AI-BASED ADAPTIVE LEARNING MANAGEMENT SYSTEM: ARCHITECTURE, DESIGN AND IMPLEMENTATION OF THE SMART-LMS PLATFORM
Received: 2026-05-29
Published: 2026-09-16
Abstract
This paper presents the complete architecture, nine functional modules, and practical implementation results of the Smart-LMS platform — an adaptive learning management system built on modern ICT and artificial intelligence. The platform integrates: NLP-based automated grading, adaptive learning pathways with knowledge graph management, predictive analytics dashboards, gamification (UniCoin system), AI proctoring and accessibility, intelligent content management, attendance and digital participation monitoring, employer integration, and mobile portfolio generation. Built on microservices architecture with Python/FastAPI, React.js, Flutter, and Gemma 4 /Llama, the system was piloted with 45 students at three Uzbek higher education institutions. Results demonstrate 65% reduction in instructor grading workload, 176% increase in student weekly platform engagement, and 9.4% improvement in test scores.Demo platform distinctly serves the Uzbek educational context with native language support and local regulatory compliance — differentiating it clearly from global LMS alternatives such as Moodle, Canvas, and Blackboard.
Keywords
List of references
-
Dabbagh, N., & Kitsantas, A. (2012). Personal learning environments, social media, and self-regulated learning. Internet and Higher Education, 15(1), 3–8.
-
Pew Research Center. (2022). Online Learning Engagement Report. Washington D.C.
-
O'zbekiston Respublikasi Prezidentining 2020-yil 6-noyabrdagi PF-6079-son Farmoni «Raqamli O'zbekiston — 2030». Toshkent.
-
Roll, I., & Wylie, R. (2016). Evolution and revolution in artificial intelligence in education. IJAIED, 26(2), 582–599.
-
Bloom, B. S. (1984). The 2 sigma problem. Educational Researcher, 13(6), 4–16.
-
VanLehn, K. (2011). The relative effectiveness of human tutoring, ITS, and other tutoring systems. Educational Psychologist, 46(4), 197–221.
-
Knewton. (2021). Adaptive Learning White Paper: Personalization at Scale. New York.
-
Ramesh, A., et al. (2013). Automated essay scoring in presence of biased ratings. NAACL-HLT 2013, 290–300.
-
Singhal, A., & Bhattacharyya, P. (2020). Short answer grading using BERT-based NLP models. EMNLP 2020 Workshop.
-
Feng, Z., et al. (2020). CodeBERT: A pre-trained model for programming and natural languages. EMNLP Findings 2020.
-
Jayaprakash, S. M., et al. (2014). Early alert of academically at-risk students. Journal of Learning Analytics, 1(1), 6–47.
-
Okubo, F., et al. (2017). A neural network approach for students' performance prediction. LAK'17, 598–599.
-
Hamari, J., et al. (2014). Does gamification work? 47th HICSS, 3025–3034.
-
Deterding, S., et al. (2011). From game design elements to gamefulness. MindTrek'11, 9–15.
-
Cohney, S., et al. (2021). Watching the watchers: Bias and vulnerability in remote proctoring software. arXiv:2109.06243.
-
Hevner, A. R., et al. (2004). Design science in information systems research. MIS Quarterly, 28(1), 75–105.
-
Ismoilov, A., & Xasanov, B. (2023). O'zbekiston oliy ta'limida raqamlashtirish to'siqlari va yechimlar. O'zbek pedagogika jurnali, 4(2), 45–58.
-
Rahimov, S. (2024). O'zbek tilidagi raqamli kontent va onlayn ta'lim: holat tahlili. Axborot texnologiyalari va ta'lim, 3(1), 12–24.
-
Musaev, A., & Tursunov, F. (2023). UzBERT: O'zbek tili uchun transformer modeli. O'zbekiston Milliy universiteti ilmiy axborotnomasi, 2(4), 88–97.
-
Ergashev, J., & Nazarov, D. (2024). Bashoratli tahlil yordamida talabalar akademik xavfini aniqlash. TATU ilmiy jurnali, 1(3), 67–79.
-
Qodirov, N., & Xoliqov, M. (2023). Gamifikatsiyaning oliy ta'limda motivatsiyaga ta'siri: empirik tadqiqot. SamDU ilmiy to'plami, 5, 112–125.
-
Karimov, R., & Yusupov, T. (2022). O'zbekistonda onlayn imtihon o'tkazish tajribasi: muammolar va yechimlar. Raqamli ta'lim, 2(1), 34–46.
About the Authors
License
This work is licensed under a Creative Commons Attribution 4.0 International License.