2011 | OriginalPaper | Buchkapitel
Correlation between Genetic Diversity and Fitness in a Predator-Prey Ecosystem Simulation
verfasst von : Marwa Khater, Elham Salehi, Robin Gras
Erschienen in: AI 2011: Advances in Artificial Intelligence
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Biologists are interested in studying the relation between the genetic diversity of a population and its fitness. We adopt the notion of entropy as a measure of genetic diversity and correlate it with fitness of an evolutionary ecosystem simulation. EcoSim is a predator-prey individual based simulation which models co-evolving sexual individuals evolving in a dynamic environment. The correlation values between entropy and fitness of all the species that ever existed during the whole simulation are presented. We show how entropy strongly correlates with fitness and investigate the factors behind this result using machine learning techniques. We build a classifier based on different species’ features and successfully predict the resulting correlation value between entropy and fitness. The best features affecting the quality of classification are also being investigated.