Educational learning spaces encompass a spectrum, from traditional classrooms to contemporary online platforms and immersive virtual reality settings, fostering versatile teaching methods like collaboration, project-based, and experiential learning. Our study delves into modern higher education environments, particularly the shift from conventional to innovative spaces. Our focus centers on the benefits and challenges intrinsic to these emerging learning spaces, intending to enlighten educators, policymakers, and researchers. Our exploration commences by revealing the limitations entrenched within traditional learning environments, emphasizing the vital need for inventive solutions to meet evolving educational demands. We further investigate diverse learning scenarios, ranging from hybrid and remote setups to the integration of online platforms and virtual tools. Through this lens we navigate complexities introduced by these novel modalities, including potential reductions in face-to-face interactions and heightened demand for adept instructional and technological support. Lastly, our inquiry underscores the disparities between traditional and contemporary learning spaces, accentuating the potential for innovative settings to elevate higher education quality. Here, we illuminate the anticipated merits of such spaces, notably heightened student engagement, enriched collaboration, and amplified creativity. Concurrently, we explore technology’s pivotal role in shaping learning environments and ultimately influencing pedagogical methodologies. Our future research will explore how Artificial Intelligence can improve higher education.

In the ever-evolving landscape of wireless communication systems, including fifth-generation (5G) networks and beyond (B5G), accurate Modulation and Coding Scheme (MCS) prediction is crucial for optimizing data transmission efficiency and quality of service. Traditional MCS selection methods rely on predefined rules and heuristics, offering transparency and control but lacking adaptability in changing wireless conditions. The emergence of Machine Learning (ML) has brought transformative capabilities, particularly in MCS prediction. ML leverages data-driven models, promising improved accuracy and adaptability in dynamic wireless environments. This paper marks a novel endeavor in this domain, as it explores and evaluates a range of machine learning (ML) techniques for predicting MCS in orthogonal frequency-division multiplexing (OFDM) systems, representing the first such investigation in this field. Additionally, it introduces a specialized Deep Neural Network (DNN) architecture with two hidden layers for MCS prediction, guided by performance metrics such as accuracy, precision, recall, and F1-score. The examined ML methods include Artificial Neural Networks (ANN), Support Vector Machine (SVM), Random Forest (RF), and Bagging with k-NN (B-kNN). These methods undergo thorough training and evaluation using a dataset generated from simulations of non-standalone 5G networks. The study incorporates physical layer measurements and employs a ray-tracing path loss prediction model for comprehensive environmental characterization. Also, advanced data mining techniques preprocess raw data, addressing model underfitting and overfitting challenges. Finally, performance evaluation results reveal that the ANN with two hidden layers achieves the highest accuracy at 98.71%, while RF and B-kNN methods attain the lowest accuracy, below 88.65%. SVM and ANN models, with one and four hidden layers, respectively, demonstrate comparable MCS prediction accuracy, ranging from 97.02 to 97.30%.

Reconfigurable Intelligent Surfaces (RIS) and UAV-assisted mmWave communications have emerged as pivotal technologies to enhance connectivity and network reliability, particularly for next-generation 6G systems. However, harnessing their full potential poses significant challenges, particularly in optimizing the UAV’s trajectory and power allocation to maximize the Signal-to-Noise Ratio (SNR) while simultaneously mitigating interference with neighboring networks. To address these challenges, we propose a reinforcement learning (RL) based trajectory and transmit power optimization scheme that combines UAV with RIS. The proposed scheme consists of spatially distributed stationary UAV (S-UAV-mm) that directly serve their associated UEs, alongside a moving UAV (M-UAV-mm), that communicates with its dedicated users through a RIS, thereby ensuring optimal coverage for its UEs while minimizing interference to neighboring groups. Simulation results confirm that the RL algorithm converges to an optimal policy, yielding an average SNR improvement of at least 73.3% and achieving robust interference mitigation with an 87.5% enhancement through closed-loop power control.

This paper introduces a coordinated framework in which a base station (BS) and a Reconfigurable Intelligent Surfaces (RIS) jointly support their respective user groups while mitigating the impact of a Uncrewed Aerial Vehicle (UAV)-based jammer. Specifically, the RIS-assisted users rely on a reflective surface under attack from an UAV-jammer, and the BS simultaneously supports its own associated UEs alongside the RIS. We adopt an alternating optimization strategy that decomposes the original non-convex formulation into tractable subproblems using Block Coordinate Descent (BCD), thereby enabling multi-tier cooperation in complex interference environments. We frame our objective as the sum rate maximization, a metric for overall system performance, to maintain service quality and enhance robustness under severe jamming. The core of our methodology is the transformation of the resulting non-convex subproblems into tractable convex formulations via Semidefinite Programming (SDP). We employ a joint design of beamforming and phase shift optimization, whose combined effect leads to substantial performance improvements within the proposed framework. Extensive simulations and comparisons with existing algorithms demonstrate that this design achieves superior interference suppression and resource efficiency, significantly outperforming state-of-the-art baselines in sum rate, energy efficiency, UAV-jamming resilience and group-aware support for both BS- and RIS-served users.