A robust joint supervision approach is required for both academic instruction and boosting the performance of students. Conventional approaches frequently come across many difficulties when merging different kinds of information, such as files, supervisor comments, and academic achievement. For the purpose of increasing the effectiveness of university supervision, this paper assesses the joint supervision approach using multidimensional data fusion. To combine the different variables used in this study such as grades, feedback evaluations, and the load of supervision mathematical techniques are applied. Next, significant factors impacting the efficiency of university supervision are examined, and students and supervisors are divided into groups based on achievement and feedback assessment. Fusion of these data is performed and analyzed in terms of different measures, like precision, recall, accuracy, level of supervision satisfaction and level of student satisfaction. The outcomes of this paper provide important evidence of the link between pupil achievement and supervision strategies. The paper recommends a multi-data fusion for the university joint supervision scheme and established a link between supervision approaches and student achievement.
Read full abstract