Geographic Information Systems (GIS) and Random Forests Regression-Based Approach for Path Loss Prediction in the Campus Environment Kampüs Ortaminda Yol Kaybi Tahmini için Coǧrafi Bilgi Sistemleri (CBS) ve Rastgele Orman Regresyonu Tabanli Yaklaşim

Perihanoǧlu G. M., Karaman H.

31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023, İstanbul, Türkiye, 5 - 08 Temmuz 2023 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/siu59756.2023.10223770
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: Geographic information systems(GIS), Path loss model, Random forests regression
  • Van Yüzüncü Yıl Üniversitesi Adresli: Hayır

Özet

Estimation of path loss in communication systems is a fundamental requirement for designing any mobile or wireless communication system and assessing the quality of service. In this study, Random Forest machine regression algorithm and GIS based path loss estimation method for 1800 and 2100 MHz in Van Yüzüncü Yil University campus area are proposed. The goal of this model is to predict the coverage area, visualize the predicted signal path loss and analyze the field strength coverage. In order to increase the training efficiency of the model, the selected parameter values are structured according to the performance metrics. Based on the preliminary information obtained from the measured results, a series of training sets were created. According to the experimental results, it was observed that the Random Forest and GIS-based model performed effectively in different terrain classes for path loss estimation.