It is anticipated that the backbone of Smart Cities concerning automation and networking will be formed by Unmanned Aerial Vehicles in the imminent future. Therefore, our research focuses on developing advanced microcontrollers embedded with Artificial Intelligence techniques for self-governing Unmanned Aerial Vehicles. The main objective of this research was to enable full automation for the execution of flight paths with non-trivial sequences that will be performed with centimetre-level accuracy. Also, by utilising dynamic flight plans and trajectories, we aim to secure autonomous aviation based on norms, with control loops and fundamental constraints. More specifically, we evolved a novel algorithmic technique for trajectory optimisation, which deploys a modification to the A* search algorithm, implemented by the Haversine formula and enhances accuracy using Vincenty's formula. Furthermore, realistic values for trajectory optimisation and obstacle avoidance were found through the implementation of a simulative investigation. The outcomes of our methodology indicate that the safety constraints associated with the integration of Unmanned Aerial Vehicles in the urban environment can be significantly mitigated. Consequently, their effectiveness will be increased in realising their diverse operations and capabilities.

Sixth-generation networks and vehicular Ad hoc networks advancement brought us to the cusp of a new era. Autonomous Vehicles with a plethora of advanced applications require a substantially enhanced vehicle-to-everything communication network. The infrastructure should efficiently support hyper-fast, ultra-reliable, and low-latency massive data exchange. Roadside units were initially exploited as a promising communication solution to overcome this challenge. However, the challenging integration with the infrastructure led to the investigation of additional solutions. Unmanned aerial vehicles are one of the most dominant assistive solutions due to their inherent advantage of mobility. Moreover, air-to-air and ground-to-air networks are more efficient than ground-to-ground. Nevertheless, it is a prerequisite to leverage the potential of unmanned aerial vehicles to attain nationwide Vehicle-to-Everything connectivity. Therefore, we focused our research orientation on developing a strategy to optimize the network’s coverage within the intelligent transportation systems framework. In particular, we have deployed an innovative algorithmic technique that constructs Voronoi diagrams using circles. Besides, we applied the poison point process to determine the optimum locations of the transceivers’ establishment. Simulation results illustrate full network coverage for the tested area after the required iterations. Also, time complexity evaluation proved the simplicity of the proposed algorithm.

This study explores the integration of sustainable practices in the advancing domain of sixth-generation and beyond (6G+) network technologies, with a particular focus on enhancing the efficiency of search and rescue operations. It presents a comprehensive strategy for network slicing designed to bolster seamless communication and operational efficacy of emergency response teams in varied and ever-changing conditions. It presents an innovative approach to managing workload fluctuations in network slicing. Also, it introduces a new slice configuration mechanism to prioritize signals for devices within the complex, compelling, hierarchical network systems. Incorporating a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm is central to the approach, tackling the complexity of implementing effective communication strategies across multiple network layers. Our findings demonstrate a highly adaptable and real-time slice configuration technique within System of Systems (SoS) environments, offering significant enhancements in systems engineering and emergency communication management. This approach contributes to the robustness and reliability of emergency response communications and underscores the importance of integrating environmental sustainability in developing next-generation network technologies.

The rapid advancement of Artificial Intelligence (AI) is reshaping industries and driving global innovation. However, the increasing complexity of AI models demands substantial data and computational resources, leading to significant energy consumption and environmental impact. This article explores the integration of quantum computing and end-to-end automation strategies in cloud-edge architectures. It proposes a hybrid quantum-classical AI framework that enhances training efficiency and reduces data and processing intensity by minimizing energy consumption. The framework leverages automated model orchestration, adaptive resource allocation, and intelligent data processing at the edge to improve system efficiency. In addition, it addresses ethical considerations, including privacy, fairness, and trustworthiness, to ensure alignment with human values. This approach significantly improves AI performance while fostering a sustainable and ethical AI ecosystem.

As we stand on the cusp of an evolution in effective and confidential smart healthcare systems, the disciplines of Psychology and Neuroscience remain a barrier. The obstacle of stress and sentiment classification is an enduring challenge to the field. Therefore, this research identifies mental health by analysing and interpreting acquired biological data. By employing convolutional neural networks in conjunction with transfer learning, the article seeks to leverage physiological signs driven by sensors for health monitoring. More precisely, we elaborate on the correlation between vital signs, arousal, and vigour data to classify a person’s sentimental state. A novel algorithmic methodology is proposed in which the source and target domains are leveraged adaptively by homogeneous and heterogeneous transfer learning. A comprehensive analysis of the outcomes from real-world acquired datasets was performed to demonstrate the proposed method’s effectiveness compared to state-of-the-art classification techniques in the field.