Now showing items 1-20 of 3075

    • De-identifying Swedish EHR text using public resources in the general domain 

      Chomutare, Taridzo; Yigzaw, Kassaye Yitbarek; Budrionis, Andrius; Makhlysheva, Alexandra; Godtliebsen, Fred; Dalianis, Hercules (Journal article; Tidsskriftartikkel; Peer reviewed, 2020)
      Sensitive data is normally required to develop rule-based or train machine learning-based models for de-identifying electronic health record (EHR) clinical notes; and this presents important problems for patient privacy. In this study, we add non-sensitive public datasets to EHR training data; (i) scientific medical text and (ii) Wikipedia word vectors. The data, all in Swedish, is used to train a ...
    • Particular: A Functional Approach to 3D Particle Simulation 

      Indreberg, Marius (Master thesis; Mastergradsoppgave, 2021-05-31)
      Simulating large bodies of entities in various environments is an old science that traces back decades in computer science. There are existing software frameworks with well built mathematical models for approximating various environments. These frameworks are however built on imperative programming fundamentals often following a object oriented paradigm. This thesis presents Particular a 3d ...
    • Sorterius: Game-inspired App for Encouraging Outdoor Physical Activity for People with Intellectual Disabilities 

      Stellander, Magnus (Master thesis; Mastergradsoppgave, 2021-05-15)
      People with intellectual disabilities have difficulties in reaching the World Health Organization's (WHO) suggested level of physical activity. Previous research shows that participating in physical activities often is related to self-efficacy in a physical activity setting and personal motivation. As physical activity has significant effects on physical and mental health, this thesis aimed to develop ...
    • Reducing Objective Function Mismatch in Deep Clustering with the Unsupervised Companion Objective 

      Trosten, Daniel Johansen; Jenssen, Robert; Kampffmeyer, Michael (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-04-19)
      Preservation of local similarity structure is a key challenge in deep clustering. Many recent deep clustering methods therefore use autoencoders to help guide the model's neural network towards an embedding which is more reflective of the input space geometry. However, recent work has shown that autoencoder-based deep clustering models can suffer from objective function mismatch (OFM). In order to ...
    • Fokus på sikkerhetskultur i organisasjoner: Hvordan kan organisasjoner bedre forstå og arbeide med sikkerhetskultur? 

      Flakstad, Thor-Eivind C. (Master thesis; Mastergradsoppgave, 2019-06-14)
      Sikkerhetskultur har fått et økende fokus i organisasjoner som et nytt verktøy som burde fokuseres på i organisasjoners sikkerhetsarbeid. Tankene rundt brukbarheten til sikkerhetskultur er sprikende mellom akademikere, lovgivere og innen organisasjoner. Denne studien forsøker å vise at sikkerhetskultur er mer enn bare de observerbare manifesteringene av kulturen, samtidig som det forsøkes å skape ...
    • Testing miniaturized extraction chromatography protocols for combined 87Sr/86Sr and δ88/86Sr analyses of pore water by MC‐ICP‐MS 

      Argentino, Claudio; Lugli, Federico; Cipriani, Anna; Panieri, Giuliana (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-05-04)
      We tested two miniaturized extraction chromatography protocols for strontium isolation based on 300 μL (Protocol 1) and 30 μL (Protocol 2) column volumes of Sr‐Spec resin, for the simultaneous determination of 87Sr/86Sr and δ88/86Sr by MC‐ICP‐MS. The accuracy and precision of the Sr isotope ratios have been evaluated by analyzing JCt‐1 and SRM 1640a reference materials, resulting in a reproducibility ...
    • Challenges and opportunities beyond structured data in analysis of electronic health records 

      Tayefi, Maryam; Ngo, Phuong; Chomutare, Taridzo; Dalianis, Hercules; Salvi, Elisa; Budrionis, Andrius; Godtliebsen, Fred (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-02-14)
      Electronic health records (EHR) contain a lot of valuable information about individual patients and the whole population. Besides structured data, unstructured data in EHRs can provide extra, valuable information but the analytics processes are complex, time-consuming, and often require excessive manual effort. Among unstructured data, clinical text and images are the two most popular and important ...
    • Keeping Up with the Market: Extracting competencies from Norwegian job listings 

      Fagerbakk, Anton Garri (Mastergradsoppgave; Master thesis, 2021-05-15)
      The Norwegian labour market is under continuous change because of fast-paced innovation in technology. It is therefore vital for educational institutions curricula to reflect the changing requirements to keep the population hireable and provide employers with a highly adaptable workforce. There are no complete systems that let us analyse and extract this information about the labour market efficiently. ...
    • The Role of Mineral Assemblages in the Environmental Impact of Cu-Sulfide Deposits: A Case Study from Norway 

      Mun, Yulia; Palinkas, Sabina Strmic; Kullerud, Kåre (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-06-12)
      Metallic mineral deposits represent natural geochemical anomalies of economically valuable commodities but, at the same time, their weathering may have negative environmental implications. Cu-sulfide mineral deposits have been recognized as deposits with a particularly large environmental footprint. However, different Cu deposits may result in significantly different environmental impacts, mostly ...
    • The influence of surface charge on the coalescence of ice and dust particles in the mesosphere 

      Baptiste, Joshua; Williamsen, Connor; Fox, John; Stace, Anthony, J.; Hassan, Muhammad; Braun, Stefanie; Mann, Ingrid; Besley, Elena (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-06-09)
      Agglomeration of charged ice and dust particles in the mesosphere and lower thermosphere is studied using a classical electrostatic approach, which is extended to capture the induced polarisation of surface charge. Collision outcomes are predicted whilst varying the particle size, charge, dielectric constant, relative kinetic energy, collision geometry and the coefficient of restitution. In addition ...
    • An overall performance index for wind farms: a case study in Norway Arctic region 

