Detection of Fetal Reactions to Maternal Voice Using Doppler Ultrasound Signals

Tastan A., HARDALAÇ N., Kavak S. B., HARDALAÇ F.

International Conference on Artificial Intelligence and Data Processing (IDAP), Malatya, Türkiye, 28 - 30 Eylül 2018 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Basıldığı Şehir: Malatya
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: Doppler ultrasound, fetal learning, prenatal, fetus, maternal voice, wavelet, DWT, fourier transform, FFT, power spectrum, FFT, AR
  • Gazi Üniversitesi Adresli: Evet

Özet

In this work, blood flow data which were taken from middle cerebral artery(MCA) was recorded using Doppler Ultrasonography from 30 healthy individuals at 37-40 weeks gestation age who came to Firat University Faculty of Medicine Hospital Gynecology and Obstetrics Department. Fetal blood flow data were taken seperately for each condition that female and maternal individuals were singing the lullaby during 2 minutes and non-stimulating. Recorded Doppler signals were processed with fast Fourier transform(FFT) and discrete wavelet transform(DWT) methods to understand whether fetus has sensitivity to maternal voice or not. Furthermore, achievements of FFT and DWT methods researched by comparing their results. Power spectral density(PSD)-frequency changes observed in both method. As a consequence of this work, fetus gave noticeably reactions to maternal voice in 3000-4000 and 800010000 frequency bands. This sensitivity to maternal voice can prove that fetus has a learning process with experience in uterus.