Cardiac Arrhythmia Multiclass Classification

EMG-based Hand Gesture Recognition using Deep Learning Model


  •   The aim is to enhance the quality of the recorded sEMG signal by implementing a novel technique that eliminates composite noise even when the input SNR is low.
  •   A model based on deep learning techniques will be suggested to recognize hand gestures.
  •   A method for extracting features from EMG signals has been suggested.
  •   Using an optimization algorithm to find the best Q-factor.
  •   Enhancing the ability to identify gestures with greater accuracy and precision while reducing the computational time required.
  •   The effectiveness of the suggested model has been demonstrated through a comparison with other advanced techniques.

  • Description

The field of human-computer interaction has seen significant advancements in hand gesture-based systems, which are continuously improving and proving to be highly effective. The sEMG signal is a commonly utilized signal that results from muscle activation, despite its intricate nature. The myoelectric control is the term used for the applications of sEMG signals, which are mainly used to activate a device. It should be noted that feedback is not always utilized in this process, despite the term "control" implying otherwise.