Abstract:

This Learning based on the use of computer systems and mobile devices converge in its use in what is called m-learning, since it allows users to stay connected with the learning environment, contents and learning resources. Thus, part of the learning process (such as practice or training through the resolution of tasks and activities), is no longer subject to a particular physical place and / or a physical person (the teacher), and depends primarily on the will to access learning resources. The problem is when the student does not have sufficient motivation to approach content offered by some existing systems, either by presenting exercises with the same level of difficulty for all students, or by showing the contents and activities always in the same way regardless of the learning style that predominates in them. This fact justifies the study of areas such as artificial intelligence applied to learning within the framework of e-learning, since in a number of contexts has been proven efficient. This article describes the development and implementation of an expert system as a support tool to tackle topics of mathematics, using Bayesian networks as the engine of inference and learning styles, as well as difficulty level of problems, for the base of the classifier probabilistic. The expert system makes decisions as to which element to visualize at a specific moment, and gives to the student the best resource, and supervises the progress of the user. The article is divided into three sections, the first one deals with the construction of the expert system, the second presents the operation of the system, through the classification of students according to their profile, which is based In the style of learning that predominates in him and in the level of difficulty that have the problems that the student succeeds in solving successfully. It also shows the operation of the system in terms of the allocation of digital resources according to the profile detected and gradually provides more activities with different degrees of difficulty, once the student progresses. An experimental study was done in which the system was tested with 30 students of engineering level and those who studied the subject of Applied Calculus in its second semester of the carrier. This group was called the study group (SG), while a second group, who did not use the system was called the control group (CG). Both have been applied the same initial and final questionnaire. The SG used the system for one semester, while the CG worked the same subjects without it during the same semester. Results for both groups in initial and final evaluation mean results on 2.08 to 3.30 and 2.58 to 7.47 for CG and SG respectively. Applying F test, a statistically significant difference in increase was found (p <0.002). This results showed that SG identified the concept of derivative and correctly applied that concept to real problems solving correctly 74% of the final questionnaire, so it is concluded that the system expert open a new way in educational research.

Keywords:

Technology, research projects, education, learning.