The adaptive extended kalman filter approach for the Lotka-Volterra model and application to economic variables
SIGMA JOURNAL OF ENGINEERING AND NATURAL SCIENCES-SIGMA MUHENDISLIK VE FEN BILIMLERI DERGISI, sa.2, ss.390-398, 2024 (ESCI, Scopus)
- Yayın Türü: Makale / Tam Makale
- Basım Tarihi: 2024
- Doi Numarası: 10.14744/sigma.2024.0003737
- Dergi Adı: SIGMA JOURNAL OF ENGINEERING AND NATURAL SCIENCES-SIGMA MUHENDISLIK VE FEN BILIMLERI DERGISI
- Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus, Academic Search Premier, Directory of Open Access Journals
- Sayfa Sayıları: ss.390-398
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- İstanbul Üniversitesi Adresli: Evet
Özet
The main aim of this article is to extend on the application of the grey Lotka-Volterra model by Wu et al. [1] with a linear programming method. We used this method for estimating the parameters of behavioral variables under the criterion of the minimization of mean absolute percentage error (MAPE). Our empirical analysis indicates that the adaptive extended Kalman filter (EKF) approach performs far better compared to traditional Lotka-Volterra model in the prediction of the relevant parameters. Comparisons of empirical results with the linear programming method for parameter estimation of the grey Lotka-Volterra model demonstrate that the EKF approach has more powerful and efficient prediction performance.