Classification of college students' mobile learning strategies based on principal component analysis and probabilistic neural network

Abstract

To increase classification accuracy of college students' mobile learning (m-learning) strategies in foreign language learning, a classification model based on principal component analysis (PCA) and probabilistic neural network (PNN) is proposed. First, an index system of college student m-learning strategy evaluation was established. Second, PCA was employed to reduce the dimensions of the original data of students' m-learning strategies obtained through questionnaire. Five principal components were extracted to be the input variables of PNN to create a PCA-PNN classification model. Third, a simulation experiment was done to compare the classification effectiveness of the established PCA-PNN model with a PNN model and a BPNN model. The experiment result shows that the PCA-PNN model has simpler network architecture, faster convergence speed, higher accuracy and better generalization ability, which proves the effectiveness of the proposed model.