An Evaluation Method for University Classroom Education Quality under Machine Vision and Single-Valued Neutrosophic Hesitant Fuzzy Set Environment

Abstract

 With the advancement of artificial intelligence, machine vision offers a novel approach to 
university teaching quality evaluation (TQE). However, existing studies are often hindered by 
subjectivity and lack of standardized evaluation methods, which impede accurate assessment of 
student learning effectiveness. Therefore, this study addresses these limitations by proposing a TQE 
framework that integrates machine vision with single-valued neutrosophic hesitant fuzzy sets 
(SVNHFSs). Specifically, the main contributions of this study are as follows. First, this study 
innovatively employs machine vision to capture student learning behaviors, constructing a 
classroom behavior matrix that serves as the foundation for evaluation. Second, this study 
introduces a combined weighting method, leveraging both the entropy weight method and the 
Criteria Importance Through Inter-Criteria Correlation (CRITIC) weight method, to assign weights 
to different time-points during the classes. Third, the SVNHFS is utilized to construct a classroom 
behavior evaluation matrix, and the single-valued neutrosophic hesitant fuzzy weighted average 
(SVNHFWA) operator is applied for weighting. In addition, the cosine measure is employed to rank 
time-points based on both ideal and non-ideal solutions, obtaining the optimal and non-optimal 
learning effectiveness periods. Finally, a case study confirms the effectiveness and feasibility of the 
proposed model, offering a robust method for evaluating university education quality. 

DOI: 10.5281/zenodo.13997087