Show simple item record

dc.contributor.authorAkhundov, Riad
dc.contributor.authorSaxby, David J
dc.contributor.authorEdwards, Suzi
dc.contributor.authorSnodgrass, Suzanne
dc.contributor.authorClausen, Phil
dc.contributor.authorDiamond, Laura E
dc.date.accessioned2019-06-19T13:04:55Z
dc.date.available2019-06-19T13:04:55Z
dc.date.issued2019
dc.identifier.issn0022-0949
dc.identifier.doi10.1242/jeb.198101
dc.identifier.urihttp://hdl.handle.net/10072/383236
dc.description.abstractDetermining 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 (n=28,000), test performance (n=12,000) and evaluate accuracy (n=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.
dc.description.peerreviewedYes
dc.languageEnglish
dc.language.isoeng
dc.publisherCOMPANY BIOLOGISTS LTD
dc.publisher.urihttp://jeb.biologists.org/content/222/5/jeb198101
dc.relation.ispartofissue5
dc.relation.ispartofjournalJOURNAL OF EXPERIMENTAL BIOLOGY
dc.relation.ispartofvolume222
dc.subject.fieldofresearchBiological Sciences
dc.subject.fieldofresearchMedical and Health Sciences
dc.subject.fieldofresearchcode06
dc.subject.fieldofresearchcode11
dc.titleDevelopment of a deep neural network for automated electromyographic pattern classification
dc.typeJournal article
dc.type.descriptionC1 - Articles
dc.type.codeC - Journal Articles
gro.rights.copyrightSelf-archiving of the author-manuscript version is not yet supported by this journal. Please refer to the journal link for access to the definitive, published version or contact the author[s] for more information.
gro.hasfulltextNo Full Text
gro.griffith.authorSaxby, David J.
gro.griffith.authorDiamond, Laura


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Journal articles
    Contains articles published by Griffith authors in scholarly journals.

Show simple item record