A new method for education quality evaluation based on belief rule base with power set and evidential reasoning

Abstract

Abstract The evaluation of education quality is an important part of the construction of the education system, and it is a direct path to improving education quality. Education quality is a complex evaluation system that takes into account a number of dimensions, such as objectives, attitudes and outcomes. In teaching practice, these dimensions are often good or bad, making it difficult to assess the results of a comprehensive evaluation, leading to the problem of ignorance. Therefore, a belief rule base with power set (PBRB) is used to construct the model for education quality evaluation. The model extends the set of evaluation results into a power set that expresses a variety of evaluation ratings that are difficult to characterize, and uses the BRB to assign belief degrees to each rating in the power set. In addition, because the evaluation of education quality requires a great number of indicators, the BRB faces the rule combination explosion problem. To solve the problem, the transformation matrix is constructed to unify the evaluation indicators, which are then fused using the evidential reasoning (ER) algorithm to reduce the number of PBRB attributes. Finally, the parameters are optimized with the projected covariance matrix adaptive evolution strategy (P-CMA-ES) to improve the model accuracy. According to the experimental results, compared with other methods, the education quality evaluation method based on the EPBRB proposed in this paper can give a clear evaluation grade and has better accuracy and stability.