Abstract
In recent years, new research has appeared in the area of education, which has focused on the use of information technology and the Internet to promote online learning, breaking many barriers of traditional education such as space, time, quantity and coverage. However, we have found that these new proposals present problems such as linear access to content, patronized teaching structures, and non-flexible methods in the style of user learning. Therefore, we have proposed the use of an intelligent model of personalized learning management in a virtual simulation environment based on instances of learning objects, using a similarity function through the weighted multidimensional Euclidean distance. The results obtained by the proposed model show an efficiency of 99.5%; which is superior to other models such as Simple Logistic with 98.99% efficiency, Naive Bayes with 97.98% efficiency, Tree J48 with 96.98% efficiency, and Neural Networks with 94.97% efficiency. For this, we have designed and implemented the experimental platform MIGAP (Intelligent Model of Personalized Learning Management), which focuses on the assembly of mastery courses in Newtonian Mechanics. Additionally, the application of this model in other areas of knowledge will allow better identification of the best learning style of each student; with the objective of providing resources, activities and educational services that are flexible to the learning style of each student, improving the quality of current educational services.
Highlights
Artificial Intelligence (AI) in education is a highly researched field [1], which focuses primarily on the formulation and application of techniques for the development of systems that improve the teaching process through computer-assisted learning [2], with the goal of building more intelligent systems [3].The term "intelligent" used in these systems is fundamentally determined by its capacity for continuous adaptation to the characteristics of learning and knowledge of different users [4].For example, an article presents an approach that recognizes the relevant elements of the student profile seeking to meet their personal and academic needs by recovering reusable knowledge units with fine granularity stored in repositories of learning objects
It is used in environments where the main objective is a prediction, we have selected it since we want to estimate the accuracy of a model
It is a technique widely used in artificial intelligence projects to validate generated models
Summary
Artificial Intelligence (AI) in education is a highly researched field [1], which focuses primarily on the formulation and application of techniques for the development of systems that improve the teaching process through computer-assisted learning [2], with the goal of building more intelligent systems [3]. The proposal is based on the technique of artificial intelligence, known as Case-Based Reasoning (CBR) [3] For these reasons, we have decided to focus our research on developing dynamic methods for the search and identification of a student's best learning style. The importance of our proposal is to adapt teaching to the specific needs of the student, giving flexibility and autonomy to the learning environment For this we use artificial intelligence techniques such as Case Based Reasoning, whose efficiency is compared to other techniques or algorithms with RN, Naive Bayes, Tree J48 and Simple Logistic
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
