Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters
File(s)
Published version
Author(s)
Guerra, Irene Mendez
Barsakcioglu, Deren Y
Farina, Dario
Type
Journal Article
Abstract
Objective. Developing neural decoders robust to non-stationary conditions is essential to ensure their long-term accuracy and stability. This is particularly important when decoding the neural drive to muscles during dynamic contractions, which pose significant challenges for stationary decoders. Approach. We propose a novel adaptive electromyography (EMG) decomposition algorithm that builds on blind source separation methods by leveraging the Kullback–Leibler
divergence and kurtosis of the signals as metrics for online learning. The proposed approach provides a theoretical framework to tune the adaptation hyperparameters and compensate for non-stationarities in the mixing matrix, such as due to dynamic contractions, and to identify the underlying motor neuron (MN) discharges. The adaptation is performed in real-time (∼22 ms of computational time per 100ms batches). Main results. The hyperparameters of the proposed adaptation captured anatomical differences between recording locations (forearm vs wrist) and
generalised across subjects. Once optimised, the proposed adaptation algorithm significantly
improved all decomposition performance metrics with respect to the absence of adaptation in a wide range of motion of the wrist (80◦). The rate of agreement, sensitivity, and precision were ⩾90%in⩾80%ofthecasesin both simulated and experimentally recorded data, according to a
two-source validation approach. Significance. The findings demonstrate the suitability of the proposed online learning metrics and hyperparameter optimisation to compensate the induced modulation and accurately decode MN discharges in dynamic conditions. Moreover, the study proposes an experimental validation method for EMG decomposition in dynamic tasks.
divergence and kurtosis of the signals as metrics for online learning. The proposed approach provides a theoretical framework to tune the adaptation hyperparameters and compensate for non-stationarities in the mixing matrix, such as due to dynamic contractions, and to identify the underlying motor neuron (MN) discharges. The adaptation is performed in real-time (∼22 ms of computational time per 100ms batches). Main results. The hyperparameters of the proposed adaptation captured anatomical differences between recording locations (forearm vs wrist) and
generalised across subjects. Once optimised, the proposed adaptation algorithm significantly
improved all decomposition performance metrics with respect to the absence of adaptation in a wide range of motion of the wrist (80◦). The rate of agreement, sensitivity, and precision were ⩾90%in⩾80%ofthecasesin both simulated and experimentally recorded data, according to a
two-source validation approach. Significance. The findings demonstrate the suitability of the proposed online learning metrics and hyperparameter optimisation to compensate the induced modulation and accurately decode MN discharges in dynamic conditions. Moreover, the study proposes an experimental validation method for EMG decomposition in dynamic tasks.
Date Issued
2024-08-01
Date Acceptance
2024-07-03
Citation
Journal of Neural Engineering, 2024, 21 (4)
ISSN
1741-2560
Publisher
IOP Publishing
Journal / Book Title
Journal of Neural Engineering
Volume
21
Issue
4
Copyright Statement
©2024 The Author(s). Published by IOP Publishing Ltd Original Content from this work may be used under the terms of the Creative Commons Attribution 4.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/38959878
Subjects
adaptive decomposition
BLIND SOURCE SEPARATION
CONDUCTION-VELOCITY
DENSITY SURFACE EMG
dynamic contractions
Engineering
Engineering, Biomedical
gradient independent component analysis
IDENTIFICATION
Life Sciences & Biomedicine
MODEL
motor unit action potential tracking
MOTOR UNIT DISCHARGES
motor units
MUSCLE
Neurosciences
Neurosciences & Neurology
POTENTIALS
real-time decomposition
Science & Technology
SIZE
Technology
wrist wearables
Publication Status
Published
Coverage Spatial
England
Article Number
046023
Date Publish Online
2024-07-29