View in EDS

Enhancing Student Performance Prediction Using Deep Belief Networks with Ant Lion Optimization

Saved in:
Bibliographic Details
Title: Enhancing Student Performance Prediction Using Deep Belief Networks with Ant Lion Optimization
Authors: M. Kannan
Source: International Journal of Intelligent Systems and Applications in Engineering; Vol. 12 No. 21s (2024); 4505 – 4514
Publisher Information: International Journal of Intelligent Systems and Applications in Engineering, 2024.
Publication Year: 2024
Subject Terms: Ant lion optimization, Deep belief networks, Student performance prediction, Feature selection, Educational data analysis
Description: Educational institutions need to predict student performance accurately in order to provide timely interventions. However, researchers often struggle to capture the complexity of student-related data, which leads to suboptimal predictions. This research proposes that we leverage deep belief networks (DBNs) and ant lion optimisation (ALO) to enhance student performance prediction. The methodology includes collecting data, preprocessing it, selecting features using ALO, training DBNs for feature learning and classification, evaluating the model, and conducting comparative analysis. The study investigates the effectiveness of DBNs in predicting student performance, explores ALO for feature selection, develops a robust methodology integrating DBNs and ALO, and evaluates the approach on real-world datasets. The results demonstrate that the proposed approach improves prediction accuracy and f-measure compared to the existing methods.
Document Type: Article
File Description: application/pdf
Language: English
ISSN: 2147-6799
Access URL: https://www.ijisae.org/index.php/IJISAE/article/view/6333
Rights: CC BY SA
Accession Number: edsair.issn21476799..b76468b0f10c9155de1eb82b64db70ee
Database: OpenAIRE
Description
Abstract:Educational institutions need to predict student performance accurately in order to provide timely interventions. However, researchers often struggle to capture the complexity of student-related data, which leads to suboptimal predictions. This research proposes that we leverage deep belief networks (DBNs) and ant lion optimisation (ALO) to enhance student performance prediction. The methodology includes collecting data, preprocessing it, selecting features using ALO, training DBNs for feature learning and classification, evaluating the model, and conducting comparative analysis. The study investigates the effectiveness of DBNs in predicting student performance, explores ALO for feature selection, develops a robust methodology integrating DBNs and ALO, and evaluates the approach on real-world datasets. The results demonstrate that the proposed approach improves prediction accuracy and f-measure compared to the existing methods.
ISSN:21476799