Novel wearable HD-EMG sensor with shift-robust gesture recognition using deep learning

Simple item page
dc.contributor.authorChamberland, Félix
dc.contributor.authorButeau, Étienne
dc.contributor.authorTam, Simon
dc.contributor.authorCampbell, Evan
dc.contributor.authorMortazavi, Ali
dc.contributor.authorScheme, Erik
dc.contributor.authorFortier, Paul
dc.contributor.authorBoukadoum, Mounir
dc.contributor.authorCampeau-Lecours, Alexandre
dc.contributor.authorGosselin, Benoit
dc.date.accessioned2023-12-21T19:38:42Z
dc.date.available2023-12-21T19:38:42Z
dc.date.issued2023-09-11
dc.description.abstractIn this work, we present a hardware-software solution to improve the robustness of hand gesture recognition to confounding factors in myoelectric control. The solution includes a novel, full-circumference, flexible, 64-channel high-density electromyography (HD-EMG) sensor called EMaGer. The stretchable, wearable sensor adapts to different forearm sizes while maintaining uniform electrode density around the limb. Leveraging this uniformity, we propose novel array barrel-shifting data augmentation (ABSDA) approach used with a convolutional neural network (CNN), and an anti-aliased CNN (AA-CNN), that provides shift invariance around the limb for improved classification robustness to electrode movement, forearm orientation, and inter-session variability. Signals are sampled from a 4×16 HD-EMG array of electrodes at a frequency of 1 kHz and 16-bit resolution. Using data from 12 non-amputated participants, the approach is tested in response to sensor rotation, forearm rotation, and inter-session scenarios. The proposed ABSDA-CNN method improves inter-session accuracy by 25.67% on average across users for 6 gesture classes compared to conventional CNN classification. A comparison with other devices shows that this benefit is enabled by the unique design of the EMaGer array. The AA-CNN yields improvements of up to 63.05% accuracy over non-augmented methods when tested with electrode displacements ranging from −45 ∘ to +45 ∘ around the limb. Overall, this article demonstrates the benefits of co-designing sensor systems, processing methods, and inference algorithms to leverage synergistic and interdependent properties to solve state-of-the-art problems.
dc.description.copyright© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
dc.identifier.urihttps://unbscholar.lib.unb.ca/handle/1882/37618
dc.language.isoen
dc.publisherIEEE
dc.relationNatural Sciences and Engineering Research Council of Canada Alliance
dc.relationCanada Research Chair in Smart Biomedical Microsystems
dc.relationMicrosystems Strategic Alliance of Quebec
dc.relationQuebec Research Funds in Science and Technologies
dc.relation.hasversionhttps://doi.org/10.1109/TBCAS.2023.3314053
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.subject.disciplineElectrical and Computer Engineering
dc.titleNovel wearable HD-EMG sensor with shift-robust gesture recognition using deep learning
dc.typejournal article
oaire.citation.endPage984
oaire.citation.issue5
oaire.citation.startPage968
oaire.citation.titleIEEE Transactions on Biomedical Circuits and Systems
oaire.citation.volume17
oaire.license.conditionother
oaire.versionhttp://purl.org/coar/version/c_ab4af688f83e57aa

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Chamberland - IEEE TBioCAS, Final Submission (1).pdf
Size:
6.96 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.13 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Journal Articles