基于PSO-RBF的大学程序设计教学效果评价方法研究

Research on the evaluation method of university programming teaching effectiveness based on PSO-RBF

教学评价是对授课教师的教学效果和学生的学习情况进行评估,已成为高等教育教学管理的重要组成部分。为了满足大学程序设计教学效果评价要求,提出一种基于粒子群(PSO)算法和径向基神经网络(RBF)的大学程序设计教学效果评价模型,从而提高大学程序设计教学效果评价的准确率。基于PSO-RBF神经网络的大学程序设计教学效果评价的机器学习方法算法收敛速度快、优化能力强、泛化能力强,有效降低了人为因素对指标权重确定的影响,可以提高评价预测的准确性。

Teaching evaluation,which assesses the teaching value of lecturers and the learning of students,has become an important part of teaching management in higher education.In order to meet the requirements of university programming teaching effectiveness evaluation,a university programming teaching effectiveness evaluation model based on particle swarm algorithm and radial basis neural network has been proposed,so as to improve the accuracy of university programming teaching effectiveness evaluation.The research in this paper demonstrates that the algorithm of machine learning method based on PSO-RBF neural network for university programming teaching effectiveness evaluation has fast convergence,strong optimization ability and generalization ability,and effectively reduces the influence of human factors on the determination of index weights.The accuracy of evaluation prediction can be improved.