An interval type-2 fuzzy logic based system with user engagement feedback for customized knowledge delivery within intelligent E-learning platforms

Recent years have witnessed an expansion on realizing adaptive educational systems for intelligent E-learning platforms. Such platforms permit the development of customised learning contexts adapted to the requirements of every student by correlating the student characteristics with instructional variables. However, the vast majority of the existing adaptive educational systems do not learn from the users' behaviors to create white box models which could handle the linguistic uncertainties and could be easily read and analyzed by the lay user. Moreover, most of the existing systems ignore gauging the students' engagements levels and mapping them to suitable delivery needs which match the students' knowledge and preferred learning styles. This paper presents a novel interval type-2 fuzzy logic based system that can learn the users' preferred knowledge delivery needs and the preferred learning style based on the students' characteristics and engagement levels to generate a customized learning environment. The paper presents a novel system for gauging the students' engagement levels based on utilizing visual information to automatically calculate the engagement degree of students. This differs from traditional methods which usually employ expensive and invasive sensors. Our approach only uses a low-cost RGB-D video camera (Kinect, Microsoft) operating in a non-intrusive mode whereby the users are allowed to act and move without restrictions. The efficiency of the proposed system has been tested through various real-world experiments with the participation of 15 students. These experiments indicate the ability of the proposed type-2 fuzzy logic based system to handle the linguistic uncertainties to produce better performance in terms of improved learning and better user engagements when compared to type-1 based fuzzy systems and non-adaptive systems.