A genetic algorithm applied in the optimization of cognitive profiles: A nonlinear dynamic system resolution

Genetic Algorithms (GAs) are gradient-free optimization algorithms that use a performance criterion for evaluation and a population of possible solutions to the search for a global optimum [2]. They are capable of handling complex and irregular solution spaces, and have been applied to various difficult problems. Inspired by the biological process of Darwinism evolution where selection, mutation and crossover play a major role, GAs can handle high-dimensional nonlinear optimization problems [1]. Therefore, our proposed approach is based on the evolvement technique through a structure named knowledge blocks (KBs). Then, the GA and a pre-evaluation statistical function are employed to construct an optimal path for each learner [3]. This paper makes three critical contributions: (1) it presents a genetic-based curriculum sequencing approach that will generate a personalized curriculum sequencing supported by the KBs; (2) it creates the bases of a new paradigm - the Knowledge Block Structure (KBS) - as a standard to implement a new learning path; and (3) it uses empirical research to indicate that the proposed approach can conduct to a correct learning path, based on individual learner needs.