Classification of Aerial Targets Based On Deep Learning


Creative Commons License

Kurt E., Başkaya K.

5. Interdisciplinary Conference on Electrics and Computer (INTCEC), Illinois, Amerika Birleşik Devletleri, 15 - 16 Eylül 2025, ss.1-6, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/intcec65580.2025.11255680
  • Basıldığı Şehir: Illinois
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.1-6
  • Gazi Üniversitesi Adresli: Evet

Özet

In this study, the effectiveness of deep learning

methods in the classification of aerial targets is investigated. By

analyzing flight data parameters such as radar cross section,

velocity and altitude obtained from surveillance radars, the

results of artificial neural networks, convolutional neural

networks and recurrent neural networks models are compared.

The results obtained via MATLAB show that deep learning

models provide superior accuracy and reliability in

distinguishing between various target classes, highlighting their

potential for applications in air traffic management and

military defense systems. In particular, the accuracy rate

91.11% has been obtained as a result of the simulation

conducted with artificial neural networks model is presented as

a promising development for artificial intelligence-based target

classification.