Design Of a Neural Modelling Scheme For Gait Temporal Features

Can E., YILMAZ A.

IEEE 17th Signal Processing and Communications Applications Conference, Antalya, Türkiye, 9 - 11 Nisan 2009, ss.798-801 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/siu.2009.5136460
  • Basıldığı Şehir: Antalya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.798-801
  • Hacettepe Üniversitesi Adresli: Evet

Özet

This paper represents an artifical neural network that captures knee angle variations for adult gait scenerios. Back propogation algorithm is used to train the neural network. The data set that are needed for training have been obtained artificially. Gait cycle is analysed in eight different phases. With the neural network model, the phase and the subsequent angle value are predicted. The suggested neural network model is trained for different inclinations and walking speed, the results are recorded and discussed.