Data Fusion Technique for E-Learning Evaluation Based on Evidence Theory

Abstract

To reduce the risk of viral infection during the coronavirus pandemic, all academic institutions have turned to online learning in recent years. The evolution of online classes presents new obstacles for academic specialists, particularly in underdeveloped nations where participants have limited access to technological gadgets. Even while some elements of online and traditional on-campus learning are comparable, online learning requires more factors to analyze, such as student evaluation. Because of the various surroundings that participants are exposed to during online education, the topic of electronic learning environments must be discussed. It calls for the development of new methodologies and procedures for assessing participants’ knowledge and skill development. Based on evidentiary theory and the data fusion idea, this research provides a new technique to evaluate participation. Because it is versatile in simulating the wide spectrum of uncertainty inherent in natural contexts, evidential theory is progressively spreading. The approach suggested is appropriate for dealing with all forms of online courses. Furthermore, it enables educators to improve academic performance by providing continuous participant feedback. After exposing participants’ weaknesses, the instructor can redirect learning processes. The experimental findings of three online university courses demonstrate the efficacy of this strategy.