A bert based method for continuous estimation of cross-subject hand kinematics from surface electromyographic signals

HIGHLIGHTS

• who: -sEMG et al. from the (UNIVERSITY) have published the research work: A BERT based Method for Continuous Estimation of Cross-subject Hand Kinematics from Surface Electromyographic Signals, in the Journal: (JOURNAL)
• what: The authors propose a method based on Bidirectional Encoder Representation from Transformers (BERT) structure to predict the movement of hands from the root mean square (RMS) feature of the signal following u00b5-law normalization. Gradient Harmonizing Mechanism (GHM) and Online Hard Samples Mining (OHEM) are applied to make the models better learn from hard samples, and a smooth layer is applied to . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.