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 13 of 13 for “"Machine Learning visualization"”.

  1. Improving Seafood Production Through Data Science Methods

    … encapsulates data processing, statistical, machine learning, visualization and optimization capabilities. The research employs unique real-world data collected in a seafood production facility over a 2-year period. The study will contribute to the economic well-being of the individual …

    york Repository record for Improving Seafood Production Through Data Science Methods (opens in a new tab)

  2. Towards Data-Driven Large Scale Scientific Visualization and Exploration

    … This dissertation builds upon recent advances in machine learning, visualization, and user interactions to facilitate exploration of large-scale scientific datasets. First, we use data-driven approaches to computationally identify regions of interest in the datasets. Second, we use visual …

    maryland Repository record for Towards Data-Driven Large Scale Scientific Visualization and Exploration (opens in a new tab)

  3. A Multidisciplinary Design and Evaluation Framework for Explainable AI Systems

    … are sought in different disciplines such as machine learning, human-computer interactions (HCI), and visual analytics. The mismatch in objectives for the scholars to define, design, and evaluate the concept of XAI may slow down the overall advances of end-to-end XAI systems. My research aims …

    tamu Repository record for A Multidisciplinary Design and Evaluation Framework for Explainable AI Systems (opens in a new tab)

  4. Visualization for Solving Non-image Problems and Saliency Mapping

    … discovery and data science. Integration of visualization, visual analytics, machine learning (ML), and data mining (DM) are the key aspects of data science research for high-dimensional data. This thesis is to explore the efficiency of a new algorithm to convert non-images data into raster …

    central-wash Repository record for Visualization for Solving Non-image Problems and Saliency Mapping (opens in a new tab)

  5. Understanding The Effects of Incorporating Scientific Knowledge on Neural Network Outputs and Loss Landscapes

    While machine learning (ML) methods have achieved considerable success on several mainstream problems in vision and language modeling, they are still challenged by their lack of interpretable decision-making that is consistent with scientific knowledge, limiting their applicability for scientific …

    vt Repository record for Understanding The Effects of Incorporating Scientific Knowledge on Neural Network Outputs and Loss Landscapes (opens in a new tab)

  6. Malware Image Classification using Machine Learning with Local Binary Pattern

    … Finally, Tensorflow, a library for machine learning, is applied to classify malware images with the LBP feature. Performance comparison results among different classifiers with different image descriptors such as GIST, a spatial envelope, and the LBP demonstrate that our proposed …

    kennesaw Repository record for Malware Image Classification using Machine Learning with Local Binary Pattern (opens in a new tab)

  7. Characterizing midair handwriting in virtual reality

    Midair handwriting poses challenges due to the lack of a physical plane to press against while writing, making it difficult to determine when ink should be placed. In this thesis, we gathered midair handwriting data from 24 participants in an environment that allowed them to write freely. We …

    uoit Repository record for Characterizing midair handwriting in virtual reality (opens in a new tab)

  8. The Effects of Mixed-Initiative Visualization Systems on Exploratory Data Analysis

    The main purpose of information visualization is to act as a window between a user and data. Historically, this has been accomplished via a single-agent framework: the only decisionmaker in the relationship between visualization system and analyst is the analyst herself. Yet this framework arose …

    wustl Repository record for The Effects of Mixed-Initiative Visualization Systems on Exploratory Data Analysis (opens in a new tab)

  9. Visualization of Deep Convolutional Neural Networks

    Deep learning has achieved great accuracy in large scale image classification and scene recognition tasks, especially after the Convolutional Neural Network (CNN) model was introduced. Although a CNN often demonstrates very good classification results, it is usually unclear how or why a …

    wustl Repository record for Visualization of Deep Convolutional Neural Networks (opens in a new tab)

  10. Predikce a vizualizace zpoždění veřejné dopravy

    Veřejná doprava je nepostradatelnou součástí každého moderního města. S rostoucí populací v uspěchané době se zvyšují nároky nejen na dostupnost, bezpečnost, ale také na dochvilnost vozů. I přes to, že ne všechny typy zpoždění se dají predikovat, jsou tu také faktory, které zpoždění ovlivňují a …

    brno-tech Repository record for Predikce a vizualizace zpoždění veřejné dopravy (opens in a new tab)

  11. Human-Centered Machine Learning with Interpretable Visual Knowledge Discovery

    This research advances interpretable machine learning (ML) by introducing hyperblocks (HBs) as a structured, rule-based approach for creating transparent and accurate models using meaningful numeric attributes directly interpretable to end users. Key techniques, including Parallel Hyperblock …

    central-wash Repository record for Human-Centered Machine Learning with Interpretable Visual Knowledge Discovery (opens in a new tab)

  12. Metabolomics Study of ARDS Diagnosis, Heterogeneity, and Mortality

    Background: Acute Respiratory Distress Syndrome (ARDS) represents 10.4% of all Intensive Care Unit (ICU) admissions with an overall mortality rate of 35.3%. Early diagnosis of ARDS is an important requirement for the timely institution of proper supportive care but it is hampered by the unreliable …

    calgary Repository record for Metabolomics Study of ARDS Diagnosis, Heterogeneity, and Mortality (opens in a new tab)

  13. A Unified Framework for Data-Driven Atomistic Modeling

    … DFT and FFs. We focus on building data-driven machine learning (ML) models in this work, because ML has been shown to be a promising alternative to analytical models. These new tools include a near-uniform sampling algorithm and software packages for training and understanding the models. Also, …

    gatech Repository record for A Unified Framework for Data-Driven Atomistic Modeling (opens in a new tab)