Small-world property evaluated by exchanging network topology

摘要

The present study quantified the degree of the small-world (SW) property defined by Watts, and evaluated its achievement level to characterize complex networks. However, because this process has a combinatorial optimization problem, we applied the chaos neural network (CNN) and the simulated annealing (SA), and confirmed their performance in terms of optimized values and numerical costs. Next, we visualized the original network and its optimized networks whose SW property was maximized or minimized by exchanging the original network topology. As a result, although CNN and SA require huge computational time, we confirmed that they can evaluate the SW property and even real SW networks still have plenty of room to enlarge their own SW property.