Abstract
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. 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. 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 R2 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. RCNN-based control strategies offer novel means of mitigating limb position challenges. This research furthers the development of improved position-aware myoelectric prosthesis control.
Highlights
Myoelectric prostheses are designed to restore lost upper limb motor function for individuals with amputation
This study identified two promising recurrent convolutional neural network (RCNN)-based myoelectric prosthesis control strategies that were found to be consistently accurate across multiple limb positions
In addition to yielding the highest prediction accuracies, both the RCNN and linear discriminant analysis (LDA) classifiers resulted in decreased training times when only accelerometer data were used (RCNN: 1.68 minutes, LDA: 38.48 milliseconds) versus when all data streams were used (RCNN: 2.52 minutes, LDA: 89.19 milliseconds)
Summary
Myoelectric prostheses are designed to restore lost upper limb motor function for individuals with amputation. Researchers have developed control strategies that use pattern recognition models to predict and execute a user’s movement intent [1]. Despite yielding reliable device movements in research environments, precise decoding of movement intent from EMG signals can be unreliable when a wide range of limb positions are introduced by users during daily activities [3]. This significant challenge to myoelectric prosthesis control is known as the "limb position effect" [4]. Resulting EMG signal variations can cause prosthesis control to degrade and unexpected prosthetic wrist and hand movements to occur.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
