Trustworthy adaptation with few-shot learning for hand gesture recognition

Elahe Rahimian, Soheil Zabihi, Amir Asif, S. Farokh Atashzar, Arash Mohammadi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This work is motivated by potentials of Deep Neural Networks (DNNs)-based solutions in improving myoelectric control for trustworthy Human-Machine Interfacing (HMI). In this context, we propose the Trustworthy Few Shot-Hand Gesture Recognition (TFS-HGR) framework as a novel DNN-based architecture for performing Hand Gesture Recognition (HGR) via multi-channel surface Electromyography (sEMG) signals. The main objective of the TFS-HGR framework is to employ Few-Shot Learning (FSL) formulation with a focus on transferring information and knowledge between source and target domains (despite their inherit differences) to address limited availability of training data. The NinaPro DB5 dataset is used for evaluation purposes. The proposed TFS-HGR achieves a performance of 83.17% for new repetitions with few-shot observations, i.e., 5-way 10-shot classification. Moreover, the TFS-HGR with the accuracy of 75.29% also generalize to new gestures with few-shot observations, i.e., 5-way 10-shot classification.

Original languageEnglish (US)
Title of host publicationICAS 2021 - 2021 IEEE International Conference on Autonomous Systems, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728172897
DOIs
StatePublished - Aug 11 2021
Event2021 IEEE International Conference on Autonomous Systems, ICAS 2021 - Virtual, Montreal, Canada
Duration: Aug 11 2021Aug 13 2021

Publication series

NameICAS 2021 - 2021 IEEE International Conference on Autonomous Systems, Proceedings

Conference

Conference2021 IEEE International Conference on Autonomous Systems, ICAS 2021
Country/TerritoryCanada
CityVirtual, Montreal
Period8/11/218/13/21

Keywords

  • Attention Mechanism
  • Few-Shot Learning (FSL)
  • Hand Gesture Recognition (HGR)
  • Surface Electromyographic (sEMG)
  • Temporal Convolution

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Trustworthy adaptation with few-shot learning for hand gesture recognition'. Together they form a unique fingerprint.

Cite this