On distributed user-centric memetic algorithms

A user-centric memetic algorithm (UcMA) represents an instance of the so-called interactive evolutionary computation, in which the subjacent algorithm that interacts with a human consists of a memetic algorithm (MA) that manages knowledge of the problem with the aim of accelerating the solution search process. UcMAs have been proved to be effective optimization methods to tackle problems that require human intervention (in the form of evaluations/decisions). This paper proposes two generic schemas to distribute a number of (interactive/proactive) UcMAs that act as independent agents and, eventually, synchronize to interchange information. These schemas can be instantiated via a number of parameters (including the cooperation topology) to develop novel 2-dimensional spatially structured cooperative UcMAs. These algorithms can be viewed as specific instances of the so-called parallel MAs but with the particularity that they are especially suited to dealing with combinatorial problems whose solving requires subjective evaluations. An experimental study over microarray ordering problems is done including distinct instances of an NP-hard problem with strong implications in biomedicine and molecular biology, namely the gene ordering problem. It is shown that some distributed UcMAs, especially those based on proactivity, which have been instantiated from our proposals, efficiently handle these problems.