Evolutionary techniques for inverse scattering - Current trends and envisaged developments

Concerning the state-of-the-art of the application of EAs to inverse scattering, it should be firstly pointed out that their use in computational electromagnetics has a relatively short history, although their use was growing faster from the beginning. However, many of these algorithms (e.g., PSO [8] and ACO [9]) cannot be considered fully developed inversion techniques when compared to other imaging methodologies. From a theoretical point of view, a further analysis concerned with the convergence issues is certainly mandatory. As a matter of fact, the stochastic nature of EAs is an effective feature, but on the other hand it is also a non-negligible obstacle for industrial applications because the non-predictable performances. Nevertheless, even though further developments are still required, existing EAs strategies already demonstrated their potential impact in dealing with complex and large-scale inversion problems. The flexibility of these algorithms and their key features fully justify the large effort dedicated to the development of EA-based techniques for microwave imaging applications [10].