Evolutionary game theory to predict the population growth in Few districts of Tamil Nadu and Kerala

The conventional models in Game Theory focuses entirely on the relative fitness of the population agents leaving the dynamic behaviour of the size of population left uncovered. Therefore, a robust model is required to combine both the growth dynamics and internal evolution of agents. Evolutionary Ga...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Measurement. Sensors Jg. 27; S. 100736
Hauptverfasser: N, Kalaivani, Visalakshidevi, E. Mona
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.06.2023
Elsevier
Schlagworte:
ISSN:2665-9174, 2665-9174
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The conventional models in Game Theory focuses entirely on the relative fitness of the population agents leaving the dynamic behaviour of the size of population left uncovered. Therefore, a robust model is required to combine both the growth dynamics and internal evolution of agents. Evolutionary Game Theory to Predict the Population Growth in Few Districts of Tamil Nadu and Kerala. In this paper, we develop an Evolutionary Game Theory (EGT) model which is integrated with the Residual deterministic learning (RDL) model to increase the rate of prediction of the population growth. Various deterministic models including Arithmetic Increase, Geometric Increase, Incremental Increase and Simple graphical models are used to improve the prediction ability of EGT. The EGT combined with RDL forms REGT model that is found scalable to predict the long-term population growth in near proximal districts of Tamil Nadu and Kerala. Various inputs affecting the population growth are considered as the inputs to the REGT model to the Matlab simulator. The experimentation shows that the proposed REGT model is better in predicting the population growth than the existing game theory models.
ISSN:2665-9174
2665-9174
DOI:10.1016/j.measen.2023.100736