Predicting Polarization Converter Transmittance Performance Using Machine Learning Makine Ö?grenmesi Kullanarak Polarizasyon Dönüştürücü Geçirgenlik Performansini Tahmin Etme
34th Signal Processing and Communications Applications Conference, SIU 2026, İstanbul, Türkiye, 7 - 10 Temmuz 2026, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu71813.2026.11636829
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: electromagnetic waves, machine learning, metamaterial design, polarization converter
- Kocaeli Üniversitesi Adresli: Evet
Özet
Metamaterials are used in many fields, including polarization converter design. In this study, five different machine learning algorithms were used to predict the transmittance performance of polarization converters. The disadvantages created by numerical-based methods have necessitated the use of alternative methods in metamaterial design. In this regard, machine learning methods have provided an opportunity for design. In the current study, predicting polarization converter transmittance performance of Linear Regression (LR), Extreme Gradient Boosting (XGBoost), Decision Tree (DT), Random Forest (RF), and Bagging Regression models are presented. The XGBoost Regression model showed the best performance for both Tyy and Tyx.