Learning regularized representations of categorically labelled surface EMG enables simultaneous and proportional myoelectric control

Alexander E Olsson,Christian Antfolk,Anders Björkman,Nebojša Malešević

doi:10.1186/s12984-021-00832-4

Abstract

BackgroundProcessing the surface electromyogram (sEMG) to decode movement intent is a promising approach for natural control of upper extremity prostheses. To this end, this paper introduces and evaluates a new framework which allows for simultaneous and proportional myoelectric control over multiple degrees of freedom (DoFs) in real-time. The framework uses multitask neural networks and domain-informed regularization in order to automatically find nonlinear mappings from the forearm sEMG envelope to multivariate and continuous encodings of concurrent hand- and wrist kinematics, despite only requiring categorical movement instruction stimuli signals for calibration.MethodsForearm sEMG with 8 channels was collected from healthy human subjects (N = 20) and used to calibrate two myoelectric control interfaces, each with two output DoFs. The interfaces were built from (I) the proposed framework, termed Myoelectric Representation Learning (MRL), and, to allow for comparisons, from (II) a standard pattern recognition framework based on Linear Discriminant Analysis (LDA). The online performances of both interfaces were assessed with a Fitts’s law type test generating 5 quantitative performance metrics. The temporal stabilities of the interfaces were evaluated by conducting identical tests without recalibration 7 days after the initial experiment session.ResultsMetric-wise two-way repeated measures ANOVA with factors method (MRL vs LDA) and session (day 1 vs day 7) revealed a significant (p<0.05) advantage for MRL over LDA in 5 out of 5 performance metrics, with metric-wise effect sizes (Cohen’s d) separating MRL from LDA ranging from left|dright|=0.62 to left|dright|=1.13. No significant effect on any metric was detected for neither session nor interaction between method and session, indicating that none of the methods deteriorated significantly in control efficacy during one week of intermission.ConclusionsThe results suggest that MRL is able to successfully generate stable mappings from EMG to kinematics, thereby enabling myoelectric control with real-time performance superior to that of the current commercial standard for pattern recognition (as represented by LDA). It is thus postulated that the presented MRL approach can be of practical utility for muscle-computer interfaces.

Highlights

Processing the surface electromyogram to decode movement intent is a promising approach for natural control of upper extremity prostheses
In order to aid in the pursuit of practical Muscle–computer interface (MCI) and to alleviate the limitations of available methods, this paper introduces a new set of methods aimed at achieving intuitive, proportional, and simultaneous myoelectric control
It is consistent with previous findings [66,67,68] to assume that subjects underwent continuous motor learning, which potentially obscures the effects of drift in EMG distribution, the results are encouraging in that they indicate that Myoelectric Representation Learning (MRL) does not require frequent recalibration in order to retain its advantages over the Linear Discriminant Analysis (LDA) approach

Summary

Introduction

Processing the surface electromyogram (sEMG) to decode movement intent is a promising approach for natural control of upper extremity prostheses. Most salient within the category of clinical applications is perhaps the field of hand- and wrist prosthetics, where myoelectrically controlled prostheses have been part of clinical routine since the 1960s [2] In this application, electromyography (EMG) signals are processed by an MCI and transformed into movement commands intended to modulate the behaviour of a powered actuator, i.e. a robotic replacement limb. The difference in some measure of intensity (e.g. signal magnitude) between the sEMG signals from the pair can thereafter be mapped directly to the force driving a single motorized degree of freedom (DoF) which is typically instantiated as the grasp aperture of a handreplacing gripper Within this framework, the additional DoFs possessed by multifunctional prostheses (which have recently become more available to hand- and arm amputees [4]) must be controlled sequentially by use of auxiliary protocols, e.g. based on co-contraction [5] or non-EMG inputs [6], for DoF switching. Disadvantages such as limited dexterity, lack of intuitiveness, and an associated cognitive burden have been observed among users [7]; these are thought to be among the main reasons for the high abandonment rates by which devices controlled in this way are afflicted [8]

Objectives

Methods

Results

Discussion

Conclusion