Comparison of EMG Based Finger Motion Classification Algorithms


Altan E., Pehlivan K., KAPLANOĞLU E.

27th Signal Processing and Communications Applications Conference (SIU), Sivas, Türkiye, 24 - 26 Nisan 2019 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/siu.2019.8806331
  • Basıldığı Şehir: Sivas
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: EMG, Variance, SVM, KNN, Decision Tree
  • Marmara Üniversitesi Adresli: Evet

Özet

The electrical signs of the muscle cells in the human body are called myoelectric. EMG is the whole of the methods for obtaining and recording myoelectric signals in the human body. In this study, as pre-study of a myoelectric controlled prosthesis control, EMG signals that perceived from surface electrodes that were taken, processed and classified was performed. During the basic finger movement of the volunteers, the surface electrodes on the forearms and EMG signs of the flexor and extensor muscles were taken, amplified, digitized and transferred to the computer for analysis for classification. In MATLAB environment, finger movements are tried to be determined correctly by using Decision Tree, Support Vector Machine, K-Nearest Neighbors algorithms.