Search

Adaptive learning has garnered researchers' interest. The main issue within this field is how to select appropriate learning objects (LOs) based on learners' requirements and context, and how to combine the selected LOs to form what is known as an adaptive learning path. Heuristic and metaheuristic approaches have achieved significant progress on personalized and adaptive recommendations, but the operators of some heuristic algorithms are often fixed which decreases the algorithms' extendibility. This paper reviews existing works and proposes an innovative approach. We model the proposed approach as a constraints satisfaction problem, and an improved genetic algorithm named adaptive genetic algorithm is proposed to solve it. The proposed solution does not only reduce the search space size and increase search efficiency but also it is more explicit in finding the best composition of LOs for a specific learner. As a result, the best personalized adaptive learning resources combination will be found in lesser time.

Recently, the field of adaptive learning has significantly attracted researchers' interest. Learning path adaptation problem (LPA) is one of the most challenging problems within this field. It is also a well-known combinatorial optimization problem, its main target is the knowledge resources sequencing offered to a specific learner with a specific context. The learning path candidate solutions can be only approximated as the LPA problem belongs to NP-hard problems and heuristics and meta-heuristics are usually used to solve it. In this direction, this paper summarizes existing works and presents an innovative approach modeled as an objective optimization problem, and an improved Genetic algorithm (GA) is proposed to deal with it. Our contribution does not only reduce the search space size and increase search efficiency, but it is also more explicit in finding the best composition of learning objects for a given learner. Besides the proposed GA, introduces an archive-based bag-of-operators mechanism to tackle two well-known standards GA drawbacks. The simulation results show that the proposed method makes a significant improvement compared to a well-known evolutionary approach, which is the PSO algorithm, and a random search approach. In addition, an empirical experiment is conducted and the results are very encouraging.