An Intelligent Knowledge Graph-Based Directional Data Clustering and Feature Selection for Improved Education

Abstract

With advancements in technology and the increasing availability of data, there is a growing interest in leveraging intelligent learning models to enhance the educational experience and improve learning outcomes. The construction of intelligent learning models, supported by knowledge graphs, has emerged as a promising approach to revolutionizing the field of education. With the vast number of educational resources and data available, knowledge graphs provide a structured and interconnected representation of knowledge, enabling intelligent systems to leverage this wealth of information. This paper aimed to construct an effective automated Intelligent Learning Model with the integration of Knowledge Graphs. The automated intelligent model comprises the directional data clustering (DDC) integrated with the Voting based Integrated effective Feature Selection model through the LSTM-integrated Grasshopper Algorithm (LSTM_GOA). The data for analysis is collected from educational institutions in China. Through the framed LSTM_GOA model the performance is evaluated fro the analysis of the student educational performance. The simulation analysis expressed that the developed model exhibits a higher classification performance compared with the conventional technique in terms of accuracy and Mean Square Error (MSE).