Key points are not available for this paper at this time.
This paper presents Gesture-Enhanced Adaptive Learning and Personalization (GEALP), an educational platform that integrates cognitive bulking and AI technologies to address key challenges in inclusive education, such as gesture recognition deficiencies, modal conversion barriers, and personalization gaps. Existing educational systems often fail to accommodate users relying on gestures, lack seamless integration across learning modalities, and provide limited adaptability to individual learning preferences. GEALP introduces a three-tier architecture combining 3D-CNN-based gesture recognition with attention-augmented temporal processing, bi-directional multi-modal content conversion, and dynamic learning adaptation supported by real-time feedback loops. Experiments with 1,000 users, 5,000 learning sessions, and 10,000 gestures demonstrate GEALP's superior performance. Results show improved gesture recognition accuracy (95.5%), user interaction (92.8%), and learning effectiveness (89.2%) compared to existing systems. The system also achieves 13.2% higher processing efficiency compared than benchmark systems such as MALS (8.1%) and PELS IRT (6.0%). The system presents an innovative bi-directional conversion framework enables seamlessly transformation across textual, auditory, visual, and gestural modalities while leveraging temporal attention mechanisms for low-latency gesture interpretation (average response time of 150 ms). Platform accessibility scores (9.2/10), personalization accuracy (94.2%), and knowledge retention rates (87.5%) further confirm the robustness of GEALP, indicating its potential for shaping future personalized learning environments.
Parveen et al. (Mon,) studied this question.