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 96 for “"Paired data"”.
-
Recent Developments in Statistical Methods of Partially Paired Data
Paired data are ubiquitous in practice, such as in pre-post treatment studies, or in genomic experiments to find differentially expressed genes between two conditions. However, missing values often occur in practice. The incompleteness can be from either one arm or both arms, yielding "partially …
-
Synthetic FDG-PET Generation from Computed Tomography Using Paired-Data and Rectified Flow Synthesis
… settings and for producing labelled training data where paired FDG-PET is scarce. A 2.5D rectified flow model was trained on paired data from the AutoPET FDG-PET-CT-Lesions cohort. At a standardized uptake value (SUV) clip of 40 it reconstructs body-region anatomy with a mean absolute error of …
-
Evaluating Robustness of Methods for Comparing Two Means Using Paired Data With Few Incomplete Pairs
Practitioners often resort to the paired t test to test equality of two means when data is complete. When small amounts of data are missing, is this method still as robust? Are there alternative methods which can perform the job better on the missing data? In this thesis, we measured the robustness …
-
In-Context Retrieval for Molecules and Chemical Synthesis Pathways
… --including patents, publications, and web-scale data -- contain vast quantities of contextually relevant but incompletely paired samples that are discarded under standard training paradigms. In this work, we demonstrate that hard negative mining can be leveraged to construct pseudo-positive …
-
Incorporating domain knowledge into medical image synthesis and analysis for accessible medical imaging
… image synthesis and prediction under limited paired data and constrained imaging resources. The first part of the thesis focuses on robust analysis under degraded inputs and constrained supervision. A similarity-weighted self-ensembling framework is developed for low-quality few-shot stroke …
-
Semi-supervised cycle-consistency training for end-to-end ASR using unpaired speech
… speech recognition (ASR) models using unpaired speech. In general, large amounts of paired data (speech and text) are needed to train an end-to-end automatic speech recognition system. To alleviate the problem of limited paired data, the idea of cycle-consistency losses has been proposed …
-
Assessment of bivariate normality
… used to assess the bivariate normality of paired data, two of which are also used to assess the multivariate normality. Nevertheless, none of the methods is very efficient or conclusive in their assessment of bivariate normality. In this thesis we are proposing a new method to test …
-
Statistical Models to Test Measurement Invariance with Paired and Partially Nested Data: A Monte Carlo Study
… are used rather scores from children themselves. Data from parent ratings or from parents and teachers are often nested such as students are within teachers and a child is within their parents. This popular nested feature of data in educational, social and behavioral sciences makes measurement …
-
Modeling the Progression of Discrete Paired Longitudinal Data.
… derive a methodology for which to model discrete paired longitudinal data. Through the use of transition matrices and maximum likelihood estimation techniques by means of software, we develop a way to model the progression of such data. We provide an example by applying this method to the …
-
Unsupervised deep learning for removing structured noise in microscopy and flow cytometry
… utilising the information contained in training data, but this is also one of their greatest limitations. To reliably remove all forms of noise, existing deep learning-based denoisers require paired training data, typically consisting of noisy observations and corresponding clean signals. In the …
-
UNSUPERVISED DOMAIN ADAPTATION FOR SPEAKER VERIFICATION IN THE WILD
… gaining access to unlabeled target domain data, e.g., from open source online media, and labeled data from other domains is more feasible. This work focuses on making ASV systems robust to uncontrolled (‘wild’) conditions, with the help of some unlabeled data acquired from such conditions. …
-
Bayesian multi-view models for data-driven drug response analysis
… molecules. Moreover, with emerging drug-response data sets being profiled over several disease types and phenotypic details, it is pertinent to develop advanced computational methods that can be used to study multiple sets of data together. In this thesis, a novel multi-disciplinary challenge is …
-
Topics on Climate Model Output Analyses
Comparison of two different data samples, and of paired data samples, is a well known problem in Statistics. Specifically, there is a wide range of applications in the fields of climate study. In this thesis, we provide a brief review on the ensemble of climate models and the need of probabilistic …
-
Bagging Classification Trees for Longitudinal Data
Many studies handle binary longitudinal data by model-based classifiers, although their assumptions are often unsatisfied with real data. In contrast, tree-based classifiers are free of distributional assumptions, and several of these classifiers use bootstrap samples to construct multiple trees …
-
Effects of Eccentric Strengthening on Force Output of the Erector Spinae as Measured by Surface Electromyography (EMG)
… at the end of the study. Pretest and post-test data were compared using the Wilcoxon signed rank test for paired data (α = 0.05). There is insufficient evidence to conclude that a four week eccentric training protocol had an effect on the force output of the erector spinae as measured by surface …
-
Embedded CycleGAN for Shape-Agnostic Image-to-Image Translation
… for entertainment purposes and applications, data augmentation, semantic image segmentation, and more. Generative Adversarial Networks (GANs), and in particular Conditional GANs have recently shown incredible success in image-to-image translation and semantic manipulation. However, such …
-
DOCKING STUDIES OF CURCUMIN ANALOGS AGAINST METHIONINE AMINOPETIDASE 2 AND BIOLOGICAL EVALUATION OF LEAD MOLECULES IN COLON CELLS
… Western blot analysis. The Student’s t-test for paired data and Dunnett’s post hoc test with p<0.05 were performed using the program IBM SPSS Statistics 26. One hundred thirty compounds were docked against MetAP2 enzyme, out of these the top 10 compounds that showed good results for their …
-
SIMPLIFYING 3D LEARNING: INTEGRATING PRIOR KNOWLEDGE AND DECOMPOSING COMPLEXITY
… challenges in 3D learning and modeling—data scarcity, ineffective prior integration, and computational complexity—through two complementary principles: strategic integration of domain-specific priors and systematic decomposition of complex problems into tractable components. Four key …
-
Commitment, Forgiveness, and Relationship Self-Regulation: An Actor-Partner Interdependence Model
… their partner's use of RSR behaviors. Using paired data from 679 cohabiting and married couples who took the RELATE questionnaire, we found that males' and females' self-reports of commitment and forgiveness were both positively associated with higher perceptions of partner RSR. Likewise, we …
-
SUSTAINING GRIT AND RESILIENCE AT THE UNITED STATES NAVAL ACADEMY
… Academy (USNA) midshipmen, providing empirical data for the institution’s "leadership laboratory" narrative. Analyzing matched paired data from the Class of 2027 (Grit n = 210; Resilience n = 155) from freshman (T1) to junior (T2) year, the research uses paired t-tests and regressions to track …
Page 1 of 5