Comparison of Using the Genetic Algorithm and Cuckoo Search for Feature Selection

Kaya Y.

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
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

We compared the performance of BCSA and GA for feature selection in this study. We used the Sonar Database from the UCI Machine in the experiments. The Sonar database has 60 attributes. Twenty-five features were specified using BCSA and 27 features were specified using GA. Classification accuracy of BCSA, GA, and all features were 99.04, 96.15 and 79.81, respectively. BCSA has achieved the most successful results in the study.