Skip to main navigation Skip to search Skip to main content

Improving Gesture Recognition by Bidirectional Temporal Convolutional Netwoks

  • Haoyu Chen*
  • , Yue Zhang
  • , Dalin Zhou
  • , Honghai Liu
  • *Corresponding author for this work
  • Zhejiang University of Technology
  • University of Portsmouth

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Surface electromyography (sEMG) based gesture recognition as an important role in Muscle-Computer interface has been researched for decades. Recently, deep learning based method has had a profound impact on this field. CNN, RNN and RNN-CNN based methods were studied by many researchers. Motivated by Bidirectional Long short-term memory (Bi-LSTM) and Temporal Convolutional Networks (TCN), we propose 1D CNN based networks called Bidirectional Temporal Convolutional Networks (Bi-TCN). The positive order signal and reverse order sEMG signal are feed to our networks to learn the different representation of the same sEMG signal. We evaluate proposed networks on two benchmark datasets, Ninapro DB1 and DB5. Our networks yields 90.74% prediction accuracy on DB1 and 90.06% prediction accuracy on DB5. The results demonstrate our networks is comparable to the state-of-the-art works.

Original languageEnglish
Title of host publicationRobotics and Rehabilitation Intelligence - First International Conference, ICRRI 2020, Proceedings
EditorsJianhua Qian, Honghai Liu, Dalin Zhou, Jiangtao Cao
PublisherSpringer Science and Business Media Deutschland GmbH
Pages413-424
Number of pages12
ISBN (Print)9789813349315
DOIs
StatePublished - 2020
Externally publishedYes
Event1st International Conference on Robotics and Rehabilitation Intelligence, ICRRI 2020 - Fushun, China
Duration: 9 Sep 202011 Sep 2020

Publication series

NameCommunications in Computer and Information Science
Volume1336
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference1st International Conference on Robotics and Rehabilitation Intelligence, ICRRI 2020
Country/TerritoryChina
CityFushun
Period9/09/2011/09/20

Keywords

  • CNN
  • Deep learning
  • Gesture recognition
  • LSTM
  • TCN
  • sEMG

Fingerprint

Dive into the research topics of 'Improving Gesture Recognition by Bidirectional Temporal Convolutional Netwoks'. Together they form a unique fingerprint.

Cite this