http://theses.ncl.ac.uk/jspui/handle/10443/5223 2026-02-04T02:23:13Z http://theses.ncl.ac.uk/jspui/handle/10443/6666 Title: Bayesian optimisation for expensive physical experiments and computer simulators with application in fluid dynamics Authors: Diessner, Mike Abstract: Expensive black-box functions such as physical experiments and computer simulators are challenging to optimise as they cannot be solved analytically, and only small numbers of function evaluations are available for optimisation. This prevents use of conventional methods that rely on gradient information or larger numbers of function evaluations, requiring a specialised optimisation strategy. Bayesian optimisation is a sample-efficient strategy that represents the objective function through a surrogate model and guides the exploration of the input space with heuristics—so-called acquisition criteria—to select promising candidate points sequentially. Expensive black-box functions are a common occurrence in fluid dynamics where the underlying systems, for example the Navier-Stokes equations, can be too complex to solve explicitly and can be viewed as a black box. In addition, the expensive nature of the associated experiments and simulations makes Bayesian optimisation a prime candidate. However, the Bayesian optimisation literature is mainly geared towards statisticians and computer scientists and is potentially challenging to scrutinise and apply for non-experts. Thus, the main motivation of this thesis is to make Bayesian optimisation more accessible and answer some fundamental questions overlooked in the literature, while also developing techniques for specific challenges encountered in but not limited to fluid dynamics. This thesis studies three topics for applying Bayesian optimisation to experiments and simulators. Firstly, it investigates key choices in Bayesian optimisation empirically, such as the choice of the acquisition criterion and the number of data points used for initialisation, and applies the findings to two computer simulators with the objective of controlling air flow to maximise the skin-friction drag reduction over a flat plate—mimicking the surface of a moving vehicle such as the wing of an aeroplane. Secondly, NUBO—an open-source Python package for optimising expensive experiments and simulators aimed at practitioners of Bayesian optimisation—is presented, and its functionalities are discussed. This transparent package allows users to tailor the optimisation loop to their specific problems and supports sequential single-point, parallel multi-point and asynchronous optimisation for bounded, constrained and mixed (discrete and continuous) input parameter spaces. Lastly, problems affected by external environmental variables that cannot be controlled are investigated, and ENVBO—a novel algorithm—is introduced. ENVBO fits a global surrogate model over all controllable and environmental variables but optimises the acquisition criterion only with regard to the controllable variables while keeping the environmental variables fixed at a current measurement. Important properties of ENVBO, such as the robustness to noisy objective functions and the number of environmental variables, are studied. ENVBO is applied to a wind farm simulator to maximise energy production by (a) finding optimal positions for four wind turbines within a complex terrain with changing wind directions and (b) setting optimal derating factors of a row of five wind turbines subject to changing wind speeds. Description: PhD Thesis 2025-01-01T00:00:00Z http://theses.ncl.ac.uk/jspui/handle/10443/6665 Title: mitoML: Machine Learning to Understand Mitochondrial Disease Pathology Authors: Khan, Mir Atif Ali Abstract: Mitochondria are organelles that reside in virtually every cell of the human body and provide the energy for the cells to function. OXPHOS is the main metabolic pathway through which mitochondria generate energy, it is a machinery made up of five complexes each built with sub-units of multiple proteins and molecules. Defects in OXPHOS machinery manifest as results of genetic mutations and lead to mitochondrial disease. Mitochondrial diseases are currently untreatable due to our limited understanding of their pathology. The study of mitochondrial disease pathology involves discovery of OXPHOS protein expression patterns linked to various genetic mutations. Mitochondrial disease affects high energy demanding cells like Skeletal Muscle (SM) cells (myofibres). The expression of various OXPHOS proteins in myofibres taken from SM biopsies is studied. These OXPHOS proteins in SM tissue are observed using various imaging techniques such as Imaging Mass Cytometry (IMC). IMC produces high dimensional (up to 40 channels) multiplexed pseudo-images representing spatial variation in the expression of a panel of OXPHOS proteins within a tissue, including sub-cellular variation. In previous methods good quality ‘analysable’ myofibres in these multichannel images are segmented and various statistical summaries, such as mean protein expression, are computed per myofibre. Statistical summaries of various groups of myofibres linked with different genetic mutations and a healthy control group are compared to analyse and understand the OXPHOS protein expression patterns of various mitochondrial diseases. Theses methods have a number of limitations i) profiling OXPHOS protein patterns in high dimensionality data: Due to high dimensionality multiplex data, it is not possible to classify and discover the OXPHOS protein expression pattern for four out of five groups of genetic mutations affecting mitochondria that have been studied [1] i.e. except for one group of genetic mutation the classification accuracy for all other groups was below 90%. ii) Precise segmentation and curation of myofibres: It is not possible to precisely segment and curate myofibres with existing applications without heavy manual corrections. iii) The use of statistical summaries per myofibre ignores all intra-myofibre features. There are many hypotheses [2, 3] that theorise the existence of differential features within myofibre in various mitochondrial dysfunctions. In this thesis