Sökning: "U-Net"

Visar resultat 1 - 5 av 11 avhandlingar innehållade ordet U-Net.

1. 1. Earth Observation based Monitoring of Urbanizationand Environmental Impact in Kigali, Rwanda

   Författare :Theodomir Mugiraneza; Yifang Ban; Jan Haas; Emmanuel Twarabamenye; Constantinos Cartalis; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Earth observation; Landsat; Sentinel-2; WorldView-2; Urbanization; Land cover classification; Support vector machines; Random forest; U-Net; LandTrendr; Landscape metrics; Ecosystem services; Environmental impact analysis; Kigali; Rwanda; Jordobservation; Landsat; Sentinel-2 MSI; WorldView-2; Urbanisering; Klassificering av marktäcke; Stödvektormaskiner; Slumpmässig skog; U-Net; LandTrendr; Landskapsmetriker; Ekosystemtjänster; Miljökon- sekvensanalys; Kigali; Rwanda.; Geoinformatics; Geoinformatik;

   Sammanfattning : Urbanization is one of the great challenges in the 21st century. Despite being an engine for the global economy, urban areas consume 78% of World's energy and emit more than 60% of greenhouse gas emission. Sub-SaharanAfrican cities, e.g. LÄS MER

3. 2. Deep Learning Methods for Classification of Gliomas and Their Molecular Subtypes, From Central Learning to Federated Learning

   Författare :Muhaddisa Barat Ali; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; glioma subtype classification; convolutional autoencoder; convolutional NN; multi-stream U-Net.; CycleGAN; 1p 19q codeletion; federated learning; IDH mutation; generative adversarial network; Deep learning;

   Sammanfattning : The most common type of brain cancer in adults are gliomas. Under the updated 2016 World Health Organization (WHO) tumor classification in central nervous system (CNS), identification of molecular subtypes of gliomas is important. LÄS MER

4. 3. Deep Learning for Wildfire Progression Monitoring Using SAR and Optical Satellite Image Time Series

   Författare :Puzhao Zhang; Yifang Ban; Lorenzo Burzzone; KTH; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Remote Sensing; Deep Learning; Wildfire; Burned Area Mapping; Synthetic Aperture Radar; Change Detection; Segmentation; Optical and Radar Image Analysis; Sentinel-1; Sentinel-2; fjärranalys; djup inlärning; skogsbrand; kartläggning av brända områden; Synthetic Aperture Radar; upptäckt av förändringar; segmentering; analys av optiska och radarbilder; Sentinel-1; Sentinel-2; Geoinformatik; Geoinformatics;

   Sammanfattning : Wildfires have coexisted with human societies for more than 350 million years, always playing an important role in affecting the Earth's surface and climate. Across the globe, wildfires are becoming larger, more frequent, and longer-duration, and tend to be more destructive both in lives lost and economic costs, because of climate change and human activities. LÄS MER

5. 4. Methods for the analysis and characterization of brain morphology from MRI images

   Författare :Irene Brusini; Chunliang Wang; Örjan Smedby; Eric Westman; Lars-Olof Wahlund; Jorge Cardoso; KTH; Karolinska Institutet; Karolinska Institutet; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; MEDICIN OCH HÄLSOVETENSKAP; MEDICAL AND HEALTH SCIENCES; Brain MRI; Image Segmentation; Machine Learning; Deep Learning; Shape Analysis; Aging; Neurodegeneration; MRT av hjärnan; Bildsegmentering; Maskininlärning; Djupinlärning; Formanalys; Åldrande; Neurodegeneration; Medical Technology; Medicinsk teknologi;

   Sammanfattning : Brain magnetic resonance imaging (MRI) is an imaging modality that produces detailed images of the brain without using any ionizing radiation. From a structural MRI scan, it is possible to extract morphological properties of different brain regions, such as their volume and shape. LÄS MER

7. 5. Supervised and Unsupervised Deep Learning Models for Flood Detection

   Författare :Ritu Yadav; Yifang Ban; Andrea Nascetti; Nicolas Audebert; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; Floods; Remote Sensing; Sentinel-1 SAR; Segmentation; Change Detection; DEM; Data Fusion; Time Series; Deep Learning; Unsupervised Learning; Contrastive Learning; Self-Attention; Convolutional LSTM; Variational AutoEncoder VAE ; Geoinformatik; Geoinformatics;

   Sammanfattning : Human civilization has an increasingly powerful influence on the earthsystem. Affected by climate change and land-use change, floods are occurringacross the globe and are expected to increase in the coming years. Currentsituations urge more focus on efficient monitoring of floods and detecting impactedareas. LÄS MER