The Quality Evaluation of Classroom Teaching Based on FOA-GRNN

Abstract

In order to improve the accuracy and efficiency of classroom teaching quality evaluation, a generalized regression neural network (GRNN) forecasting model is proposed based on fruit fly optimization algorithm (FOA). This method combines some of the advantages which FOA has a fast convergence rate and GRNN retains a strong generalization ability, then the FOA algorithm is used to optimize the smoothing parameter Spread of GRNN to reduce the adverse influence of man-induced factors in model construction process and enhance the learning ability of GRNN. The simulation results show that FOA-GRNN algorithm has the lowest relative error and the average relatively variety value compared with GRNN and BP network, and the validity of the proposed algorithm is verified.