Membrane fouling remains a major obstacle to the performance of the reverse osmosis (RO) desalination processes. Artificial intelligence (AI) is now a promising approach for the reliable modeling of these complex systems. This study evaluates three modeling techniques—multiple linear regression (MLR), artificial neural networks (ANNs), and support vector regression (SVR)—for predicting transmembrane pressure (TMP) at the Boujdour desalination plant, based on five input parameters: temperature, turbidity, pH, conductivity, and feedflow. The analysis is based on an original dataset of 195 daily measurements, and due to the absence of timestamps, the study focuses on state-to-TMP prediction rather than chronological forecasting, with no temporal generalization claimed. Approximately 2000 augmented training samples generated using a conservative SMOGN approach were used for model development, while performance evaluation relied exclusively on 39 independent real test observations. Two modeling strategies were adopted: (i) a minimalist approach based on significant variables identified by an ordinary least squares (OLS) model (pH and conductivity), and (ii) a multivariate approach integrating all parameters to capture non-linear interactions. A rigorous validation framework was put in place to avoid information leakage and ensure the robustness and generalizability of the models. Performance was evaluated using R², RMSE, and MAE metrics, supplemented by robustness and significance analyses including bootstrap confidence intervals, paired statistical comparisons, and interpretability analyses based on permutation importance, partial dependence plots (PDPs), and individual conditional expectation (ICE) curves. The results indicate that the SVR model achieves the best average predictive accuracy among the tested models, albeit with moderate explanatory power.

Immersive technologies, including virtual reality, augmented reality, and mixed reality, commonly known as VR, AR and MR, are transforming the educational landscape by providing engaging, interactive, and highly effective learning environments. This paper explores the impact of immersive technologies on teaching methodologies and learning outcomes, focusing on student engagement, knowledge retention, critical thinking, and accessibility. A mixed-methods approach, incorporating a systematic literature review, quantitative analysis of case studies, and qualitative interviews with educators and students, is employed to demonstrate the transformative potential of immersive technologies in education. The findings reveal that immersive learning environments significantly enhance student engagement, knowledge retention, critical thinking skills, and accessibility, offering a more engaging, effective, and inclusive approach to teaching and learning. The implications of these findings for the future of education are discussed, and actionable recommendations are provided for educators, policymakers, and researchers to leverage immersive technologies effectively in teaching and learning. The adoption of these innovations has the potential to create a more engaging, equitable, and impactful educational experience for all learners.

The convergence of Multi-Agent Systems (MAS) and immersive technologies represents a rapidly evolving research domain with significant implications for intelligent virtual environments. This systematic review presents a comprehensive comparative analysis of approaches, frameworks, and applications that integrate MAS within Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR) environments. Following PRISMA guidelines, we systematically reviewed 170 peer-reviewed articles published between 2020-2025, ultimately analyzing 25 high-quality studies that met our inclusion criteria. Our analysis reveals diverse architectural approaches including distributed multi-agent reinforcement learning frameworks, federated learning-enabled systems, and adaptive collaborative platforms. Key application domains identified include healthcare informatics, vehicular metaverses, educational training environments, and immersive collaboration systems. The study identifies critical challenges in real-time performance optimization, scalability with large agent populations, and maintaining quality of experience in distributed environments. Our findings contribute a novel classification framework for MAS-immersive technology integration, highlighting the shift towards privacy-preserving federated approaches and the emergence of metaverse applications. We present quantitative analysis of research trends and provide a roadmap for future developments in this intersection of artificial intelligence and immersive computing.

Digital mental health interventions increasingly require robust security frameworks, authenticated content delivery, and personalized therapeutic experiences. This systematic literature review examines the convergence of Blockchain technology, non-fungible tokens (NFTs), and deepfake synthesis in mental health applications, addressing a critical gap in interdisciplinary research. Following PRISMA guidelines, we conducted comprehensive searches across Scopus database (2014-2024), supplemented by IEEE Xplore, Web of Science, and PubMed Central. Our methodology employed PICO framework-based queries, identifying 15 037 relevant studies across seven queries (Q) configurations (Q1-Q7), with 5093 studies meeting inclusion criteria after rigorous quality assessment. Results demonstrate Blockchain provides immutable data governance (3962 studies), NFTs enable secure therapeutic asset tokenization (771 studies), while deepfakes facilitate personalized avatar-based therapy (230 studies). Cross-technology integration remains limited: Blockchain-NFTs combinations (102 studies), Blockchain-Deepfake integrations (24 studies), NFTs-Deepfake applications (2 studies), with only 2 studies addressing all three technologies simultaneously. This review establishes the first comprehensive taxonomy of converged technologies in mental health, identifying critical research directions for scalable, secure, and ethically-compliant digital therapeutic platforms.