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 81 for “"Synthetic samples"”.

  1. Iron oxidation in (Mg,Fe)0: Calibration of the Flank method on synthetic samples and applications on natural inclusions from lower mantle diamonds

    … the “flank method” by electron microprobe using synthetic (Mg,Fe)O, and then apply the method to determine in situ Fe3+/Fetot in ferropericlase inclusions from lower mantle diamonds. Up to now a calibration of the flank method is available only for garnets. Initially, the flank method was …

    bayreuth Repository record for Iron oxidation in (Mg,Fe)0: Calibration of the Flank method on synthetic samples and applications on natural inclusions from lower mantle diamonds (opens in a new tab)

  2. COMPARISON OF NON-HEATING PALEOINTENSITY TECHNIQUES USING BASALTS FROM LEMPTÉGY VOLCANO, FRANCE AND SYNTHETIC MAGNETITE-BEARING SAMPLES

    … effectiveness and reliability using both natural samples from Lemptégy Volcano, France, and synthetic samples. Paleointensity was measured from the natural and synthetic samples using the Pseudo-Thellier, ARM, REM, REMc, REM’, and Preisach methods. For the natural samples, only the Pseudo-Thellier …

    mtu Repository record for COMPARISON OF NON-HEATING PALEOINTENSITY TECHNIQUES USING BASALTS FROM LEMPTÉGY VOLCANO, FRANCE AND SYNTHETIC MAGNETITE-BEARING SAMPLES (opens in a new tab)

  3. A SELECTIVE GAN-BASED DATA AUGMENTATION METHOD FOR MEDICAL IMAGE CLASSIFICATION

    … and triplet loss to control the quality of synthetic samples generated, and make the dataset more balanced by generating more synthetic samples for minority classes. The research evaluates the method on the HyperKvasir dataset. Eventually, we achieved better classification performance than …

    nus Repository record for A SELECTIVE GAN-BASED DATA AUGMENTATION METHOD FOR MEDICAL IMAGE CLASSIFICATION (opens in a new tab) Download file for A SELECTIVE GAN-BASED DATA AUGMENTATION METHOD FOR MEDICAL IMAGE CLASSIFICATION (opens in a new tab)

  4. Generating synthetic data by morphing transformation for handwritten numeral recognition (with v-SVM)

    … size is adding synthesized data. In this study, synthetic data generation using morphing transformation with convex evolution is investigated. This technique uses a pair of original samples as the source and the target, and generates the synthetic samples by evolving the source towards the …

    concordia Download PDF for Generating synthetic data by morphing transformation for handwritten numeral recognition (with v-SVM) (opens in a new tab)

  5. Trajectory modelling with limited speech data

    … is not sufficient to observe a large number of samples of each acoustic unit during training; it is necessary to observe sufficient samples appearing in similar contexts to those found in the test data. To obtain a better understanding of co-articulation effects, we analysed the behaviour of …

    nwu-za Repository record for Trajectory modelling with limited speech data (opens in a new tab)

  6. Insights into the Application of Deep Reinforcement Learning in Healthcare and Materials Science

    … policies and cause bias. Additionally, because synthetic samples are often used to improve the utility of incomplete datasets, we evaluate the impact of data completeness in both panel and longitudinal medical data on the ability of deep generative models to generate similar synthetic samples to …

    utk-theses Repository record for Insights into the Application of Deep Reinforcement Learning in Healthcare and Materials Science (opens in a new tab)

  7. How does cement influence the mechanical properties of sands and sandstones?

    … porosity distribution across deformation band samples from Utah, Hungary and Arran by comparing 2D slice to 3D sub-volume analysis methods.;Characterisation of cement in outcrops of sand(stone)s is complex due to variable mineralogy and multiple periods of cementation. The second half of this …

    strathclyde Repository record for How does cement influence the mechanical properties of sands and sandstones? (opens in a new tab)

  8. Generated Image Quality Assurance and Generative Adversarial Network Augmentation for Machine Learning

    … how Pix2Pix can generate realistic and varied synthetic samples to address the issue of underrepresented data in training sets are discussed. To further enhance the quality ofPix2Pix’s output the thesis presents a grid-based search strategy for efficient hyperparameter tuning of Pix2Pix, …

    plymouth Repository record for Generated Image Quality Assurance and Generative Adversarial Network Augmentation for Machine Learning (opens in a new tab)

  9. New developments for addressing class imbalance issue in classification tasks

    … learn from minority class instances. The Synthetic Minority Over-sampling Technique (SMOTE) is a well-established method to address this issue by generating synthetic samples for underrepresented classes. This Ph.D. thesis introduces several novel extensions to SMOTE, including Distance …

    manitoba Repository record for New developments for addressing class imbalance issue in classification tasks (opens in a new tab)

