Category: Artificial intelligence
Teacher candidates mostly viewed AI positively in language learning
Study of 46 Turkish language teacher candidates reveals predominantly positive metaphorical views of AI in education, with 78% expressing optimism, but highlights need for ethics education.
Network DLN shows cost-adjusted utility gains at large scale
Computational models of cognitive stages show that network-stage architectures outperform linear stages through estimation efficiency and explicit exposure tracking, not just parameter reduction.
Thompson sampling improved exercise recommendations for learner skill gain
Contextual Thompson sampling approach for personalizing exercise sequences in digital learning environments, optimizing skill advancement at scale using bandit-based algorithms.
Adaptive music generation improved emotional matching
Emotion-Conditioned Deep Reinforcement Learning framework for adaptive music generation. Achieves 98% emotion mapping accuracy with 280ms real-time responsiveness, enabling dynamic musical.
Emotion-adaptive eco-feedback concepts were generated for home assistants
Study investigating emotion-adaptive eco-feedback in personal assistants through co-design methodology, generating eight design concepts integrating emotion AI for home energy management.
AI campus platform reports better engagement and faster evaluation
Gurukulya is an AI-powered smart campus platform combining LLMs, sentiment analysis, and automated assessment to boost student engagement, reduce evaluation time by 85%, and improve learning.
Vision–language model improved pediatric dental disease classification
Deep learning vision-language model for diagnosing pediatric dental diseases in panoramic radiographs, combining visual and textual information with 90% accuracy for caries and periapical.
Prompt-driven KG-enhanced LLM reasoning improved KBQA accuracy
Prompt-driven framework combining LLMs with knowledge graphs for reliable knowledge-based question answering through structured subgraph retrieval and stepwise reasoning validation.
BrainADNet improves depression diagnosis across episode stages
Graph neural networks with augmented brain signals improve MDD diagnosis through gender-specific and stage-wise analysis, enabling personalized therapeutic strategies.
Agentic AI generated decision tables from BPMN models
Agentic AI system for automated DMN decision table generation from BPMN models, reducing human error and cognitive bias in critical business process decision management.
