An Efficient Big Data Visualization Deep Learning Architecture Model for Path Selection of College Students through Moral Education

Abstract

Visualization technology can be used to present the analysis results in a more intuitive and easy-to-understand way, which can help educators to better understand the moral education needs of college students, and adjust their teaching strategies accordingly. The combination of big data analysis and visualization technology can also help to improve the efficiency and effectiveness of moral education in colleges and universities. The research on the moral education path selection of college students based on big data visualization has great significance for promoting the development of moral education in colleges and universities, and for cultivating high-quality talent with good moral character. This paper proposed an Optimization model for big data analytics for moral education. The data associated with moral education and information are stored in cloud with the big data. The stored big data visualization process is performed with the optimization model for the feature extraction. The optimization is performed with an integrated Flamingo and weighted black widow Optimization model. The proposed model is stated as the Integrated Flamingo Black Widow (IFBW) model. The performance of the IFBW model is implemented with the deep learning Restricted Boltzmann Machine (RBM) architecture. Simulation analysis stated that IFBW model achieves a higher classification accuracy rate of 99% with a minimal error rate.