Feature weighting concatenated multi-head self-attention for amputee EMG classification

Basit Öğe Kaydı
dc.authorid0000-0003-4236-3646
dc.contributor.authorBilgin, Metin
dc.contributor.authorMert, Ahmet
dc.date.accessioned2026-02-08T15:15:09Z
dc.date.available2026-02-08T15:15:09Z
dc.date.issued2025
dc.departmentBursa Teknik Üniversitesi
dc.description.abstractReliefF and neighborhood component analysis (NCA) concatenated multi-head self-attention (MSA) based multi-channel amputee EMG signals classification model is proposed in this paper. It is inspired by the Transformer and Vision Transformer models, and designed to be lightweight for prosthetic applications. The ReliefF and NCA layers are integrated to the MSA for class separability concatenation of 8-channel EMG signals. The contribution as weight concatenation is performed on publicly available amputee dataset, and the effects of ReliefF and NCA are compared to the conventional MSA architecture against varying contraction levels. Six hand gestures with three contraction levels are recognized using the popular features of waveform length (WL) and root mean square (RMS) depending on three evaluation schemes (within the same force level, unseen level and all levels). The proposed class separability concatenation yields up to 2.08% increase rates when compared to the conventional MSA model.
dc.identifier.doi10.1016/j.bspc.2024.107402
dc.identifier.issn1746-8094
dc.identifier.issn1746-8108
dc.identifier.scopus2-s2.0-85213060760
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.bspc.2024.107402
dc.identifier.urihttps://hdl.handle.net/20.500.12885/5633
dc.identifier.volume103
dc.identifier.wosWOS:001401407100001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier Sci Ltd
dc.relation.ispartofBiomedical Signal Processing and Control
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzWOS_KA_20260207
dc.subjectHuman-machine interaction
dc.subjectSelf-attention
dc.subjectFeature ranking
dc.subjectDeep learning
dc.subjectProsthetic hand control
dc.subjectElectromyography
dc.titleFeature weighting concatenated multi-head self-attention for amputee EMG classification
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu