Real-time visual and EMG signals recognition to control dexterous prosthetic hand based on deep learning and machine learning

View Full Paper

Ask AI

Bookmark

Proposed method achieves 95% recognition accuracy in controlling prosthetic hands using EMG signals.
EMG signals collected from five healthy participants reached an accuracy of 89% using SVM analysis.
GoogLeNet algorithm successfully sorted 723 RGB images into seven gripping classes with 99% training accuracy.
The innovative Vision-EMG approach combines image recognition with myoelectric control for better prosthetic function.

Discussion

No takes yet. Share an insight, caveat, or question.

Experiment demonstrates effective classification of gripping patterns in prosthetic hands using EMG and image recognition.

Mahmood et al. (2021) studied this question.

View Full Paper

Ask AI

Bookmark