Sökning: "neural networks"

Visar resultat 1 - 5 av 1488 uppsatser innehållade orden neural networks.

  1. 1. Establishment of a deep learning algorithm for dosimetry of radiopharmaceuticals

    Master-uppsats,

    Författare :Dennis Lipnicevic; [2022-01-13]
    Nyckelord :Medical physics; automated segmentation; dosimetry; kidney; nuclear medicine dosimetry; deep learning; convolutional neural network;

    Sammanfattning : Purpose: The aim of this study was to introduce a volumetric convolutional neural network for segmentation of the kidneys in SPECT images and to apply it in the dosimetry of radiopharmaceuticals of this organ, in order to decrease segmentation time and to standardize the segmentation of the kidneys. Method: Three networks were trained using two network architectures and a total of 216 retrospectively collected images from patients that underwent imaging procedures at Sahlgrenska University Hospital between 2009 and 2018. LÄS MER

  2. 2. Convolutions on graphs for learning vehicle crash behaviour

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Daniel Adin; [2021-11-09]
    Nyckelord :Computer; science; computer science; engineering; graph; convolutions; inite element method; project; thesis;

    Sammanfattning : Convolutional Neural Networks (CNN) have shown successful results in the recent years, especially within the area of image analysis. The idea of learning to predict the result of a crash simulation using machine learning rose from the analogy between images and Finite Element models (FE-models) used in crash simulations. LÄS MER

  3. 3. Driver Behavior Classification in Electric Vehicles

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :FEDERICA COMUNI; CHRISTOPHER MÉSZÁROS; [2021-07-06]
    Nyckelord :Aggressive driver behavior; Driver behavior classification; Self-attention; Recurrence plots; active learning; Active deep dropout; Gradual pseudo labeling;

    Sammanfattning : Studies have shown that driving style affects the energy consumption of electric vehicles, with aggressive driving consuming up to 30% more energy than moderate driving. Therefore, modeling of aggressive driving can provide a more precise estimation of the energy consumption and the remaining range of a vehicle. LÄS MER

  4. 4. Funktionell PCA mot Artificiella Neuronnät

    Kandidat-uppsats, Göteborgs universitet/Institutionen för matematiska vetenskaper

    Författare :Freja Nordh; Mattis Hallberg; Shayan Mollahosseini; Jack Sandberg; Erik Jansson; Philip Gard; [2021-07-01]
    Nyckelord :;

    Sammanfattning : Denna rapport fokuserar på jämförelsen av några olika klassificeringsmetoder appliceradepå bilddatan Fashion-MNIST. De olika metoderna är artificiella neurala nätverk och funktionellprincipalkomponentanalys och principalkomponentanalys. För de neurala nätverken har vi tvåtyper: CNN och FNN. LÄS MER

  5. 5. Quantum Error Correction Using Graph Neural Networks

    Master-uppsats, Göteborgs universitet / Institutionen för fysik

    Författare :Valdemar Bergentall; [2021-06-17]
    Nyckelord :Quantum error correction; surface code; graph neural networks;

    Sammanfattning : A graph neural network (GNN) is constructed and trained with a purpose of usingit as a quantum error correction decoder for depolarized noise on the surface code.Since associating syndromes on the surface code with graphs instead of grid-likedata seemed promising, a previous decoder based on the Markov Chain Monte Carlomethod was used to generate data to create graphs. LÄS MER