Abstract
In this article, various metaheuristics for a numerical optimization problem with application to Electric Impedance Tomography are tested and compared. The experimental setup is composed of a real valued Genetic Algorithm, the Differential Evolution, a self adaptive Differential Evolution recently proposed in literature, and two novel Memetic Algorithms designed for the problem understudy. The two proposed algorithms employ different algorithmic philosophies in the field of Memetic Computing. The first algorithm integrates a local search into the operations of the offspring generation, while the second algorithm applies a local search to individuals already generated in the spirit of life-time learning. Numerical results show that the fitness landscape and difficulty of the optimization problem heavily depends on the geometrical configuration, as well the proposed Memetic Algorithms seem to be more promising when the geometrical conditions make the problem harder to solve.