基于改进灰色神经网络的学生体育成绩预测

Prediction of college sports performance based on improved grey neural network

学生体育成绩预测是指导体育课程制定和提高训练效果的关键。针对现有学生体育成绩预测模型精度低、收敛速度慢的问题,提出了一种基于灰色神经网络的学生体育成绩预测方法。该方法采用灰色模型和BP神经网络组合的方式,克服了单一模型的缺陷。为解决模型随机初始权值和门限设定对预测精度的影响问题,利用遗传算法对初始权值和门限进行优化,进一步提高了模型的预测精度。测试结果表明,该模型能够有效克服传统预测模型不足,具有较高的预测精度。

Prediction of college sports performance is the key to the formulation of physical education curriculum and the improvement of training effect. Aiming at the problems of low accuracy and slow convergence speed of the existing prediction model of college sports achievements, a prediction method of students′ sports achievements based on grey neural network is proposed. This method combines grey model with BP neural network, and overcomes the shortcomings of single model. In order to solve the influence of random initial weights and threshold setting on prediction accuracy, genetic algorithm is used to optimize the initial weights and thresholds, which further improves the prediction accuracy of the model. The test results show that the model can effectively overcome the shortcomings of the traditional prediction model and has high prediction accuracy.