MULTI-STAGE ANN EMBEDDED PARAMETER ESTIMATION FOR STOCHASTIC EPIDEMIC MODELS
Far East Journal of Theoretical Statistics · 01.07.2026 · 70 (2) · 293-337
DOI: 10.17654/0972086326015 ↗Kurz gefasst
Fachartikel in der Zeitschrift Far East Journal of Theoretical Statistics, online erschienen am 01.07.2026. Verfasst von Mokaedi V. Lekgari und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
A novel three-stage procedure is proposed for parameter estimation of various stochastic epidemic models. Based on branching processes theory and stochastic numerical calculus, the derivations of the stochastic models are considered. Branching processes theory is used to derive Markov chain models while numerical calculus is used for continuous stochastic models. Artificial neural networks are then employed to characterize the nonlinear interactions and co-dependencies between time datasets and state variables’ datasets. Thus, artificial neural networks are integrated into the stochastic models to create the desirable continuous state space trajectories to overcome the time variable mismatches between model solutions and data, enabling parameter estimation through basic traditional parameter estimation techniques. Even though the proposed procedure is computationally costly, its advantage is that it simplifies parameter estimation of all stochastic epidemic models. The applicability of the proposed technique is transferable to all stochastic models.
Zitieren
APA
Lekgari, M. V., & Mapharing, T. (2026). MULTI-STAGE ANN EMBEDDED PARAMETER ESTIMATION FOR STOCHASTIC EPIDEMIC MODELS. Far East Journal of Theoretical Statistics, 70(2), 293-337. https://doi.org/10.17654/0972086326015
Vancouver
Lekgari MV, Mapharing T. MULTI-STAGE ANN EMBEDDED PARAMETER ESTIMATION FOR STOCHASTIC EPIDEMIC MODELS. Far East Journal of Theoretical Statistics. 2026;70(2):293-337. doi:10.17654/0972086326015
BibTeX
@article{Lekgari2026,
author = {Lekgari, Mokaedi V. and Mapharing, Thabang},
title = {MULTI-STAGE ANN EMBEDDED PARAMETER ESTIMATION FOR STOCHASTIC EPIDEMIC MODELS},
journal = {Far East Journal of Theoretical Statistics},
year = {2026},
volume = {70},
number = {2},
pages = {293--337},
doi = {10.17654/0972086326015}
}
EUVIMED