearm and upper arm IMU data) predicted movements with 99.00% accuracy (versus the LDA's 97.67%). An RCNN regressor (trained with forearm EMG and IMU data) predicted movements with R 2 values of 84.93% for wrist flexion/extension and 84.97% for forearm pronation/supination (versus the SVR's 77.26% and 60.73%, respectively). The control strategies that employed these models required fewer than all available data streams. Conclusion: RCNN-based control strategies offer novel means of mitigating limb position challenges. Significance: This research furthers the development of improved position-aware myoelectric prosthesis control.