Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 22 for “"model refinement"”.
-
Assessment of Varying Model Representations in CFD Simulations
… thesis investigates the effects of varying model refinement and representation of computational fluid dynamics (CFD) simulations in two case studies. Product and process realization in engineering design requires substantial resources (time and money) in order to test novel designs for …
-
Machine Learning Methods for Protein Model Quality Estimation
In my research, I developed protein model quality estimation methods aimed at evaluating the reliability of computationally predicted protein models in the absence of experimentally solved ground truth structures. These methods specifically focus on estimating errors within the protein models to …
-
Weakly-supervised text classification
… such attractiveness, neural text classification models suffer from the lack of training data in many real-world applications. Although many semi-supervised and weakly-supervised text classification models exist, they cannot be easily applied to deep neural models and meanwhile support limited …
-
Uncertainty-Integrated Surrogate Modeling for Complex System Optimization
<p>Approximation models such as surrogate models provide a tractable substitute to expensive physical simulations and an effective solution to the potential lack of quantitative models of system behavior. These capabilities not only enable the efficient design of complex systems, but is also …
-
Bridging the Health Divide: Achieving Equitable Healthcare Access in Kenya through Artificial Intelligence
… Generative Pre-trained Transformer (GPT) models, in designing culturally sensitive hospitals for rural Kenya. The research addresses the critical need for improved healthcare infrastructure in underserved areas, focusing on the potential of AI to create efficient, adaptable, and …
-
Evaluating Sources of Arsenic in Groundwater in Virginia using a Logistic Regression Model
… study, I have constructed a logistic regression model, using existing datasets of environmental parameters to predict the probability of As concentrations above 5 parts per billion (ppb) in Virginia groundwater and to evaluate if geologic or other characteristics are linked to elevated As …
-
Empirical Multiphase Model for Strength Evolution of High-Chromium Steel Alloys
… Evolution and Thermal Ageing-Linked Strength) model. An empirical multiphase framework coupling phase-field microstructural predictions with mechanical property evolution through phenomenological energy-strength relationships. A comprehensive six-month isothermal ageing study at 500 °C …
-
Acies-OS: a twin-assisted systems architecture for edge intelligence
… innovation that spans from performance modeling and resource optimization to workflow orchestration and adaptive learning. This dissertation introduces Acies-OS, a twin-assisted, content-centric middleware framework designed to enhance the efficiency and robustness of distributed edge …
-
Measurement and Analysis of Sub-Convective Pressure Fluctuations in Turbulent Boundary Layers: A Novel Methodology
… counterpart, making it difficult to measure and model accurately. Existing studies rely on limited measurements, constrained by instrumentation and facility capabilities, leading to empirical wall pressure models with restricted accuracy and applicability. This study presents the first …
-
Improving microbial fate and transport modeling to support TMDL development in an urban watershed
… in the United States. Continuous watershed-scale models are typically employed to facilitate Total Maximum Daily Load (TMDL) restoration efforts. Due to limited understanding of microbial fate and transport, predictions of FIB concentrations are associated with considerable uncertainty relative to …
-
Facilitating golden mole conservation in South African highland grasslands : a predictive modelling approach
… This study employed species distribution modelling to predict the distributional ranges of these taxa, and involved four main processes: (i) creating initial models trained on sparse museum data records; (ii) ground-truthing field surveys during austral spring/summer to gather additional …
-
Functional and mathematical analysis of the glyoxylate shunt in Streptomyces coelicolor
Streptomyces coelicolor is the model organism for the genus Streptomyces, which produces many bioactive secondary metabolites with clinical applications. Based on work done in Escherichia coli, the glyoxylate shunt was thought to be the main anapleurotic pathway in S. coelicolor during growth on …
-
Evaluation of an End-to-End Radiotherapy Treatment Planning Pipeline for Prostate Cancer
… radiation.</p> <p>Deep learning segmentation models were developed from retrospective CT simulation imaging data and clinical contours to delineate intact, postoperative, and nodal treatment structures for prostate cancer to accomplish this objective. Quality contours were extracted per …
-
Component-wise Z-residual Diagnosis for Bayesian Hurdle Models
… if not properly accounted for. Traditional models assume specific data-generating mechanisms and often perform poorly when zero counts dominate. Hurdle models provide a flexible solution by separating the modeling process into two parts: (1) a binary model that predicts whether the count is …
-
Dynamic Spatial Forecasting of Sea Lice Abundances
… of salmonids. This thesis explores the current modelling approaches to the planktonic and attached stages of L. salmonis and explores a method of combining these modelling approaches. A combined modelling approach will increase understanding of the dynamics of sea lice populations on farms, …
-
Structural Basis for the Molecular Recognition of Androgen Receptor Ligands: Insights Guiding the Design and Synthesis of Novel Nonsteroidal Ligands
… AR ligands.</p> <p>We developed homology models of the human AR ligand-binding domain (LBD) in the agonist- and antagonist-bound forms. These models of the AR were based on the crystal structure of the human progesterone receptor LBD bound to progesterone, or the estrogen receptor LBD …
-
Uncertainty-aware learning from sparse, unlabelled, and out-of-distribution time series
… Despite the potential that machine learning models offer for healthcare time series, they still face notable challenges. Sensor-based datasets are frequently sparse (with missing values) if acquired outside controlled environments, while a substantial proportion remain unlabelled or only …
-
InSAR time series analysis and machine learning for ground subsidence monitoring and susceptibility mapping in Midvaal, South Africa
… examining the impact of Digital Elevation Model (DEM) vertical accuracy on ground subsidence monitoring accuracy, identifying the spatial and temporal (spatio-temporal) patterns of ground subsidence, and employing machine learning to create predictive models for ground subsidence …
Page 1 of 2