An Adaptive Meta-cognitive Artificial Fish School Algorithm

Artificial fish school algorithm (AFSA) is a novel optimizing method. Based on the study of this algorithm, to deal with the problem of low optimizing precision and low speed of convergence in the later period of the optimization, this paper proposed a novel AFSA called adaptive meta-cognitive artificial fish school algorithm (AMAFSA). The new algorithm constructed an improved artificial fish model based on meta-cognition, which could make self-study by using its knowledge of the surrounding environment. To speed up the convergence, the algorithm improved on the meta-cognitive ability of artificial fish; To advance the precision, it changed parameters self-adaptively. Experimental simulations showed that the proposed method can not only significantly speed up the convergence ,but also can find the global optimization accurately.