AI-Driven Personalized Learning in Mobile Applications Using Edge Computing and Federated Learning

Jastini Mohd Jamil; Mazri Yaakob; Kasmaruddin Che Hussin; Aizul Nahar Harun; Roshartini Omar; Nur Amalina Mohamad Zaki

doi:10.3991/ijim.v20i12.62171

Authors

Jastini Mohd Jamil Universiti Utara Malaysia, Kedah, Malaysia https://orcid.org/0000-0002-6262-6223
Mazri Yaakob Universiti Utara Malaysia, Kedah, Malaysia
Kasmaruddin Che Hussin Universiti Malaysia Kelantan, Kelantan, Malaysia
Aizul Nahar Harun Universiti Teknologi Malaysia, Kuala Lumpur, Malaysia
Roshartini Omar Universiti Tun Hussein Onn Malaysia, Johor, Malaysia
Nur Amalina Mohamad Zaki Universiti Malaysia Terengganu (UMT), Terengganu, Malaysia https://orcid.org/0000-0002-4784-8901

DOI:

https://doi.org/10.3991/ijim.v20i12.62171

Keywords:

Artificial Intelligence, Edge Computing, Federated Learning, Personalized Learning

Abstract

Artificial intelligence (AI)-assisted educational systems have opened up new possibilities for personalized learning in higher education, but they also raise significant issues with platform fragmentation and data protection. As cloud computing continues to develop, security, privacy, and compliance concerns must continue to receive attention. However, issues with latency, network dependency, and data privacy are frequently brought up by conventional cloudbased personalization techniques. Due to the sensitive nature of student data and the varied infrastructure present in academic institutions, traditional centralized training approaches become impractical. Therefore, this study explores the integration of AI, edge computing, and federated learning (FL) to develop an efficient and privacy-preserving personalized learning framework for mobile applications. The suggested system analyses learner behavior, preferences, and performance in real time using on-device AI models that are deployed via edge computing. FL ensures improved privacy and security by facilitating cooperative model training across several devices without sending private user information to centralized servers. The system lowers communication overhead, speeds up reaction times, and keeps recommendations customized for each learner by fusing distributed learning methods with local data processing. When compared to traditional cloud-centric approaches, experimental research shows that the suggested framework increases system efficiency, learning engagement, and recommendation accuracy. The study emphasizes the promise of FL and edge-based AI as a scalable solution for future intelligent mobile learning environments.

References

[1] Katiyar, N., Awasthi, M.V.K., Pratap, R., Mishra, M.K., Shukla, M.N., Tiwari, M. and Singh, R., 2024. AI-driven personalized learning systems: Enhancing educational effectiveness. Educational Administration: Theory and Practice, 30(5), pp.11514-11524.

[2] Javeed, D., Saeed, M.S., Kumar, P., Jolfaei, A., Islam, S. and Islam, A.N., 2023. Federated learning-based personalized recommendation systems: An overview on security and privacy challenges. IEEE Transactions on Consumer Electronics, 70(1), pp.2618-2627.

[3] Tapalova, O. and Zhiyenbayeva, N., 2022. Artificial intelligence in education: AIEd for personalised learning pathways. Electronic Journal of e-Learning, 20(5), pp.639-653.

[4] Merino-Campos, C., 2025. The impact of artificial intelligence on personalized learning in higher education: A systematic review. Trends in Higher Education, 4(2), p.17.

[5] Peng, J. and Li, Y., 2025. Frontiers of artificial intelligence for personalized learning in higher education: A systematic review of leading articles. Applied Sciences, 15(18), p.10096.

[6] Chu, Y.W., Hosseinalipour, S., Tenorio, E., Cruz, L., Douglas, K., Lan, A.S. and Brinton, C.G., 2024. Multi-layer personalized federated learning for mitigating biases in student predictive analytics. IEEE Transactions on Emerging Topics in Computing.

[7] Fachola, C., Tornaría, A., Bermolen, P., Capdehourat, G., Etcheverry, L. and Fariello, M.I., 2023. Federated learning for data analytics in education. Data, 8(2), p.43.

[8] de Amorim Silva, R., Pacheco, L.H., dos Santos, S.A., Barros, A.N. and Melo, R.F., 2025. Ai-powered personalized learning for higher education: a systematic mapping review. EDULEARN25 Proceedings, pp.7446-7455.

[9] Ullah, R.S., Hashim, F., Bandeali, M.M. and Akbar, A., 2025. Artificial Intelligence in Curriculum Design a Roadmap for Adaptive and Personalized Learning in Higher Education. The Critical Review of Social Sciences Studies, 3(3), pp.304-322.

[10] Surapaneni, P., Bojjagani, S. and Sharma, N.K., 2024, November. Federated learning-based big data analytics for the education system. In 2024 International Conference on Intelligent Computing and Emerging Communication Technologies (ICEC) (pp. 1-6). IEEE.

[11] Yekollu, R.K., Bhimraj Ghuge, T., Sunil Biradar, S., Haldikar, S.V. and Farook Mohideen Abdul Kader, O., 2024, February. AI-driven personalized learning paths: Enhancing education through adaptive systems. In International Conference on Smart data intelligence (pp. 507-517). Singapore: Springer Nature Singapore.

[12] Huang, Z. and Cao, C., 2025, April. Federated Learning for AI-Assisted Education: Privacy-Preserving and Cross-Platform Collaborative Modeling in Higher Education. In Proceedings of the 2nd International Conference on Machine Intelligence and Digital Applications (pp. 146-151).

[13] Hridi, A.P., Sahay, R., Hosseinalipour, S. and Akram, B., 2024, May. Revolutionizing AI-assisted education with federated learning: a pathway to distributed, privacy-preserving, and debiased learning ecosystems. In Proceedings of the AAAI Symposium Series (Vol. 3, No. 1, pp. 297-303).

[14] Wasif, F. and Badi, S., 2023. The Role of Cloud Computing in AI-Driven Personalized Learning and Data Security in EdTech.

[15] Firdaus, M., Noh, S., Qian, Z., Larasati, H.T. and Rhee, K.H., 2023. Personalized federated learning for heterogeneous data: A distributed edge clustering approach. Mathematical Biosciences and Engineering, 20(6), pp.10725-10740.

[16] Shidaganti, G., Raj, V.A., Raman, V.M. and Kumaran, S., 2025. Edge Computing in Educational Technology: The Power of Edge AI for Dynamic and Personalized Learning. Edge of Intelligence: Exploring the Frontiers of AI at the Edge, pp.121-152.

[17] SRINIVASAN, P., 2025. Federated Learning and AI-Driven Edge Computing for Secure and Efficient Healthcare Data Processing. International Journal of Multidisciplinary Sciences and Technology, 1(1), pp.29-40.

[18] Chelliah, P.R., Rahmani, A.M., Colby, R., Nagasubramanian, G. and Ranganath, S. eds., 2024. Model Optimization Methods for Efficient and Edge AI: Federated Learning Architectures, Frameworks and Applications. John Wiley & Sons.