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 30 for “"under-sampling"”.
-
Sequential anomaly detection under sampling constraints
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2025-05-01
-
Four-Dimensional Imaging of Respiratory Motion in the Radiotherapy Treatment Room Using a Gantry Mounted Flat Panel Imaging Device
… by high doses, long scan times and severe under-sampling artifacts. The focus of the work completed in this thesis was to find ways to improve 4D imaging using a gantry mounted 2D kV imaging system. Specifically, the goals were to investigate methods for minimizing imaging dose and scan …
-
Assessing the benefits of DCT compressive sensing for computational electromagnetics
… as sparseness. It has been proven that through under sampling, computation runtimes can be substantially decreased while maintaining sufficient accuracy. Lawrence Carin and his team of researchers at Duke University developed an in situ compressive sensing algorithm specifically tailored for …
-
Optimising credit card fraud detection through machine learning and deep learning with spatial-temporal imbalance handling
… data balancing techniques, including random over sampling (ROS), synthetic minority over-sampling technique (SMOTE), adaptive synthetic sampling (ADASYN), and random under sampling. We assessed eight machine learning algorithms—Bagging Classifier, Random Forest, CatBoost, Logistic Regression (LR), …
-
Deep learning-based medical image reconstruction for multi-contrast magnetic resonance imaging
… aiming to accelerate MRI acquisition by under-sampling while preserving the quality of acquired images. First, we address the issue of effectively leveraging highly correlated information across contrasts in sequentially acquired multi-contrast MR scans. We design a framework to optimise …
-
On the role of correspondence noise in human visual motion perception. A systematic study on the role of correspondence noise affecting Dmax and Dmin, using random dot kinematograms: A psychophysical and modelling approach.
… in the light of correspondence noise and under-sampling. Based on the psychophysical experiments performed in the early parts of the dissertation, a model for correspondence noise based on the principle of receptive field scaling is developed for Dmax. Model simulations provide a good …
-
Scanning-free compressive reconstruction of object motion with sub-pixel accuracy
Sub-pixel movement detection is an under-sampling problem. The basic idea for successful detection is to spread out the information over a larger sampling region. Diffraction provides a natural way to spread out the information; however, conventional digital holographic methods are not effective …
-
The Search for a Cost Matrix to Solve Rare-Class Biological Problems
… other rare-class learning techniques like oversampling and under-sampling. Overall our method is a robust and effective solution to the rare-class problem.
-
Efficient modeling of sound source radiation in free-space and room environments
… equivalent source model is used, and the under-sampling errors from all regions will accumulate to affect the predictions in any particular region. However, if localized basis functions are used to represent the sound field, the under-sampling errors from different regions do not affect …
-
Selecting the best model for predicting a term deposit product take-up in banking
… confirms this finding. We, therefore, use three sampling techniques, namely, under-sampling, oversampling and Synthetic Minority Over-sampling Technique, to balance the data, this results in three additional datasets to use for modelling. We build the following predictive models: random forest, …
-
Supervised Classification of Imbalanced Bidding Fraud Data
… we assess and compare several advanced over-sampling (SMOTE), under-sampling (NearMiss and ClusterCentroid) and hybrid sampling (SMOTE-ENN and SMOTE-TomekLink) methods to solve the imbalanced learning problem. We utilize the Randomized Search Cross Validation to tune the hyper-parameters for …
-
Hyper and structural Markov laws for graphical models
… distribution for the odds-ratio is the same under both the prospective and retrospective likelihoods. These conditions can be used to derive a parametric family of prior laws that may be used for such an analysis. The second part focuses on the problem of inferring the structure of the …
-
Randomized sampling and multiplier-less filtering
… in two fundamental signal processing techniques: sampling and filtering. The first part develops randomized non-uniform sampling as a method to mitigate the effects of aliasing. Randomization of the sampling times is shown to convert aliasing error due to uniform under-sampling into uncorrelated …
-
Diffusion Tensor Imaging: Evaluation of Tractography Algorithm Performance Using Ground Truth Phantoms
… are a macroscopically sampled description of underlying microscopic structure, and are therefore of limited validity. The under-sampling of underlying white matter structure in DTI data gives rise to Intra-Voxel Orientational Heterogeneity (IVOH), a condition in which white matter structures …
-
The inefficiency of open-loop fMRI experiments
… network whose functional roles are not well understood. Until recently, event related fMRI experiments used to study the DMN could only be conducted in an open-loop format. The purpose of this study was to demonstrate the potential statistical advantages of real-time fMRI studies to conduct …
-
Toward explainable machine learning methods for stroke patient outcomes in Tennessee
… of data modification, especially with under-sampling methods, and suitable ML algorithms can lead to high model performance, measured in terms of Recall and other metrics. Furthermore, based on the features of the data available in our work, using SHAP explainable ML method, the …
-
Toward Improved Classification of Imbalanced Data
… of learning algorithms in the presence of underrepresented data and severely skewed class distributions. Models trained on imbalanced datasets strongly favor the majority class and largely ignore the minority class. Several approaches introduced to date present both data-based and …
-
Compressive super-localization
… the influence on localization accuracy of finite sampling rate, number of samples, and noise in the data acquisition process. Two classes of super-localization problems will be investigated. The first class of problem aims to improve the accuracy in localizing and tracking the physical position of …
-
Improvements In Four-Dimensional and Dual Energy Computed to mography
… prior to radiation treatment, but suffers from under sampling artifacts. An iterative volume of interest based reconstruction (I4D VOI) that aims to reduce artifacts without increases in computation time was compared to several other reconstruction techniques using a long scan patient data set. …
-
LINKING ALLOMETRIC SCALING THEORY WITH LIDAR REMOTE SENSING FOR IMPROVED BIOMASS ESTIMATION AND ECOSYSTEM CHARACTERIZATION
… that small samples sizes tend to result in an under sampling of large stems, which yields a more linear fit than the true allometry. An assessment of the potential carbon implications of this problem yielded site-level biomass predictions with biases of 10-178%. We suggest that empirical …
Page 1 of 2