Open AccessGrade Prediction Model Based on DeepCycle Neural Network Classification Algorithm
Author(s) -
Yuanfu Mao,
Xiaoying Sun
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1648/4/042110
Subject(s) - artificial neural network , computer science , principal component analysis , artificial intelligence , convergence (economics) , construct (python library) , machine learning , dimensionality reduction , curse of dimensionality , algorithm , time delay neural network , deep learning , economics , programming language , economic growth
There are many factors affecting students’ grades, which make the prediction of students’ grades present high dimensional and nonlinear characteristics. Therefore, the traditional method has a large error in the prediction results, which is difficult to meet the practical needs. With the rapid development of artificial neural network (Ann), the deep cycle neural network algorithm based on Ann provides a new approach for student achievement prediction. In order to further improve the accuracy of student achievement prediction, this paper proposes a performance prediction model based on deep cycle neural network algorithm. First, principal component analysis is used for data dimensionality reduction processing of the established student writing evaluation system, and the first five principal components are extracted. Then, these principal components are taken as the input of the neural network to construct a three-layer neural network prediction model. The experimental results show that, compared with the single RBF neural network and BP neural network, the prediction model under deep cycle neural network is simple in structure, fast in convergence and 21.6% higher in prediction accuracy, which verifies the effectiveness of the model proposed in this paper.