A Multi-Agent Memetic System for Human-Based Knowledge Selection

In these last decades, both industrial and academic organizations have used extensively different learning methods to improve humans´ capabilities and, as consequence, their overall performance and competitiveness in the new economy context. However, the rapid change in modern knowledge due to exponential growth of information sources is complicating learners´ activity. At the same time, new technologies offer, if used in a right way, a range of possibilities for the efficient design of learning scenarios. For that reason, novel approaches are necessary to obtain suitable learning solutions which are able to generate efficient, personalized, and flexible learning experiences. From this point of view, computational intelligence methodologies can be exploited to provide efficient and intelligent tools to be able to analyze learner´s needs and preferences and, consequently, personalize its knowledge acquirement. This paper reports an attempt to achieve these results by exploiting an ontological representation of learning environment and an adaptive memetic approach, integrated into a cooperative multi-agent framework. In particular, a collection of agents analyzes learner preferences and generate high-quality learning presentations by executing, in a parallel way, different cooperating optimization strategies. This cooperation is performed by jointly exploiting data mining via fuzzy decision trees, together with a decision-making framework exploiting fuzzy methodologies.