Citation

Deshpande, Sudhindra B. and Goh, Michael Kah Ong and Kadkol, Rakesh J. and Karekar, N. V. and Deshpande, Uttam U. and Lamani, Dharmanna (2025) Optimising Content Recommendations in Context‐Aware Mobile Learning Platform Through Machine Learning. Applied Computational Intelligence and Soft Computing, 2025 (1). ISSN 1687-9724

Text Optimising Content Recommendations in Context‐Aware Mobile Learning Platform Through Machine Learning.pdf - Published Version Restricted to Repository staff only Download (2MB)

Abstract

In today’s mobile communication society, the integration of mobile technology in education has revolutionised learning through m-Learning. Tis approach leverages wireless mobile technology and computing, enabling learners to access educational resources anytime and anywhere, thereby enhancing fexibility and freedom. Mobile devices, such as smartphones, tablets and PDAs, facilitate m-Learning by providing mobility and interactive learning environments. M-Learning is characterised by its personalised, collaborative, and ubiquitous nature, ofering learners context-aware experiences tailored to their immediate surroundings and needs. Context awareness plays a pivotal role in m-Learning, distinguishing it from traditional education by dynamically adapting content delivery based on factors beyond just location, including time, network conditions and user preferences. Tis adaptability poses signifcant challenges in designing efective teaching strategies that meet diverse learner requirements. To address these challenges, this study explores the application of machine learning techniques—specifcally “Artifcial Neural Networks (ANN), K-Nearest Neighbours (KNN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS)”—in developing a Context-Aware m-Learning platform. Performance comparisons based on RMSE, MAE and accuracy metrics reveal ANFIS as the optimal method for enhancing the proposed m-Learning system, aligning with the contextual demands and parameters defned for efective mobile education. ANFIS’s ability to minimise absolute prediction errors more efectively than the other methods. In terms of accuracy, ANFIS again leads the performance metrics, achieving an accuracy of 82.46% with 10 neurons. In comparison, ANN and KNN achieved accuracies of 81.17% and 80.74%, respectively. Tese accuracy values indicate that ANFIS not only reduces prediction errors but also consistently delivers higher predictive accuracy. Tis research contributes to advancing the feld by providing insights into leveraging machine learning for adaptive and context-aware educational technologies, thereby optimising learning experiences in today’s mobile-centric educational landscape.

Item Type:	Article
Uncontrolled Keywords:	Machine learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	30 Sep 2025 07:24
Last Modified:	05 Oct 2025 11:19
URII:	http://shdl.mmu.edu.my/id/eprint/14593

Downloads

Edit (login required)