The unmanned aerial vehicles (UAVs) are new types of user equipment connected to cellular networks with promising revenue through additional new subscribers and use cases, especially for aviation sector. In addition, UAVs are accepted as an extension to base stations by boosting coverage, spectral efficiency and user quality of experience. In this context, the main aim of this project is to provide high quality of data link and smooth UAVs connectivity into cellular network infrastructure. The UAVs allow rapid deployment of a multi-hop communication backbone in challenging environments with applications for public safety, delivery and monitoring. Therefore, Unmanned aerial vehicles (UAVs) can be used as complementary infrastructure to provide wireless services for the ground users or they may require wireless connectivity from the ground for a safe and reliable operation. This PhD project aims to study several UAV use-cases covering 5G core networks and to validate UAV/UTM connectivity KPIs for supporting such challenging. The project will drive UAV and 5G networks to a win-win position, on one hand by showing that 5G is able to guarantee UAV vertical KPIs, and on the other hand by demonstrating that 5G can support challenging use-cases that put pressure on network resources. To achieve that we will look to study of where 5G can add value to improve the existing UAV connectivity.

1

Provide the state of art regarding tools and techniques used for big data and predictive maintenance. Implement and validate models for feature extraction and fault detection and isolation or diagnostics. Implement and validate models for fault prognostics. Design, implement and validate the framework Stage 1: Establish base lines and literature review. Examine common practices, and discoveries in the field related to techniques and process, and common tools and infrastructures used. Risk assessment. Stage 2: Identify research gap, and review aims. Data collection, establish requirements for the framework requirement. Data cleaning and preparation, data management plan. Stage 3: Using a condition based maintenance process, begin data analysis. Feature extraction; fault detection and isolation; diagnosis and prognostics using novel "big data" tools and knowledge discovery techniques. Stage 4: Results visualisation; framework implemented and validated. The work aims at a novel approach to time series analysis for system and machine faults, integrating physics, engineering know-how and discovered data patterns. The work has been trialled on train engine performance behaviour, door response, and wheel slip, seeking early and robust detection, diagnosis and prognosis.

The PhD project aims in tracing the structural pathway of liquid metals to vitrification and revealing the structural origin of the remarkable slowdown of the dynamics occurring in the super-cooled liquids that leads to the formation of glasses. How the atomic structure of metallic liquids evolves during rapid quenching is currently not well understood. This limitation is largely attributed to the experimental times for the acquisition of diffraction data being longer than the short quenching times required for vitrification, and thus hindering in-situ structural measurements. A sophisticated approach will be used to overcome these limitations and study the structure of metallic liquids, super-cooled liquids and glasses using state of the art structural characterization techniques and modelling including high energy synchrotron radiation and containerless solidification methods. This PhD project includes the structural analysis of the liquid, super-cooled liquid and glassy states of glass forming alloys using X-ray Diffraction, pair and radial distribution function and electron microscopy. Molecular Dynamics and Reverse Monte Carlo Simulations will be employed to provide insights of the evolution of the local geometrical atomic arrangements in the liquid and the glassy structures and will be compared with the experimental results.

Artificial Intelligence (AI) is revolutionising a wide range of industries. Wireless networks with emerging high dimensional challenges are set to benefit from data-driven deep learning optimisation across layers. In particular, we expect that the deep supervised and deep reinforcement learning modules can resolve high-dimensionality inputs, achieve near optimal solutions, and efficiently scale via confederated learning. However, what is not well understood is the energy cost and carbon footprint of AI in future wireless networks. The danger is that intelligent networks are not green networks and that the recent progress made in green communication risk being undermined by the new breed of AI-based wireless communication. Here, in this project, we propose to develop green machine learning algorithms for radio resource management. This will lead to a future of intelligent and sustainable wireless networking.