Development of a deep neural network for automated electromyographic pattern classification.

Journal: The Journal of experimental biology
Published Date:

Abstract

Determining the signal quality of surface electromyography (sEMG) recordings is time consuming and requires the judgement of trained observers. An automated procedure to evaluate sEMG quality would streamline data processing and reduce time demands. This paper compares the performance of two supervised and three unsupervised artificial neural networks (ANNs) in the evaluation of sEMG quality. Manually classified sEMG recordings from various lower-limb muscles during motor tasks were used to train (=28,000), test performance (=12,000) and evaluate accuracy (=47,000) of the five ANNs in classifying signals into four categories. Unsupervised ANNs demonstrated a 30-40% increase in classification accuracy (>98%) compared with supervised ANNs. AlexNet demonstrated the highest accuracy (99.55%) with negligible false classifications. The results indicate that sEMG quality evaluation can be automated via an ANN without compromising human-like classification accuracy. This classifier will be publicly available and will be a valuable tool for researchers and clinicians using electromyography.

Authors

  • Riad Akhundov
    Gold Coast Orthopaedics Research, Engineering & Education Alliance (GCORE), Menzies Health Institute Queensland, Griffith University, QLD 4222, Australia riad.akhundov@uon.edu.au.
  • David J Saxby
    Gold Coast Orthopaedics Research, Engineering & Education Alliance (GCORE), Menzies Health Institute Queensland, Griffith University, QLD 4222, Australia.
  • Suzi Edwards
    School of Environment and Life Sciences, University of Newcastle, Ourimbah, NSW 2258, Australia.
  • Suzanne Snodgrass
    School of Health Sciences, University of Newcastle, Callaghan, NSW 2308, Australia.
  • Phil Clausen
    School of Engineering, University of Newcastle, Callaghan, NSW 2308, Australia.
  • Laura E Diamond
    Gold Coast Orthopaedics Research, Engineering & Education Alliance (GCORE), Menzies Health Institute Queensland, Griffith University, QLD 4222, Australia.