Research on Quality Evaluation of Smart Education Schools Based on Fuzzy Clustering Algorithm and Strategies for Future Development

Abstract

Abstract The burgeoning field of wisdom education has led to a disparity in the quality of educational institutions, thereby necessitating enhancements to the existing school quality evaluation systems. This study refines the traditional fuzzy C-mean clustering algorithm by incorporating a Gaussian mixture distribution and information entropy regularization. It then employs this enhanced algorithm to construct a quality evaluation system for smart education schools. The improved fuzzy C-mean clustering algorithm demonstrated in this paper significantly outperforms the standard C-means used at SCU and the K-means algorithm in terms of Mean Absolute Error (MAE) and Total Hit Rate (THR). Specifically, the optimized algorithm decreased the MAE to 0.572 from 0.619, a reduction of 16.01% compared to the K-means algorithm. It increased the THR to 0.158 from 0.147, marking an improvement of 17.04% over the Kmeans algorithm. Furthermore, the refined clustering algorithm achieved an impressive accuracy of 95.71%. Analysis through this clustering approach reveals that the developed quality evaluation system accurately reflects the operational level of smart education within schools. The establishment of such a system is anticipated to significantly guide the future progression of smart education and aid in the foundational development of smart education schools.