Author(s)

H.A. Wan

Abstract

This paper describes a way by which a special kind of cellular automata— Kauffman network—can be identified so that it can be used to model a physical system. The only known characteristics of the system is a time series of observations over the system. Fourier analysis is applied to the time series to determine the size of the Network, the values that the cells may assume, and the transition rules. Results of several experiments are reported and found to be supportive to the method derived. 1 Introduction Real-world systems are not always depictable as sets of mathematical func- tions. It is in general very difficult to find explicitly the functions which govern the changes in natural or socio-economical systems. These systems usually change in an aperiodic way. For ages, the unpredictability of these systems have been accounted for by noises; but resear

Keywords