Online and Offline Teaching Effect of C Language in Colleges and Universities Based on Principal Component Analysis and Neural Network

Abstract

In classroom teaching evaluation, there are a lot of non-linear problems, the data is complex and useless, and the existing teaching effect evaluation methods can not eliminate the problem of data surplus, and cannot effectively capture the non-linear law, which will lead to low prediction accuracy. In this case, this paper proposes a teaching effect evaluation method based on principal component analysis and neural network. In this paper, the principal component analysis and BP neural network are combined to construct the teaching effect evaluation system, and the feasibility of this method is verified by evaluating the online and offline teaching effect of C language in Colleges and universities. In addition, in order to highlight the advantages of this method, we choose the absolute error value as the accuracy evaluation index, and compare this method with the BP neural network teaching effect evaluation method to highlight the advantages of this method. It is found that the actual score of the first level index teaching quality is 7.25, the predicted value of BP neural network is 7.7739, and the absolute error value is 0.5239. The prediction value of this method is 7.5842, and the absolute error value is 0.3342. The experimental results show that the prediction value of the online and offline teaching effect evaluation method of C language based on principal component analysis and neural network is closer to the actual score.