Comparison of evolutionary and swarm intelligence-based approaches in the improvement of peach fruit quality

Abstract : We investigated two major families of algorithms for the multi-objective optimization: evolutionary and swarm intelligence-based optimization approaches. Non-dominated Sorting Genetic Algorithm II (NSGA-II) and multi-objective particle swarm optimization (MOPSO) algorithms are biology inspired and are population-based as use a set of solutions which evolve within the search space. These approaches employ different strategies and computational effort; therefore, a comparison of their performance is needed. This paper presents the application and performance comparison of NSGA-II and one variant of the MOPSO, namely MOPSO-CD which incorporates the crowding distance computation and the constraints handling, to design ideotypes for sustainable fruit production systems. The design of peach ideotypes that satisfy the requirement of high fruit quality and low sensitivity to brown rot in a given environment was formulated as a multi-objective problem, and both NSGA-II and MOPSO-CD are used to find the best combinations of genetic resources and cultural practices adapted to, and respectful of specific environments. Statistically significant performance measures are employed to compare the two algorithms.