Background: Dental caries is a prevalent, complex, chronic illness that is avoidable. Better dental health outcomes are achieved as a result of accurate and early caries risk prediction in children, which also helps to avoid additional expenses and repercussions. In recent years, artificial intelligence (AI) has been employed in the medical field to aid in the diagnosis and treatment of medical diseases. This technology is a critical tool for the early prediction of the risk of developing caries. Aim: Through the development of computational models and the use of machine learning classification techniques, we investigated the potential for dental caries factors and lifestyle among children under the age of five. Design: A total of 780 parents and their children under the age of five made up the sample. To build a classification model with high accuracy to predict caries risk in 0–5-year-old children, ten different machine learning modelling techniques (DT, XGBoost, KNN, LR, MLP, RF, SVM (linear, rbf, poly, sigmoid)) and two assessment methods (Leave-One-Out and K-fold) were utilised. The best classification model for caries risk prediction was chosen by analysing each classification model’s accuracy, specificity, and sensitivity. Results: Machine learning helped with the creation of computer algorithms that could take a variety of parameters into account, as well as the identification of risk factors for childhood caries. The performance of the classifier is almost unbiased, making it generalizable. Among all applied machine learning algorithms, Multilayer Perceptron and Random Forest had the best accuracy, with 97.4%. Support Vector Machine with RBF Kernel (with an accuracy of 97.4%) was better than Extreme Gradient Boosting (with 94.9% accuracy). Conclusion: The outcomes of this study show the potential of regular screening of children for caries risk by experts and finding the risk scores of dental caries for any individual. Therefore, in order to avoid dental caries, it is possible to concentrate on each individual by utilizing machine learning modelling.

Hydroinformatics education has been constrained by pedagogical approaches that fail to convey the complexity of water systems. Virtual Reality (VR) offers a transformative solution through interactive and experiential learning. This study introduces HydroVerse Education, an immersive virtual classroom integrating VR and artificial intelligence to modernize hydroinformatics education. Using Unreal Engine, Metahuman, and Generative AI, the platform creates an interactive environment with immersive communication and knowledge generation. An AI-driven virtual instructor enables real-time voice-based interactions providing personalized guidance for diverse learning styles. HydroVerse Education enhances engagement through realistic simulations of complex hydroinformatics scenarios, bridging theory and practice. Addressing the need for accessible, cost-effective educational tools, the platform offers flexible, adaptive learning experiences for instructors, and researchers. This study details the system's development, architecture, and capabilities, while discussing challenges and future directions for VR integration in education.

Scientific conferences are essential for knowledge exchange but often suffer from limited engagement, accessibility challenges, and passive content delivery, whether in traditional physical venues or current virtual formats. This paper introduces the HydroVerse Immersive Virtual Conference Environment with Interactive Metahuman AI, a novel system that reimagines conference presentations through the seamless integration of Extended Reality (XR), generative Artificial Intelligence (AI), and web technologies. Within an immersive 3D virtual space, users can navigate a presentation hall, select academic presentations, and engage in real-time, voice-driven interactions with a highly realistic Metahuman avatar. Powered by Unreal Engine and OpenAI’s language models, the Metahuman delivers concise voice-over summaries and answers user questions with synthesized speech and synchronized lip movements, creating an intuitive and lifelike communication experience. The system architecture includes modules for high-fidelity rendering, natural language processing, semantic content retrieval, and adaptive interaction workflows. Together, these components offer a dynamic and accessible alternative to static conference models. This study introduces a new paradigm in scientific communication, one that emphasizes personalization, engagement, and embodied understanding, and supports more inclusive, interactive, and effective academic exchange.