  10. Crystal chemistry of the jarosite group of minerals - solid solution and atomic structures

    … X-ray powder diffraction data. The synthesized samples have full iron occupancy, where in many previous studies there was significant vacancies in the B site. Well-defined trends can be seen in the unit cell parameters, bond lengths A – O and Fe - O across the solid-solution series in the …

    queens Repository record for Crystal chemistry of the jarosite group of minerals - solid solution and atomic structures (opens in a new tab)

  11. Vérification des structures proposées pour la ferrihydrite par diffraction des rayons X des nanoparticules

    … powder x-ray diffraction patterns recorded from synthetic samples of 2-lines and 6-lines ferrihydrite with the calculated ones (Debye sum) from the proposed structures. The comparisons show that all structure propositions are incorrect. Although, three of the six propositions suggest jointly that …

    ottawa-retro Repository record for Vérification des structures proposées pour la ferrihydrite par diffraction des rayons X des nanoparticules (opens in a new tab)

  12. Rbm-od: a restricted Boltzmann machine framework for outlier detection

    … complex data patterns. By generating synthetic samples from trained RBMs and comparing them to input data, the approach enables unsupervised detection of unusual or unexpected instances. This gener ative perspective distinguishes RBM-OD from traditional methods and provides a flexible …

    lethbridge Repository record for Rbm-od: a restricted Boltzmann machine framework for outlier detection (opens in a new tab)

  13. Spiking Neural Network Framework for Brain Computer Interfaces

    … cause further rejection of these recorded samples. To overcome this, a few studies have developed generative models based on deep neural network (DNN) to create artificial EEG samples, but these models still require a huge number of samples which is counter-intuitive. Therefore, in this …

    uts Repository record for Spiking Neural Network Framework for Brain Computer Interfaces (opens in a new tab)

  14. A Detailed Analysis of the Multi-Class Classification Problem in Network Intrusion Detection using Resampling Techniques

    … using CGAN in a dataset with extremely low samples in its minority classes based on our experimental results. Consequently, we also investigate the choice of minority class(es) to be oversampled in a dataset with low minority samples. Finally, the impact of the number of synthetic samples to …

    carleton Repository record for A Detailed Analysis of the Multi-Class Classification Problem in Network Intrusion Detection using Resampling Techniques (opens in a new tab)

  15. Quality-Based Face Recognition System

    … been found in many studies that the quality of samples significantly affects the performance of a biometric system. This thesis focuses on designing a unified framework which can adaptively compensate for different quality degradations of the facial images. The proposed quality estimation model …

    calgary Repository record for Quality-Based Face Recognition System (opens in a new tab)

  16. Identification of sustainable Adsorbents for Mercury Removal from gold mining Tailings

    … Hg(II), demonstrating promising results in both synthetic samples and real wastewater from mining processing plants in Zaruma (Virgen de las Nieves and Hermanos Granda). The findings highlight the potential of these biomaterials for environmental remediation applications, offering a viable, …

    sevilla Repository record for Identification of sustainable Adsorbents for Mercury Removal from gold mining Tailings (opens in a new tab)

  17. A Broadband Laboratory Study of the Seismic Properties of Cracked and Fluid-saturated Synthetic Glass Materials

    … measurements were performed on a suite of synthetic media made either by sintering soda-lime-silica glass beads or from glass rods of similar composition with artificially controlled microstructures involving both equant pores and cracks. The goal was an improved understanding of the origin …

    anu Repository record for A Broadband Laboratory Study of the Seismic Properties of Cracked and Fluid-saturated Synthetic Glass Materials (opens in a new tab)

  18. Conditioning Hierarchical Diffusion Transformers on RF Circuit Parameters

    … RF-Diffusion, for generating high-quality synthetic data conditioned on circuit-specific parameters. Using mathematical models of circuit properties, a dataset of synthetic examples was created to test the architecture’s ability to learn and implement these parameters. The metrics of Error …

    wustl Repository record for Conditioning Hierarchical Diffusion Transformers on RF Circuit Parameters (opens in a new tab)

  19. ToolRAG: A Novel Approach to the Detection of Code Vulnerabilities Through Large Language Models

    … seeks to use gpt-4o-mini to evaluate both synthetic and real-world code samples containing common vulnerabilities. The framework was tasked with identifying the vulnerability status of a code sample, and to indicate a confidence level in its response. When evaluated against both vulnerable …

    tamu Repository record for ToolRAG: A Novel Approach to the Detection of Code Vulnerabilities Through Large Language Models (opens in a new tab)

Page 1 of 5