Research on Thinking Tendency Prediction Technology of Students Based on Big Data Analysis
Wei Wang, Li Zhu · 2017 International Conference on Smart Grid and Electrical Automation (ICSGEA) · 2017
In the research of the thinking tendency prediction technology of students, using current methods to predict the feature description of students thinking tendency is not detailed enough. This can not accurately reflect the characteristics of changes in the students thinking tendency. There is a big error in the prediction process. Therefore, this paper proposes a method of thinking tendency prediction technology of students based on large data analysis. This method targeted non-stationary characteristics of students thinking tendency prediction time series, and combined the principle of empirical mode decomposition, decomposing it into several intrinsic mode components. On this basis, we used the large data analysis to set up the corresponding prediction model of college students thinking, and used the information provided by initial data of finding trends for nonlinear combination of the trend parameters and boundary values to be identified in the model. We identified again, predicting the tendency of students thinking. Experimental results show that the using large data analysis to predict the tendency of students thinking has high accuracy and satisfactory result.