Bioinspired metaheuristics for image segmentation

1 Abstract In general, the purpose of Global Optimization (GO) is finding the global optimum of an objective function defined inside a search space. The GO has applications in many areas of science, engineering, economics, among other, where mathematical models are utilized. Those algorithms are divided into two groups: deterministic, and evolutionary. Since deterministic methods only provide a theoretical guarantee of locating local minimums of the objective function, they face great difficulties in solving GO problems. On the other hand, evolutionary methods are faster in locating a global optimum than deterministic ones, because they operate over a population of candidate solutions, therefore they have a bigger likelihood of finding the global optimum, and a better adaptation to black box formulations or complicated function forms. Despite that during the last decade the field of metaheuristics applied to optimization has had an important increase, the quest of such methods still considered as an open problem in research, due to the most part that they yet present difficulties; for instance, the premature convergence, and the difficulty to overcome local optimum values in multimodal functions. For that reason, in this work it is proposed a bio-inspired algorithm, which utilizes the allostatic mechanism as a base model. Allostasis means 'to maintain stability through change (of several set points-SP)'. That medical model considers the existence of several set points of mechanisms, their non-linear relationships with mediators, other mechanisms, and the brain. Moreover, in this model the brain 'predicts' the new set points, allowing faster responses concerning to the instability. In general terms, once the brain detects some external or internal change (stress, pollution, changes in social status, disease, etc), it determines if the stability (of a single organ, organ system, condition, health, etc) is compromised. Supposing that the instability is confirmed, then the body activates the communication-coordination scheme and starts sending chemical-electrical signals (mediators) to specific mechanisms (viz., target cells, tissues, organs, or even other OS). Those mechanisms should modify