About the journal

• Home page
• Contact information
• Aims and scope
• Indexing information
• Editorial policies
• ComSIS consortium
• Journal boards
• Managing board

For authors

• Information for contributors
• Article submission
• Accepted papers
• Copyright transfer form
• Download section

For readers

• Forthcoming articles
• Current issue
• Archive

For reviewers

• Review submissions
• Review submissions OJS

News

• Journal's Facebook page
• Special issue proposal
• Calls for special issues

An ANN-WSM Hybrid Framework for Sustainable Personalized Learning in Smart Education

Christos Troussas¹, Akrivi Krouska¹, Phivos Mylonas¹, Cleo Sgouropoulou¹ and Ioannis Voyiatzis¹

1. Department of Informatics and Computer Engineering, University of West Attica
   Egaleo 12243, Greece
   {ctrouss, akrouska, mylonasf, csgouro, voyageri}@uniwa.gr

Abstract

Personalized learning in modern education helps create learning experiences based on learners' individual preferences. This paper presents an adaptive learning system integrated with ANNs and WSM that recommends particular learning activities to students based on their cognitive styles. The system classifies learners according to the Gregorc Mind Styles Model and, through the ANN, provides probabilities of predefined learning activities. Static expert-assigned weights in WSM finalize the recommendations with adherence to pedagogical best practices while harnessing AI-driven personalization. This implies that a fundamental way this system contributes to sustainable education is that it dynamically optimizes the recommendations on which learning activities are proposed to boost engagement, retention of knowledge, and instructional efficiency. In this way, it undertakes enabled, resource-efficient learning by correspondence of learning activities that require little, if any, mismatch with instructional materials and minimal manual intervention. The weights of WSM, provided by experts, are static constants which contribute to higher decision-making stability, simplicity of resource consumption on computations, with the strong achievement on recommendations. In the pursuit of assessing our approach, we embedded this system in an educational software platform for C++. A study involving 70 undergraduate students found significant improvements in engagement, retention, and performance. The results validated ANNs-implemented adaptive learning using the WSM-based ranking, laying the foundation to improve personal education both in terms of a well-organized and sustainable manner. The research captures the potential of learning systems driven by AI as becoming a transformative mode to deliver efficient, broad-scale, and bespoke education.

Key words

Adaptive Learning Systems, Artificial Neural Networks in Education, Personalized Learning, Recommendations, Sustainable Education, Programming Education

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS250831075T

Publication information

Volume 23, Issue 1 (January 2026)
Year of Publication: 2026
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

Available in PDF
Portable Document Format

How to cite

Troussas, C., Krouska, A., Mylonas, P., Sgouropoulou, C., Voyiatzis, I.: An ANN-WSM Hybrid Framework for Sustainable Personalized Learning in Smart Education. Computer Science and Information Systems, Vol. 23, No. 1, 185-206. (2026), https://doi.org/10.2298/CSIS250831075T