EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dual Stream Long Short-Term Memory Feature Fusion Classifier for Surface Electromyography Gesture Recognition

Kexin Zhang iD, Francisco J Badesa iD, Yinlong Liu iD, Manuel Ferre Pérez iD

Sensors · 04.06.2024 · 24 (11) · 3631

DOI: 10.3390/s24113631 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.06.2024. Verfasst von Kexin Zhang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Automation and Robotics (CAR) UPM-CSIC, Universidad Politécnica de Madrid (UPM), 28006 Madrid, Spain. Hauptthemen laut MEDLINE: Electromyography, Gestures, Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EXOSKELETON FOR LOAD MANIPULATION, Spanish “Ministerio de Ciencia e Innovación”.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gesture recognition using electromyography (EMG) signals has prevailed recently in the field of human–computer interactions for controlling intelligent prosthetics. Currently, machine learning and deep learning are the two most commonly employed methods for classifying hand gestures. Despite traditional machine learning methods already achieving impressive performance, it is still a huge amount of work to carry out feature extraction manually. The existing deep learning methods utilize complex neural network architectures to achieve higher accuracy, which will suffer from overfitting, insufficient adaptability, and low recognition accuracy. To improve the existing phenomenon, a novel lightweight model named dual stream LSTM feature fusion classifier is proposed based on the concatenation of five time-domain features of EMG signals and raw data, which are both processed with one-dimensional convolutional neural networks and LSTM layers to carry out the classification. The proposed method can effectively capture global features of EMG signals using a simple architecture, which means less computational cost. An experiment is conducted on a public DB1 dataset with 52 gestures, and each of the 27 subjects repeats every gesture 10 times. The accuracy rate achieved by the model is 89.66%, which is comparable to that achieved by more complex deep learning neural networks, and the inference time for each gesture is 87.6 ms, which can also be implied in a real-time control system. The proposed model is validated using a subject-wise experiment on 10 out of the 40 subjects in the DB2 dataset, achieving a mean accuracy of 91.74%. This is illustrated by its ability to fuse time-domain features and raw data to extract more effective information from the sEMG signal and select an appropriate, efficient, lightweight network to enhance the recognition results.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectromyographyGesturesNeural Networks, ComputerDeep LearningHumansSignal Processing, Computer-AssistedPattern Recognition, AutomatedAlgorithmsMachine LearningHand

Stichwörter der Autor:innen

deep learningdual stream LSTMfeature fusiongesture recognition

Autor:innen und Institutionen

  • Centre for Automation and Robotics (CAR) UPM-CSIC, Universidad Politécnica de Madrid (UPM), 28006 Madrid, Spain.
  • State Key Laboratory of Internet of Things for Smart City, University of Macao, Macao.

ORCID-Profile: Kexin Zhang, Francisco J Badesa, Yinlong Liu, Manuel Ferre Pérez

Förderung

  • EXOSKELETON FOR LOAD MANIPULATION
  • Spanish “Ministerio de Ciencia e Innovación”

Zitieren

APA

Zhang, K., Badesa, F. J., Liu, Y., & Ferre Pérez, M. (2024). Dual Stream Long Short-Term Memory Feature Fusion Classifier for Surface Electromyography Gesture Recognition. Sensors, 24(11), 3631. https://doi.org/10.3390/s24113631

Vancouver

Zhang K, Badesa FJ, Liu Y, Ferre Pérez M. Dual Stream Long Short-Term Memory Feature Fusion Classifier for Surface Electromyography Gesture Recognition. Sensors. 2024;24(11):3631. doi:10.3390/s24113631

BibTeX
@article{Zhang2024,
  author = {Zhang, Kexin and Badesa, Francisco J and Liu, Yinlong and Ferre Pérez, Manuel},
  title = {Dual Stream Long Short-Term Memory Feature Fusion Classifier for Surface Electromyography Gesture Recognition},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {11},
  pages = {3631},
  doi = {10.3390/s24113631}
}
Kostenlos starten →