Research of Teacher’s Performance Evaluation Model Based on AHP and Improved PSO-BP Neural Network

Abstract

The teacher’s performance evaluation is an important guarantee for the development of higher education. In view of the limitations of traditional analytic hierarchy process in the teachers' performance comprehensive evaluation and the shortcomings of BP neural network in the teachers' performance comprehensive evaluation, such as non-convergence and large prediction error, the paper proposed an evaluation index system based on analytic hierarchy process as input of BP neural network, and used dynamic inertial weight and multiple empirical particles to improve PSO algorithm and optimize the weights and thresholds of BP network, established teacher's performance evaluation model. The simulation results show that the model effectively reduces the number of network iterations, improves the prediction accuracy, and has a good application prospect in the teacher's performance evaluation.