Recent additions

  • Segmentation and Unsupervised Adversarial Domain Adaptation Between Medical Imaging Modalities 

    Strauman, Andreas Storvik (Master thesis; Mastergradsoppgave, 2019-07-13)
    Segmenting and labelling tumors in multimodal medical imaging are often vital parts of diagnostics and can in many cases be very labor intensive for clinicians. The effort in advancing time-saving methods in the medical health sector might be of great help for busy clinicians and can maybe even save lives. Furthermore, creating methods that generically, accurately and successfully process unlabelled ...
  • An investigation of the robustness of distance measure-based supervised labelling of segmented remote sensing images 

    Kiærbech, Åshild (Master thesis; Mastergradsoppgave, 2019-06-03)
    Unsupervised clustering methods on remote sensing images have shown good results. However, this type of machine learning needs additional labelling to be an end-to-end classification in the same manner as traditional supervised classification. The automation of the labelling needs further exploration. We want to investigate the robustness of a supervised automatic labelling scheme by comparing a ...
  • Correction Strategies for Breathing Induced Motion in PET Images 

    Bakkevoll, Stian (Master thesis; Mastergradsoppgave, 2019-06-03)
    Breathing induced motion highly impacts the quality of PET images. Motion blur impacts important parameters such as standardised uptake value (SUV) and lesion volume. To be able to stage lung cancer correctly, and provide correct treatment, the impact of motion needs to be reduced. There exists techniques to combat the breathing motion, such as elastic motion correction and gating strategies. ...
  • Deep Image Clustering with Tensor Kernels and Unsupervised Companion Objectives 

    Trosten, Daniel Johansen (Master thesis; Mastergradsoppgave, 2019-05-31)
    Deep image clustering is a rapidly growing branch of machine learning and computer vision, in which deep neural networks are trained to discover groups within a set of images, in an unsupervised manner. Deep neural networks have proven to be immensely successful in several machine learning tasks, but the majority of these advances have been in supervised settings. The process of labeling data for ...
  • Estimering av egenskaper til naturlige klasser i radarbilder med en blandingsmodell 

    Moe, Åse Mari (Master thesis; Mastergradsoppgave, 2018-05-31)
    I løpet av de siste årene har isdekket i polhavet gått fra å være flerårsis til å bli en sesongbasert istype. Hvordan isen utvikler seg på sommeren vil avhenge av smeltevannandelen, blant annet på grunn av at smeltevannet har mindre albedo enn isen. For å estimere andelen smeltevann er det i denne oppgaven utviklet flere metoder som kan brukes på satellittbilder. Disse metodene bruker en statistisk ...
  • Analyzing Behavioral Biometrics of Handwriting Using Myo Gesture Control Armband 

    Tveit, Brynjulv (Master thesis; Mastergradsoppgave, 2018-06-05)
    Through the last few decades, computer technology has gradually merged into our everyday lives. Computers and sensors are embedded in an increasing amount of household items, enabling us to monitor and remotely control our connected devices from apps on our smartphones. The technology interfaces are also evolving along with new technologies. Among the up and coming digital interfaces are wearable ...
  • A compact portable resonance probe system for in situ measurements of snow conditions 

    Reistad, Jakop (Master thesis; Mastergradsoppgave, 2018-01-31)
    A resonance probe for measuring the dielectric properties of snow in terms of the resonance frequency is described and tested. The dielectric properties of snow are closely related to the density and the water content in snow. Having a probe capable of measuring the dielectric properties is therefore a useful tool for anyone working with quantitative descriptions of snow properties. In situ measurements ...
  • Reconstruction of the full-polarimetric covariance matrix from compact-polarimetric synthetic aperture radar data with convolutional neural networks 

    Bollo Del Rio, Umberto (Master thesis; Mastergradsoppgave, 2017-09-05)
    The focus of this thesis is to find an alternative way to reconstruct a pseudo quadrature polarimetric (quad-pol) covariance matrix from compact polarimetric (compact-pol) data. In the latest years, the compact polarimetry SAR mode was developed and used more and more widely. It provides a good compromise between area covered and information content per pixel [13]. The literature has focused ...
  • A Classification Strategy for Multi-Sensor Remote Sensing Data. An analysis and implementation of Meta-Gaussian classification schemes 

    Kvamme, Arja Beate (Master thesis; Mastergradsoppgave, 2017-08-18)
    In integrated remote sensing, one of the objectives is to create reliable services by combining information from various data sources. The combination of multiple data sources is often denoted "data fusion", and is a topic that has high interest in remote sensing applications. In this thesis, we devise a classification strategy for multi-sensor remote sensing data, based on the strategy presented ...
  • Speckle filtering of Polarimetric SAR data 

    Anzilotti, Stefano (Master thesis; Mastergradsoppgave, 2017-06-17)
    In the field of Remote Sensing the main device, used to obtain the surface images, are the so-called Synthetic Aperture Radar. This systems are devices able to catch high-resolution images, which keep peculiar informations about the observed surface. Through the use of a Radar, mounted on board of a spaceborne or airborne vehicle, large overflow areas are electromagnetically radiating. The ...
  • Laser Based Altimetry for Unmanned Aerial Vehicle Hovering Over a Snow Surface 

