Graph Neural Network–Enhanced Smart Education Management for Dynamic Student Trajectory Prediction

Abstract

Interest in Behaviour (IoB) and AI in students’ education is growing in both industries and academia. Tools for e-learning can aid student learning, with the need for stronger assessment procedures for fairness. Chatbots could enhance education, but lack of user acceptance studies poses a challenge. To takles this, a new model has introduced DHGSIT model combines Deep Learning (DL), Graph Neural Networks (GNN), the Internet of Behaviors (IoB), and the TOPSIS decision-making methodology to support smart education management through adaptive learning analytics and intelligent decision-making which is mainly developed to predict the student’s performance. Label and one-hot encoding as well as the Interquartile Range (IQR) normalization approach to reduce noise and improve model reliability were used in the model. The IoB framework converts educational behavioural data into information at five levels of the hierarchy so that the student’s talent and behaviour on various fields can get analysed. Besides, the model makes use of explainable Artificial Intelligence (XAI) to study the patterns of learners’ behavior and performance that, in turn, can be used to make the most appropriate educational recommendations. The YOLOv7 system uses EMA technique to improve behavioural recognition to reduce localization errors in object detection. DT and LSTMs combine machine learning and DL for sequence analysis. TOPSIS ranks alternatives using weighted performance and distance metrics. The GNN module represents educational entities and relationships, updating node embeddings with attention-based message passing for spatial and temporal dependencies. The experimental analysis is conducted in python and the parameters used for the analysis are accuracy, loss, predicted
and observed of GNN, precision, recall, and F1-Score.