Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Indonesian Journal of Information System
Femi Elegbeleye
North West University
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
DevQuizzer: An Adaptive Game-Based Learning System for Personalized Programming Instruction Femi Elegbeleye; Isong Bassey
Indonesian Journal of Information Systems Vol. 9 No. 1 (2026): August 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v9i1.14181

Abstract

Over the years, balancing personalized support with learner motivation has proven difficult in programming education. Traditional instructional approaches seldom adapt to individual needs, often resulting in uneven engagement and cognitive overload. Gamified settings can enhance motivation, but many lack adaptive mechanisms informed by motivational frameworks such as Self-Determination Theory (SDT). As a result, few systems combine reinforcement learning (RL) with probabilistic learner modelling to deliver scalable, personalized learning pathways. This paper proposes DevQuizzer, an adaptive game-based learning (AGBL) system designed to support personalized programming instruction. The system combines RL and Bayesian Networks (BNs) models to dynamically adjust task difficulty, feedback, and learning pathways according to learner performance and engagement. A dual-mode instructional design: code-first and theory-first, accommodates various learning preferences, while gamified elements sustain motivation. We evaluated AGBL with students from five universities using a mixed-methods approach that combined quantitative measures of usability, engagement, and adaptivity with qualitative insights into learner experiences. Results confirmed the system’s reliability and construct validity, with learners reporting high satisfaction, autonomy, and perceived learning gains. The findings show the potential of hybrid RL-BN models to provide transparent, interpretable, and scalable adaptive learning environments for programming education.
Optimized Multi-Agent Reinforcement Learning for Dynamic Open RAN Slicing Femi Elegbeleye
Indonesian Journal of Information Systems Vol. 9 No. 1 (2026): August 2026
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/ijis.v9i1.14219

Abstract

Fifth generation (5G) networks enable radio access network (RAN) slicing, allowing a shared physical infrastructure to be partitioned into multiple logical slices, each tailored to meet heterogeneous service requirements. Slice tenants specify service-level agreements (SLAs) that must be satisfied; however, inefficient resource allocation mechanisms frequently result in SLA violations. Recent studies have adopted constrained multi-agent reinforcement learning (MARL) to dynamically allocate RAN resources, yet these approaches often remain inefficient due to reward misalignment with SLA objectives and unstable exploration in high-dimensional state–action spaces. This paper presents a reward-function–centric analysis of constrained MARL for 5G RAN slicing, examining how different reward designs affect learning efficiency and SLA compliance. Based on this analysis, we propose heuristic-guided reward shaping strategies that explicitly align the learning objective with SLA satisfaction and resource utilization efficiency. In addition, we introduce a state-space optimization technique that aggregates local agent states into a weighted global state representation, thereby reducing state dimensionality while preserving critical SLA-related information. Extensive experimental evaluations demonstrate that the proposed approach achieves a 60% reduction in SLA violations compared to an existing constrained MARL model and a 46% reduction compared to a state-of-the-art model-based reinforcement learning approach. Furthermore, the proposed solution converges faster and requires less training time and computational resources, highlighting its effectiveness and practical applicability for efficient 5G RAN slicing.
Co-Authors Isong Bassey