An Approach to Teaching Quality Evaluation Based on ANN and Boosting

Abstract

An implementation scheme of intelligent evaluator for teaching of university based on artificial neural network (ANN) was proposed. The scheme realized non-linear mapping from factors to results of evaluation, and the current parameters are determined by the data produced in different periods, which makes the dynamic weights can fit to the evaluation of different periods. The evaluator integrates three sub-evaluators using the Boosting method to form the intelligent evaluator and intelligently evaluate the operational rules through the multi-evaluator. It is proved in practice that the method proposed in this paper can reflect the dynamic characteristics and the complex relationship between the factors and the results more effectively than the traditional evaluation methods, and produce better evaluation results.