Classification of Normal Beat, Atrial Premature Contraction and Ventricular Premature Contraction Based on Discrete Wavelet Transform and Artificial Neural Networks

Akin Z. E., BİLGİN S.

Medical Technologies National Congress (TIPTEKNO), Trabzon, Türkiye, 12 - 14 Ekim 2017 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/tiptekno.2017.8238027
  • Basıldığı Şehir: Trabzon
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: Electrocardiogram, Normal Beat, Atrial Premature Contraction, Ventricular Premature Contraction, Discrete Wavelet Transform, Automatic Detection, TIME, ECG
  • Akdeniz Üniversitesi Adresli: Evet

Özet

Analysis and evaluation of ECG (Electrocardiogram) signals is one of the important methods used in the determination of heart diseases. Since the interpretation of ECG signals is a time consuming and demanding process for physicians, detailed analysis and interpretation software that gives the same result as the diagnosis of the physician at high rates by interpreting these signals in the computer environment is being developed and its usage is increasing. In this study, automatic detection of Normal Beat (NOR), APC (Atrial Premature Contraction) and PVC (Ventricular Premature Contraction) arrhythmia was studied and it was aimed to catch the points that the physician would avoid from the eye and to facilitate the treatment. In the study, the energy of the pulses was calculated, analyzed with Discrete Wavelet Transform (DWT) and classified according to Linear Discriminant Analysis (LDA).