ECG beat classification by a novel hybrid neural network and wavelet transform

Olmez T., Dokur Z.

IEEE-EMBS Asia-Pacific Conference on Biomedical Engineering, Hangzhou, Çin, 26 - 28 Eylül 2000, ss.718-719 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Hangzhou
  • Basıldığı Ülke: Çin
  • Sayfa Sayıları: ss.718-719
  • İstanbul Teknik Üniversitesi Adresli: Hayır

Özet

This paper presents a novel hybrid neural network structure for the classification of the electrocardiogram (ECG) beats. Two feature extraction methods: Fourier and wavelet analyses for ECG beat classification are comparatively investigated in 8 dimensional feature space. Classification performance, training time and the number of nodes of the multi-layer perceptron (MLP) and a novel hybrid neural network are comparatively presented. 10 types of ECG beats obtained from the MIT-BIH database and from a real-time ECG measurement system are classified with a success of 97% by using the hybrid neural network structure.