Real-Time Neurofeedback-Driven Mobile Learning Systems with Cognitive State-Responsive Content Personalization for Enhanced Engagement

Real-time adaptive mobile learning systems have gained popularity due to their portability and flexibility; however, very few of them can adjust themselves in real time depending on the cognitive state of users, thus leading to low motivation and effectiveness. This current study introduces a Real-Time Neurofeedback-Driven Mobile Learning System (RNMP). It utilizes the information received via neurophysiological sensing to adapt its behavior in response to users' mental state and provide a more effective learning experience. The aim of the research is to improve user engagement and knowledge retention via content adaptation. The RNMP utilizes neurophysiological signals such as electroencephalography, heart rate variability, and eye tracking data obtained via wearable technology. These neuro signals go through a preprocessing stage, where they are filtered for noise, normalized, and converted into cognitive feature representation. After that, the classification of cognitive states is performed via a machine learning algorithm to define states such as high engagement, moderate attention, and cognitive load. Based on these states, an adaptation algorithm adjusts the complexity, pace, and modality of the material provided. An experimental assessment was carried out by leveraging a mixed dataset from DEAP and SEED, along with artificially generated mobile learning interaction data comprising 45 subjects and 1.2 million signal instances. The RNMP model was able to achieve an accuracy rate of 94.1% as compared to conventional mobile learning (78.2%), rule-based personalized adaptive learning (81.5%), deep-learning personalization models (86.7%), and reinforcement learning (89.3%). In addition to this, the model achieved an engagement score of 0.91, a retention rate 89.7%, and a latency of 98ms, proving its effectiveness in real-world applications. The findings demonstrate that neurofeedback-based personalization greatly enhances cognitive engagement and learning effectiveness. The paper concludes that cognitive state detection, along with adaptive learning, is an effective methodology to be implemented in next-generation mobile learning platforms.

Hali tarjima qilinmagan