EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Surface EMG-Based Hand Gesture Recognition Using a Hybrid Multistream Deep Learning Architecture

Yusuf Çelik iD, Umit Can iD

Sensors · 07.04.2026 · 26 (7) · 2281

DOI: 10.3390/s26072281 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.04.2026. Verfasst von Yusuf Çelik und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computer Engineering Department, Munzur University, 62000 Tunceli, Turkey. Hauptthemen laut MEDLINE: Electromyography, Gestures, Deep Learning, Hand. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Surface electromyography (sEMG) enables non-invasive measurement of muscle activity for applications such as human–machine interaction, rehabilitation, and prosthesis control. However, high noise levels, inter-subject variability, and the complex nature of muscle activation hinder robust gesture classification. This study proposes a multistream hybrid deep-learning architecture for the FORS-EMG dataset to address these challenges. The model integrates Temporal Convolutional Networks (TCN), depthwise separable convolutions, bidirectional Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) layers, and a Transformer encoder to capture complementary temporal and spectral patterns, and an ArcFace-based classifier to enhance class separability. We evaluate the approach under three protocols: subject-wise, random split without augmentation, and random split with augmentation. In the augmented random-split setting, the model attains 96.4% accuracy, surpassing previously reported values. In the subject-wise setting, accuracy is 74%, revealing limited cross-user generalization. The results demonstrate the method’s high performance and highlight the impact of data-partition strategies for real-world sEMG-based gesture recognition.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectromyographyGesturesDeep LearningHandHumansLong Short Term MemoryPattern Recognition, AutomatedSignal Processing, Computer-AssistedAlgorithmsConvolutional Neural Networks

Stichwörter der Autor:innen

biometric signal processingdeep learninghand gesture recognitionsurface electromyography

Autor:innen und Institutionen

  • Computer Engineering Department, Munzur University, 62000 Tunceli, Turkey.

ORCID-Profile: Yusuf Çelik, Umit Can

Zitieren

APA

Çelik, Y., & Can, U. (2026). Surface EMG-Based Hand Gesture Recognition Using a Hybrid Multistream Deep Learning Architecture. Sensors, 26(7), 2281. https://doi.org/10.3390/s26072281

Vancouver

Çelik Y, Can U. Surface EMG-Based Hand Gesture Recognition Using a Hybrid Multistream Deep Learning Architecture. Sensors. 2026;26(7):2281. doi:10.3390/s26072281

BibTeX
@article{elik2026,
  author = {Çelik, Yusuf and Can, Umit},
  title = {Surface EMG-Based Hand Gesture Recognition Using a Hybrid Multistream Deep Learning Architecture},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {7},
  pages = {2281},
  doi = {10.3390/s26072281}
}
Kostenlos starten →