Study On Teaching Quality Evaluation Model Based On Improved Genetic Algorithm And BP Neural Network

The improvement of teaching quality is an indispensable part of the modernization of Chinese education.The scientific,rational and timely improvement of teaching quality evaluation plays a key role.The limitations of traditional evaluation methods are controversial.Therefore,it is very important to establish an teaching quality evaluation model to evaluate the teaching quality of undergraduate teachers.The main content of this thesis is as follows:(1)The limitations of the existing teaching quality evaluation system in our school are constructed based on the principle of constructing a perfect teaching quality evaluation system and the analysis of the advantages of previous teaching quality evaluation methods.The evaluation system for teaching quality is more scientific and reasonable to solve the problems existing in the existing teaching quality evaluation system.(2)An adaptive mutation algorithm is proposed based on the traditional genetic algorithm.The improved process is to use the adaptive mutation probability to obtain different adaptations in the group when the genetic algorithm finds the global optimal solution.At the time of the degree,different mutation probabilities are adopted in time to enhance or reduce the diversity of the group and the number of excellent individuals,thereby the global optimal solution search ability and speed of the genetic algorithm are improved.(3)The genetic algorithm of adaptive mutation is used to optimize the initial weight and threshold of BP neural network.Because BP neural network has strong dependence on initial weight and threshold,the improved genetic algorithm is used to optimize the initial weight and threshold of BP neural network,and reduce the time for BP neural network to find the weight and threshold that meet the training termination condition.Thereby,the convergence speed of the neural network can be improved.(4)The entropy method is introduced as a data-based objectivity evaluation method.It is used as the guiding mechanism of BP neural network.The a priori guidance sample is obtained by entropy method,and then BP neural network is optimized by adaptive mutation genetic algorithm.The prior sample knowledge is learned and a new evaluation model is established by the model.The model not only reduces the subjective randomness of BP neural network learning,but also enhances the applicability of the entropy method.(5)In order to improve the reliability and evaluation efficiency of the teaching quality evaluation model,taking the evaluation of the theoretical teaching quality of our school as an example,the entropy method,the adaptive mutation genetic algorithm and the BP neural network are combined to establish an model.The teaching quality evaluation model provides a more feasible plan and model for the evaluation of teaching quality.