    Haugen, Hallvard (Master thesis; Mastergradsoppgave, 2017-06-02)
    A microwave radar for non-invasive snow stratigraphy measurements has been developed. Results were promising, but it failed to detect light powder snow in the air-snowpack interface. The aim of this thesis is to find and verify a system for estimating altitude on centimeter scale over a snow surface, independent of snow conditions. Also, relative pitch and roll angle estimation between the UAV and ...
  • An initial assessment of the possibilities of fish catch prediction using Gaussian processes 

    Björk, Sara Maria (Master thesis; Mastergradsoppgave, 2016-12-15)
    The fishing and aquaculture industry is one of the largest industries of Norway. Enhanced knowledge of the distribution of fish in the ocean is important for an economical and sustainable fishing industry. This study investigates the possibilities of using Gaussian processes for regression within fish catch prediction. A dataset that combines catch reports from the Norwegian shipping company Havfisk ...
  • Modeling probability density functions of non-negative random variables using novel series expansions based on mellin kind statistics 

    Brenn, Torgeir (Master thesis; Mastergradsoppgave, 2017-05-31)
    Mellin kind (MK) statistics is the framework which arises if the Fourier transform is replaced with the Mellin transform when computing the characteristic function from the probability density function. We may then proceed to retrieve logarithmic moments and cumulants, which have important applications in the analysis of heavy-tailed distribution models for non-negative random variables. In this ...
  • Snow Stratigraphy Measurements With UWB Radar 

    Jenssen, Rolf-Ole Rydeng (Master thesis; Mastergradsoppgave, 2016-12-14)
    The focus of this thesis is to find and verify a non-invasive method to determine the layer distribution (stratigraphy) in snowpacks, which might aid avalanche risk assessment. Slab avalanches release due to failure and collapse in a weak snow layer. Determining the spatial distribution and depth of weak layers in avalanche starting zones is a high-risk task. Moreover, by manually digging snow ...
  • Numerisk modellering av absorberende randbetingelser for ultralydbølger i væsker og elastiske materialer 

    Grønmo, Tor Arne (Master thesis; Mastergradsoppgave, 2015-06-01)
    Simuleringer av utbredelse av ultralydbølger i elastiske polymerer og i væsker ble utført med et kommersielt simuleringsverktøy, COMSOL Multiphysics, basert på endelig element metode. Simuleringer ble utført i en- og to-dimensjoner. Undersøkelser ble utført for å finne ut ved hvilke oppløsninger av tid og rom ga stabile simuleringer. For en to-dimensjonal modell basert på en elastisk ...
  • Physical and statistical based decomposition of Polarimetric Synthetic Aperture Radar images of Arctic Sea ice 

    Arienzo, Alberto (Master thesis; Mastergradsoppgave, 2015-06-01)
    The studies about the climatic changes have always more underlined the importance of the climatic balance of the Arctic regions. For this reason the need of monitoring the Arctic becomes always more urgent. To measure the sea ice thickness, the sea ice cover, the motion of the glaciers and to discriminate the various kind of ice are only several of the challenges about the Arctic monitoring. But the ...
  • Joint ranking and clustering based on Markov Chain transition probabilities learned from data 

    Løkse, Sigurd (Master thesis; Mastergradsoppgave, 2014-12-15)
    The focus of this thesis is to develop a Markov Chain based framework for joint ranking and clustering of a dataset without the need for critical user-defined hyper-parameters. Joint ranking and clustering may be useful in several respects, and may give additional insight for the data analyst, as opposed to the traditional separate ranking and clustering procedures. By coupling Markov ...
  • Oil Spill Analysis Using Hybrid-Polarization Synthetic Aperture Radar 

    Høifødt, Audun Leonard (Master thesis; Mastergradsoppgave, 2016-06-01)
    The goal for this thesis is to test various Hybrid-Polarization (HP) Synthetic Aperture Radar (SAR) parameters using actual HP data, and to evaluate the validity of these parameters with respect to oil slick detection. As part of the evaluation, the impact of the system noise and incidence angle on the SAR images is discussed. It is shown that the Signal-to-Noise Ratio (SNR) of the sensor has a ...
  • On the improvement and acceleration of eigenvalue decomposition in spectral methods using GPUs 

    Johansen, Thomas A. Haugland (Master thesis; Mastergradsoppgave, 2016-12-08)
    The key objectives in this thesis are; the study of GPU-accelerated eigenvalue decomposition in an effort to uncover both benefits and pitfalls, and then to investigate and facilitate a future GPU implementation of the symmetric QR algorithm with permutations. With the current trend of having ever larger datasets both in terms of features and observations, we propose that GPU computation can help ...
  • Wind resource assessment using mesoscale modelling. A case study at the potential wind farm site Rieppi 

    Blæsterdalen, Torgeir (Master thesis; Mastergradsoppgave, 2016-06-01)
    The growing wind power industry, increased occurrence of extreme weather, and the need for becoming independent of fossil fuels motivate the research on accurate simulation of near-surface wind. The aim of this study is wind resource assessment at the potential wind park site Rieppi, using two on-site measurement masts, simulations from the Weather Research and Forecasting (WRF) model, and ERA-Interim ...

View more