Study of classification model for college students' M-learning strategies based on PCA-LVQ neural network

Study of learner-oriented mobile learning (m-learning) instructions based on classification of student m-learning strategies has aroused much attention over the last decade. Due to the multivariate nature of students' learning strategies, traditional classification methods often fail to produce reliable classification results. In this paper, a new classification method based on Principal Component Analysis (PCA) and Learning Vector Quantization (LVQ) neural network is proposed. PCA was first used to reduce the dimensionality of original data about students' learning strategies. 5 principal components were extracted to create a PCA-LVQ classification model. The classification result of the proposed model was compared with those produced by a simple LVQ network model and a standard BP network model. The simulation results show that compared with the other two networks, the PCA-LVQ model has a better performance in training speed, classification accuracy and generalization ability.