I use Machine Learning (ML)-specifically logistic regression and XGboost, and various Deep Learning (DL) methods to address the three limitations mentioned above with the following contributions. I) Classify myofibres of mitochondrial patients affected by various genetic mutations, using explainable ML and myofibre statistical summaries. I show that using ML the classification accuracy for all five mutations exceeds 90% . I also demonstrate the use of explainable ML methods to discover the OXPHOS protein expression patterns associated with these high predictive accuracy ML models. II) Precise myofibre segmentation and curation pipeline: I developed ‘myocytoML’ a precise myofibre segmentation and curation pipeline that meets the quality of gold standard manual human annotations. This also led to the building of NCL-SM: A large dataset of more than 50k manually annotated myofibres, which is now available for public use. III) Classify myofibres of mitochondrial patients affected by various genetic mutations, using explainable DL and segmented multichannel raw images. I show that using DL the classification accuracy for all five mutations exceeds 98%. I also demonstrate the use of explainable DL methods to discover the OXPHOS protein expression patterns associated with these high predictive accuracy DL models. Description: PhD Thesis 2025-01-01T00:00:00Z http://theses.ncl.ac.uk/jspui/handle/10443/6657 Title: Computational modelling of immune interaction and epidermal homeostasis in Psoriasis Authors: Paramalingam, Dinika Abstract: Psoriasis is an incurable chronic inflammatory skin disease characterised by immune cytokinestimulated epidermal hyperproliferation. This results in the skin becoming red with scaly plaques that can appear anywhere on the body, decreasing the quality of life for patients. Previous modelling studies of psoriatic skin have been limited to 2D models and lacked cellcell interactions. I have developed a 3D agent-based model of epidermal cell dynamics to gain insights into how immune cytokine stimuli induces hyperproliferation in psoriasis to better understand disease formation and structural changes. The model takes into account the main cell types - stem, transit-amplifying (TA), differentiated and T cells with the growth and division of stem and TA cells governed by extracellular calcium, endogenous growth factors and immune cytokines in line with known experimental data. Each cell has a set of attributes (growth rate, division probability, position, etc) whose values are governed by processes such as monod-based cellular growth model, probability-based division based on calcium and cytokine concentration and various forces to form the epidermal layers. Different scenarios can be simulated including delineating how psoriasis developed in response to immune stimuli concentration and duration and changing the rate of division of proliferative cells to capture how it changes from normal to diseased state. The model has 2 steady states, healthy (non-lesional) and psoriatic (lesional) skin. Transition from healthy to psoriatic state is triggered by a temporary cytokine stimulus which causes hyperproliferation to occur, a hallmark of psoriasis. This results in the deepening of rete ridges and thickening of the epidermal structure. The model has been validated against population ratios of stem, TA, differentiated, and T cells, cell cycle and turnover times in vivo. The model simulates the structural properties of epidermis, including layer stratification, formation of wave-like rete ridges, change in epidermal height and length of rete ridges from normal to psoriatic. The model has helped gain some insights on the complex spatio-temporal changes when transitioning between the 2 steady states and how a shot of temporary cytokine stimulus can induce different severity of psoriasis and how proliferation is altered between healthy and psoriatic skin in line with known literature. This provides the basis to study different cytokine simulation variations of psoriasis development and tracking of cell proliferation in the lab. In addition, it provides a base to model the effects of psoriasis treatments such as UVB or biologics and predict potential treatment outcomes for patients. Description: PhD Thesis 2024-01-01T00:00:00Z http://theses.ncl.ac.uk/jspui/handle/10443/6655 Title: Provenance Tracking of In-game Virtual Items via the Blockchain Authors: Lu, Yiang Abstract: This thesis explores the integration of blockchain technology within the gaming industry, with a specific focus on in-game virtual item trading. Through a comprehensive examination of various consensus algorithms, the research identifies optimal solutions that enhance latency and throughput in real-time game trading. A specialized communication model for blockchain-based streamed gaming is developed, offering new insights into transaction delays and enriching our understanding of real-time trading dynamics within gaming environments. A significant contribution is the development of a mathematical model designed to predict system performance and resource allocation, holding substantial potential for enhancing system optimization within the gaming industry. The thesis also delves into the delivery of video games through cloud and edge-based technologies, revolutionizing the gaming industry by enabling players to access and play games on various devices. Experimental aspects are detailed, including in-game trading transactions, communication models, and simulator design, leading to comprehensive results and analysis. The concluding chapter synthesizes the findings, emphasizing the integration of blockchain technology in the gaming industry, the development of a mathematical model, and the potential applications in creating secure platforms for trading in-game assets. Future work includes the exciting avenue of developing a lighting network simulation for cloud game trading. This research not only advances the theoretical understanding of blockchain technology in gaming but also provides practical models and tools that can guide future research and development in this field. Description: Ph. D. Thesis. 2025-01-01T00:00:00Z