Reinforcement Learning-Based Dynamic Fuzzy Weight Adjustment for Adaptive User Interfaces in Educational Software DOI Creative Commons
Christos Troussas, Akrivi Krouska, Phivos Mylonas

и другие.

Future Internet, Год журнала: 2025, Номер 17(4), С. 166 - 166

Опубликована: Апрель 9, 2025

Adaptive educational systems are essential for addressing the diverse learning needs of students by dynamically adjusting instructional content and user interfaces (UI) based on real-time performance. Traditional adaptive environments often rely static fuzzy logic rules, which lack flexibility to evolve with learners’ changing behaviors. To address this limitation, paper presents an UI system software in Java programming, integrating reinforcement (RL) personalize experiences. The consists two main modules: (a) Fuzzy Inference Module, classifies learners into Fast, Moderate, or Slow categories triangular membership functions, (b) Reinforcement Learning Optimization adjusts function thresholds enhance personalization over time. By refining timing necessity modifications, optimizes hints, difficulty levels, structured guidance, ensuring interventions neither premature nor delayed. was evaluated 100 postgraduate students. evaluation, efficiency, engagement, usability metrics, demonstrated promising results, particularly slow moderate learners, confirming that learning-driven weight adjustments significantly improve effectiveness.

Язык: Английский

Reinforcement Learning-Based Dynamic Fuzzy Weight Adjustment for Adaptive User Interfaces in Educational Software DOI Creative Commons
Christos Troussas, Akrivi Krouska, Phivos Mylonas

и другие.

Future Internet, Год журнала: 2025, Номер 17(4), С. 166 - 166

Опубликована: Апрель 9, 2025

Adaptive educational systems are essential for addressing the diverse learning needs of students by dynamically adjusting instructional content and user interfaces (UI) based on real-time performance. Traditional adaptive environments often rely static fuzzy logic rules, which lack flexibility to evolve with learners’ changing behaviors. To address this limitation, paper presents an UI system software in Java programming, integrating reinforcement (RL) personalize experiences. The consists two main modules: (a) Fuzzy Inference Module, classifies learners into Fast, Moderate, or Slow categories triangular membership functions, (b) Reinforcement Learning Optimization adjusts function thresholds enhance personalization over time. By refining timing necessity modifications, optimizes hints, difficulty levels, structured guidance, ensuring interventions neither premature nor delayed. was evaluated 100 postgraduate students. evaluation, efficiency, engagement, usability metrics, demonstrated promising results, particularly slow moderate learners, confirming that learning-driven weight adjustments significantly improve effectiveness.

Язык: Английский

Процитировано

0