http://bura.brunel.ac.uk/handle/2438/8623 2026-04-13T13:29:42Z http://bura.brunel.ac.uk/handle/2438/33068 Title: Design and development of an AI enhanced channel coding technique with adaptive reconfigurable intelligent surface for terahertz 6G communication Authors: Ahmed AL-Joudi, Aya Khalid Abstract: This thesis presents a novel approach to design and implement a new channel coding method combined with a Adaptive RIS (ARIS) to enhance Terahertz (THz) communication in 6G networks. The research addresses the crucial requirements of 6G communication, including ultra-fast data transmission, minimal delay, extensive connectivity, and optimal energy usage. The innovative channel coding approaches, Polar Convolutional Serial Code (PCSC) and Polar Convolutional Parallel Code (PCPC), are specifically designed to enhance the reliability and data transfer rate of wireless communication systems operating at THz frequencies. Their performance is rigorously evaluated in congested network conditions, a common scenario in 6G applications, in conjunction with Non Orthogonal Multiple Access (NOMA) strategies. A key achievement in this research is the integration of ARIS into the commu-nication system, leading to the development of a ARIS Decision Making Algorithm (ARIS-DMA). This technology optimises signal strength and coverage by dynamically adjusting surface reflection and transmission properties based on the user’s location and network conditions. The ARIS-DMA effectively reduces power loss and latency, providing comprehensive coverage and a 70% signal power loss reduction, instilling confidence of users about the progress in the field. In addition, the thesis investigates the application of Deep Learning (DL) methods for decoding PCPC. It suggests a Deep Q Network (DQN) based Deep Q Network ARISDMA (DQN-ARISDMA) to improve beamforming and increase spectral efficiency. The findings exhibit significant enhancements in data transmission speeds, utilisation of the frequency spectrum, and the ability of the system to respond promptly, all of which are vital for time-sensitive applications in 6G networks. The outcomes of this study contribute significantly to the development of communication systems that can meet the rigorous standards of future 6G networks while also being scalable, energy-efficient, and reliable. This advancement creates opportunities for progress in areas such as smart cities, autonomous vehicles, and augmented/virtual reality experiences, demonstrating the practical implications of our research. Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London 2026-01-01T00:00:00Z http://bura.brunel.ac.uk/handle/2438/32827 Title: Development of YOLO-based object detection and tracking systems for airport ground safety and simulation-based collision analysis Authors: Bingol, Emre Can Abstract: Airport ground incidents remain one of the major safety concerns in aviation, causing operational disruption and substantial economic losses. Although conventional surveillance and sensing can support surface awareness, cost, deployment constraints, and limited interpretability at close range motivate low-cost, vision-based alternatives. Key research gaps include (i) apron-specific, part-level, openly available labelled datasets, (ii) systematic and fair benchmarking of modern deep learning architectures under consistent evaluation conditions, and (iii) integrated risk analysis that progresses from perception to actionable early warning. This thesis addresses these gaps by developing and validating a scalable early-warning framework based on Computer Vision (CV) and Deep Learning (DL), designed for integration with existing Closed-Circuit Television (CCTV) infrastructures. The thesis follows a multi-stage methodology. First, a new detection and segmentation dataset was constructed with five aircraft classes (airplane, wing, nose, tail, and fuselage) to support part-level perception for apron safety. Using this dataset, twelve modern object detection and segmentation architectures were trained and evaluated under consistent experimental settings to establish a benchmarking baseline. YOLOv8-Seg (You Only Look Once, version 8-Segmentation) emerged as the most suitable backbone for the intended operational constraints. Second, to improve robust detection and segmentation of aircraft and their components, YOLOv8-Seg was systematically optimised through a six-step, ablation-driven pipeline, spanning parameter tuning, loss-function refinement, data augmentation, and inference-efficiency improvements. Third, a Multi-Object Tracking (MOT) dataset was created and annotated in the MOTChallenge format to benchmark leading trackers under identical evaluation settings. Finally, two complementary safety layers were developed: (i) a reactive module that issues immediate alerts using image-plane geometric proximity derived from segmentation outputs, and (ii) a proactive module that forecasts short-horizon conflicts by extrapolating past motion and evaluating future overlap using Intersection over Union (IoU). Experimental results show that the optimised YOLOv8-Seg model significantly improves segmentation performance by +8.04 points in mAP@0.5:0.95 (mean Average Precision averaged over IoU thresholds from 0.50 to 0.95) and +4.74 points in mAP@0.5. On the tracking benchmark with airplane-only ground truth, DeepSORT achieved the strongest overall performance, reaching 92.77% Multi-Object Tracking Accuracy (MOTA) with 93.27% recall. The framework was validated across multiple representative scenarios using both simulated and real-world video, supporting the feasibility of a low-cost, CCTV-compatible approach for enhancing apron safety through integrated perception, tracking, and early warning. Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London 2025-01-01T00:00:00Z http://bura.brunel.ac.uk/handle/2438/32754 Title: Analysis of backhaul networks for developing countries to support next generation communication systems Authors: Al-Zubaidi, Inas Abstract: In its most basic form, the target of fifth generation (5G) is to provide reliable and continued connectivity for the user despite obstacles and challenges. These obstacles and challenges vary depending on the scenario, whether it’s an urban or rural area in developed or developing countries. This thesis focuses on the 5G backhaul for standalone (SA) network and the im-pacts of backhaul technologies on the Quality of Service (QoS) and user experiences, in particular, end to end delay (E2E) and capacity planning requirements. In par-ticular, the aim is to facilitate the work of providers, developers, and investors when planning to introduce 5G technology to developing countries. This work looks into employing simulation-based approach to consider bandwidth aspects when design-ing/ upgrading current/ future cellular systems in developing countries. It presents a scheme to maximize the use of bandwidth considering both capacity and delay aspects and helps to identify major parameters that influence system design for different 5G use cases and scenarios. The result proves that the method to determine the required link capacity is by observing the traffic delay and users access statistics as well as by increasing the capacity incrementally by changing the factor for each link in the network, un-til optimal capacity is achieved. It also indicates that within the ”broadband in the crowd” scenario for 5G services and applications, the necessary bandwidth for last-mile network connections can vary depending on the service type. Specifically, bandwidth requirements can be lessened for ultra-low latency services and applica-tions, with even greater reductions possible for those that do not require such low latency. These adjustments are observed when the backbone link is operating at its full capacity. The finding shows that for developing countries, and by considering the cost of the bit per second, user down link/ uplink, and convenience of user terminals as more critical considerations for the adoption of one of the technologies for backhauling 5G traffic, a satellite and hybrid topology based on the existing networks, financial considerations will play an important role in determining the backhaul network topology with optimizing for the specific requirements. Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London 2024-01-01T00:00:00Z http://bura.brunel.ac.uk/handle/2438/32680 Title: Advancing AI-driven lung ultrasound diagnostics for COVID-19: Procedural data synthesis, image enhancement, and pleural line detection Authors: Hill, Cameron Abstract: This thesis presents novel advancements in lung ultrasound imaging through the integration of computational techniques and artificial intelligence. Addressing critical challenges such as low contrast, noise, data scarcity, and diagnostic variability, the research focuses on three core areas: contrast enhancement, synthetic data generation, and AI-driven diagnostic models for COVID-19 detection. A contrast enhancement technique utilising Rayleigh Gaussian Mixture Models and k-means clustering was developed to improve image clarity while preserving diagnostic features. This method demonstrated substantial improvements in pleural line detection accuracy, with Support Vector Machine (SVM)-based models achieving 84.3% accuracy and superior preci-sion metrics. To mitigate the scarcity of annotated lung ultrasound datasets, synthetic image gener-ation methods were implemented. Generative Adversarial Networks (GANs) were used to produce realistic ultrasound images, achieving a Structural Similarity Index (SSIM) of 0.46 and a Fr´echet Inception Distance (FID) of 257.95, showcasing their potential in addressing data limitations. The thesis also introduces P-Net, a multi-architecture neural network ensemble, designed to classify lung ultrasound images for COVID-19 diagnostics. P-Net integrates segmentation outputs and latent features, achieving a Dice coefficient of 0.87 and Intersection-over-Union (IoU) of 0.89, demonstrating robust diagnostic accuracy even in limited data scenarios. These contributions enhance the utility of lung ultrasound imaging, particularly for diag-nosing COVID-19, by combining advanced computational methods with clinical needs. This research underscores the transformative potential of artificial intelligence in medical imaging, paving the way for improved patient outcomes and innovations in healthcare technology. Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London 2025-01-01T00:00:00Z