EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters

Irene Mendez Guerra iD, Deren Y Barsakcioglu iD, Dario Farina iD

Journal of Neural Engineering · 2024

DOI: 10.1088/1741-2552/ad5ebf ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neural Engineering, 2024. Verfasst von Irene Mendez Guerra und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioengineering, Imperial College London, London, United Kingdom. Hauptthemen laut MEDLINE: Electromyography. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Imperial-META Wearable Neural Interfaces Research Centre, Meta, EPSRC Centre for Doctoral Training in Neurotechnology for Life and Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 100 ms 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 % of the cases in 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectromyographyHumansMaleAdultAlgorithmsFemaleYoung AdultMuscle, SkeletalOnline SystemsMuscle ContractionMotor NeuronsMachine Learning

Stichwörter der Autor:innen

adaptive decompositiondynamic contractionsgradient independent component analysismotor unit action potential trackingmotor unitsreal-time decompositionwrist wearables

Autor:innen und Institutionen

  • Department of Bioengineering, Imperial College London, London, United Kingdom.

ORCID-Profile: Irene Mendez Guerra, Deren Y Barsakcioglu, Dario Farina

Förderung

  • Imperial-META Wearable Neural Interfaces Research Centre
  • Meta
  • EPSRC Centre for Doctoral Training in Neurotechnology for Life and Health
  • ERC Natural BionicS

Zitieren

APA

Mendez Guerra, I., Barsakcioglu, D. Y., & Farina, D. (2024). Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters. Journal of Neural Engineering. https://doi.org/10.1088/1741-2552/ad5ebf

Vancouver

Mendez Guerra I, Barsakcioglu DY, Farina D. Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters. Journal of Neural Engineering. 2024. doi:10.1088/1741-2552/ad5ebf

BibTeX
@article{MendezGuerra2024,
  author = {Mendez Guerra, Irene and Barsakcioglu, Deren Y and Farina, Dario},
  title = {Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters},
  journal = {Journal of Neural Engineering},
  year = {2024},
  doi = {10.1088/1741-2552/ad5ebf}
}
Kostenlos starten →