The Research of Teaching Quality Evaluation Model Based on the Principal Component Analysis and Learning Vector Quantization

Abstract

To further improve the accuracy of teaching quality evaluation, a teaching quality evaluation model based on the combination of principal component analysis (PCA) and learning vector quantization (LVQ) is proposed. The teaching quality evaluation system is established using analytic hierarchy process (AHP), and then the characteristic information of the initial evaluation index system is extracted using principal component analysis. The characteristic information after dimensionality reduction is input to the LVQ neural network, and the network model is trained and tested for generalization ability. The experimental results show that the PCA-LVQ network model is simpler in structure, stronger in learning ability, faster in convergence speed, higher in evaluation accuracy and generalization ability than the single LVQ and BP neural network.