Complex system modeling using TSK fuzzy cellular automata and differential evolution

This paper presents a proposal to model the dynamics of complex systems that can be represented as homogeneous continuous cellular automata. The method includes a homogeneous fuzzy cellular automaton whose representative cell is a Takagi-Sugeno-Kang fuzzy system. This cell is tuned by means of the differential evolution algorithm, which tries to optimize a similarity measure between the dynamics of the target complex system and the automaton. The experiments show that our approach is able to obtain a valid model for a complex system that exhibits a two-dimensional nonlinear wave scheme.