Dielectric Constant Estimation of GPR Signals Using Wavelet-Based Feature Extraction

Creative Commons License

Uslu S., Helhel S., Bilgin S.

International Conference on Next-Generation Engineering Technologies (ISNET'2025), Antalya, Türkiye, 30 Ekim - 01 Kasım 2025, ss.44-45, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Basıldığı Şehir: Antalya
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.44-45
  • Akdeniz Üniversitesi Adresli: Evet

Özet

In this study, wavelet-based feature extraction was performed by generating synthetic signals to estimate the dielectric constants of underground structures. Two signals were generated: the first one is a two-layered single signal, and the other one is four two-layered signals with four different dielectric constants. CWT (Continuous Wavelet Transform) was applied to all generated signals. RMS, entropy, energy, and dominant frequency features were extracted, and the synthetic signals with four different dielectric constants were inserted into the developed regression model.