Refining Graduation Classification Accuracy with Synergistic Deep Learning Models

Learning Analytics plays an important role in monitoring and improving educational outcomes, but is often challenged by limited dataset sizes, resulting from privacy regulations and curriculum changes. This paper proposes the LATCGAd (Learning Analysis by Transformer with Conditional Generative Adve...

Full description

Saved in:
Bibliographic Details
Main Authors: Son Nguyen Thi Kim, Quynh Nguyen Huu, Minh Bui Tuan
Format: Article
Language:English
Published: Sciendo 2025-06-01
Series:Cybernetics and Information Technologies
Subjects:
Online Access:https://doi.org/10.2478/cait-2025-0016
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849424639395102720
author Son Nguyen Thi Kim
Quynh Nguyen Huu
Minh Bui Tuan
author_facet Son Nguyen Thi Kim
Quynh Nguyen Huu
Minh Bui Tuan
author_sort Son Nguyen Thi Kim
collection DOAJ
description Learning Analytics plays an important role in monitoring and improving educational outcomes, but is often challenged by limited dataset sizes, resulting from privacy regulations and curriculum changes. This paper proposes the LATCGAd (Learning Analysis by Transformer with Conditional Generative Adversarial Framework Network and Adaptive Layer Normalization model), a deep learning framework that combines the Transformer architecture and Conditional Generative Adversarial Network (CGAN) to overcome the above problems. The CGAN component generates synthetic data samples, which balance and expands the dataset size, while the Transformer leverages this rich dataset to improve prediction performance. The integration of Adaptive Layer Normalization (AdaLN) in the Transformer also helps stabilize the learning process and minimize overfitting. Experiments on datasets from Hanoi Metropolitan University and Hanoi National University show that the LATCGAd model achieves an accuracy of up to 96.97%, outperforming traditional models such as Decision Tree, SVM and Transformer alone. This result confirms the effectiveness of LATCGAd in educational predictive analysis and its potential for widespread application in the field of learning analytics.
format Article
id doaj-art-e0d957a43e404f8a882c08c67ddb8f62
institution Kabale University
issn 1314-4081
language English
publishDate 2025-06-01
publisher Sciendo
record_format Article
series Cybernetics and Information Technologies
spelling doaj-art-e0d957a43e404f8a882c08c67ddb8f622025-08-20T03:30:04ZengSciendoCybernetics and Information Technologies1314-40812025-06-0125213115110.2478/cait-2025-0016Refining Graduation Classification Accuracy with Synergistic Deep Learning ModelsSon Nguyen Thi Kim0Quynh Nguyen Huu1Minh Bui Tuan21Hanoi University of Industry, Hanoi, Vietnam3CMC University, Hanoi, Vietnam4Thuyloi University, Hanoi, VietnamLearning Analytics plays an important role in monitoring and improving educational outcomes, but is often challenged by limited dataset sizes, resulting from privacy regulations and curriculum changes. This paper proposes the LATCGAd (Learning Analysis by Transformer with Conditional Generative Adversarial Framework Network and Adaptive Layer Normalization model), a deep learning framework that combines the Transformer architecture and Conditional Generative Adversarial Network (CGAN) to overcome the above problems. The CGAN component generates synthetic data samples, which balance and expands the dataset size, while the Transformer leverages this rich dataset to improve prediction performance. The integration of Adaptive Layer Normalization (AdaLN) in the Transformer also helps stabilize the learning process and minimize overfitting. Experiments on datasets from Hanoi Metropolitan University and Hanoi National University show that the LATCGAd model achieves an accuracy of up to 96.97%, outperforming traditional models such as Decision Tree, SVM and Transformer alone. This result confirms the effectiveness of LATCGAd in educational predictive analysis and its potential for widespread application in the field of learning analytics.https://doi.org/10.2478/cait-2025-0016deep learningtransformercgangraduation classificationlearning analytics
spellingShingle Son Nguyen Thi Kim
Quynh Nguyen Huu
Minh Bui Tuan
Refining Graduation Classification Accuracy with Synergistic Deep Learning Models
Cybernetics and Information Technologies
deep learning
transformer
cgan
graduation classification
learning analytics
title Refining Graduation Classification Accuracy with Synergistic Deep Learning Models
title_full Refining Graduation Classification Accuracy with Synergistic Deep Learning Models
title_fullStr Refining Graduation Classification Accuracy with Synergistic Deep Learning Models
title_full_unstemmed Refining Graduation Classification Accuracy with Synergistic Deep Learning Models
title_short Refining Graduation Classification Accuracy with Synergistic Deep Learning Models
title_sort refining graduation classification accuracy with synergistic deep learning models
topic deep learning
transformer
cgan
graduation classification
learning analytics
url https://doi.org/10.2478/cait-2025-0016
work_keys_str_mv AT sonnguyenthikim refininggraduationclassificationaccuracywithsynergisticdeeplearningmodels
AT quynhnguyenhuu refininggraduationclassificationaccuracywithsynergisticdeeplearningmodels
AT minhbuituan refininggraduationclassificationaccuracywithsynergisticdeeplearningmodels