Pareto Front Estimation in Multi-Objective Optimization for Signal Separation Isaret Ayristirma i in ok Ama li Optimizasyonda Pareto Cephesi Tahmini

ÇELİK H., KARABOĞA N.

2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023, Sivas, Türkiye, 11 - 13 Ekim 2023 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/asyu58738.2023.10296583
  • Basıldığı Şehir: Sivas
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: blind source separation, EEG, multi-objective optimization, Pareto, strength Pareto evolutionary algorithm
  • Erciyes Üniversitesi Adresli: Evet

Özet

For the correct interpretation of the diagnosis of the disease, the electrical activity of the human brain must be recorded without noise. When this situation is sometimes difficult, separation should be done for the recorded noisy EEG signals. For this process, mixed signals can be separated by optimizing the blind source separation process with multi-objective optimization algorithms. In this study, Strength Pareto Evolutionary Algorithm, which takes into account both the quality and diversity of the solutions, has been used as a multi-objective optimization method. In this algorithm, a new method is proposed for the estimation of the Pareto curve and the results are measured with the SNR value.