Sökning: "POST CLASSIFICATION COMPARISON"

Visar resultat 1 - 5 av 17 uppsatser innehållade orden POST CLASSIFICATION COMPARISON.

  1. 1. Uncertainty Quantification in Deep Learning for Breast Cancer Classification in Point-of-Care Ultrasound Imaging

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Marisa Wodrich; [2024]
    Nyckelord :Uncertainty quantification; Deep learning; Breast cancer classification; Trustworthy AI; Point-of-care ultrasound; Mathematics and Statistics;

    Sammanfattning : Breast cancer is the most common type of cancer worldwide with an estimate of 2.3 million new cases in 2020, and the number one cause of cancer-related deaths in women. LÄS MER

  3. 2. Deep Learning for Building Damage Assessment of the 2023 Turkey Earthquakes : A comparison of two remote sensing methods

    Kandidat-uppsats, KTH/Geoinformatik

    Författare :Tobias Karlbrg; Jennifer Malmgren; [2023]
    Nyckelord :Deep learning; U-Net; Earthquake-induced building damage; VHR satellite imagery; Djup maskininlärning; U-Net; Byggnadsskador; Jordbävning; Satellitbilder;

    Sammanfattning : Current disaster response strategies are based on damage assessments carried out on the ground, which can be dangerous following a ä destructive event. Damage assessments can also be performed remotely using satellite imagery, but are usually carried out through visual interpretation, which can take a lot of time. LÄS MER

  4. 3. A Comparison of Statistical Methods to Generate Short-Term Probabilistic Forecasts for Wind Power Production Purposes in Iceland

    Master-uppsats, Uppsala universitet/Luft-, vatten- och landskapslära

    Författare :Arnór Tumi Jóhannsson; [2022]
    Nyckelord :Wind power; Iceland; Atmospheric Boundary Layer; atmospheric stability; probabilistic forecasting; Machine Learning; Quantile Regression Forest; Vindkraft; Island; gränsskikt; atmosfärisk stabilitet; probabilistisk prognos; Machine Learning; Quantile Regression Forest;

    Sammanfattning : Accurate forecasts of wind speed and power production are of great value for wind power producers. In Southwest Iceland, wind power installations are being planned by various entities. LÄS MER

  5. 4. Using NDVI Time-Series to Examine Post-fire Vegetation Recovery in California

    Master-uppsats, Uppsala universitet/Institutionen för geovetenskaper

    Författare :Viktor Wu; [2022]
    Nyckelord :fire; California; NDVI; land cover; vegetation; post-fire recovery;

    Sammanfattning : Over the past couple of decades, fires have experienced changes on a global scale. These changing fire regimes point to an alarming direction where fire-dependent ecosystems are experiencing a decline in burned area, while fire-independent ecosystems are experiencing an increase. LÄS MER

  7. 5. Approximating the element matrices in an unfitted finite element method using neural networks

    Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för fysik

    Författare :Amanda Bertgren; [2022]
    Nyckelord :Finite element method; CutFEM; neural networks; machine learning;

    Sammanfattning : This study investigates the possibility of combining an unfitted finite element method, CutFEM, with neural networks, in an attempt to reduce the computational time on evolving domains. Finite element methods are used to solve partial differential equations by fitting a spatial and temporal discretisation to the momentous domain. LÄS MER