Chip design for intelligent data classification algorithms and implementation on an FPGA: A case study to classify EMG signals Akilli veri̇ siniflandirma algori̇tmalari i̇çi̇n yonga tasarimi ve FPGA üzeri̇nde gerçekleme: EMG si̇nyalleri̇ni̇ siniflandirmak i̇çi̇n bi̇r durum çalişmasi

ALKIM E., Kılıç E.

2011 IEEE 19th Signal Processing and Communications Applications Conference, SIU 2011, Antalya, Türkiye, 20 - 22 Nisan 2011, ss.307-310 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu.2011.5929649
  • Basıldığı Şehir: Antalya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.307-310
  • Ondokuz Mayıs Üniversitesi Adresli: Evet

Özet

FPGA chips stand out with parallel processing capabilities. Besides this, artificial neural networks require parallel computing because of their algorithm. In this study, it is aimed to design an artificial neural network chip, the designed chip algorithm is implemented on an FPGA chip. Artificial neural network model is chosen as the Learning Vector Quantization (LVQ), and this model is used for the prediction of the four movements (up, down, open, close) from electromyogram (EMG) signals taken from the muscles. In order to create the chip, decision-making algorithm is developed firstly, and this algorithm is finally tested on the ALTERA DE2 demo board by using verilog HDL. © 2011 IEEE.