Advances in knowledge discovery and data mining
Advances in knowledge discovery and data mining
A hybrid evolutionary modeling algorithm for system of ordinary differential equations
Neural, Parallel & Scientific Computations
Hi-index | 0.00 |
In this paper An Asynchronous Parallel Evolutionary Modeling Algorithm (APEMA) for automatically modeling of dynamic systems is proposed. The algorithm is based on a two -level hybrid evolutionary modeling algorithm HEMA]. The APEMA is used to automatically discover knowledge modeled by higher order of ordinary differential equations from dynamic data by using different computing systems, especially, the MIMD computers. Two cases of modeling examples are used to demonstrate the potential of APEMA .One is for modeling the limit of the solutions of BUMP problem as its dimension n tending to infinity, another is for modeling the super-spreading events of severe acute respiratory syndrome (SORS) in Beijing, 2003. The results show that the dynamic models automatically discovered in data by computer sometimes can compare with the models discovered by human beings.