      Mustafa, Albara; Barabadi, Abbas; Markeset, Tore; Naseri, Masoud (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-06-12)
      Wind farms (WFs) experience various challenges that affect their performance. Mostly, designers focus on the technical side of WFs performance, mainly increasing the power production of WFs, through improving their manufacturing and design quality, wind turbines capacity, their availability, reliability, maintainability, and supportability. On the other hand, WFs induce impacts on their surroundings, ...
    • Planktic foraminiferal and pteropod contributions to carbon dynamics in the Arctic Ocean (north Svalbard margin) 

      Anglada-Ortiz, Griselda; Zamelczyk, Katarzyna; Meilland, Julie; Ziveri, Patrizia; Chierici, Melissa; Fransson, Agneta; Rasmussen, Tine Lander (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-06-09)
      Planktic foraminifera and shelled pteropods are some of the major producers of calcium carbonate (CaCO<sub>3</sub>) in the ocean. Their calcitic (foraminifera) and aragonitic (pteropods) shells are particularly sensitive to changes in the carbonate chemistry and play an important role for the inorganic and organic carbon pump of the ocean. Here, we have studied the abundance distribution of planktic ...
    • Conjugate ionospheric perturbation during the 2017 solar eclipse 

      Zhang, Shunrong; Erickson, Philip J.; Vierinen, Juha; Aa, Ercha; Rideout, William; Coster, Anthea; Goncharenko, Larisa (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-01-16)
      We report new findings of total electron content (TEC) perturbations in the southern hemisphere at conjugate locations to the northern eclipse on August 21, 2017. We identified a persistent conjugate TEC depletion by 10%–15% during the eclipse time, elongating along magnetic latitudes with at least ∼5° latitudinal width. As the Moon's shadow swept southward, this conjugate depletion moved northward ...
    • Leveraging Computer Vision for Applications in Biomedicine and Geoscience 

      Johansen, Thomas Haugland (Doctoral thesis; Doktorgradsavhandling, 2021-06-25)
      Skin cancer is one of the most common types of cancer and is usually classified as either non-melanoma and melanoma skin cancer. Melanoma skin cancer accounts for about half of all skin cancer-related deaths. The 5-year survival rate is 99% when the cancer is detected early but drops to 25% once it becomes metastatic. In other words, the key to preventing death is early detection. Foraminifera ...
    • En undersøkelse av elevers motivasjon og oppfatninger om matematikkfaget og matematikkundervisning 

      Jensen, Joakim André (Master thesis; Mastergradsoppgave, 2021-04-01)
      Tema for avhandlingen er motivasjon og oppfatninger om matematikkfaget og matematikkundervisning blant elever. Avhandlingen mål er å undersøke elevers motivasjon og oppfatninger gjennom en sammenligning av svarene til de enkelte elevene på et spørreskjema og i et intervju. Fokuset er på om svarene elevene gir i intervjuet kan utdype hva de har svart i spørreskjemaet.
    • Anomalous transport due to large coherent structures in a magnetized toroidal plasma 

      Fredriksen, Åshild; Pécseli, Hans L; Trulsen, Jan Karsten (Journal article; Tidsskriftartikkel; Peer reviewed, 2020-11-18)
      Anomalous transport due to large coherent structures, or coherent events, is studied experimentally in a magnetized toroidal discharge plasma. The present analysis emphasizes anomalous plasma losses as well as transport of electron thermal energy density across magnetic field lines. The experiment was carried out in the Blaamann device at the University of Tromsø. The diagnostics are based on data ...
    • A New Technique for Investigating Dust Charging in the PMSE Source Region 

      Mahmoudian, Alireza; Kosch, Michael J.; Vierinen, Juha; Rietveld, Michael T (Journal article; Tidsskriftartikkel; Peer reviewed, 2020-09-21)
      A new technique for investigating dust charging in the PMSE (polar mesospheric summer echoes) source region is proposed and discussed in this paper. The first high-frequency (HF) modulation of the PMSE with varying pump power was employed during a recent experimental campaign at EISCAT (European Incoherent Scatter Scientific Association). Two experiment setups including HF pump power stepping as ...
    • Characterizing slope processes along the Piggtind mountain ridge, using 2D InSAR 

      Sandbakken, Henrik (Mastergradsoppgave; Master thesis, 2021-05-15)
      Large rock slope deformations potentially evolving into catastrophic rock avalanches pose an eminent threat to the Norwegian society. A comprehensive characterization of their kinematic behavior, progressive slope development, and current deformation rates are thus required for hazard management. Njunnás and Piggtind/Skulvatindane are two adjacent rock slopes located in Troms County, Norway. Both ...
    • Multi-frequency polarimetric SAR signatures of lead sea ice and oil spills 

      Johansson, Malin; Brekke, Camilla; Spreen, Gunnar (Journal article; Tidsskriftartikkel; Peer reviewed; Conference object; Konferansebidrag, 2017-12-04)
      Synthetic aperture radar is used to identify and monitor oil spills. Separation from oil spill look-alikes is an important part of a fully automatic oil spill detection scheme. Here we investigate the polarimetric signatures for oil spills and newly formed sea ice (a well-known look-alike) in fully polarimetric Radarsat-2 satellite scenes. Using the fully polarimetric scenes we calculate four different ...
    • Optical Waveguides for Infrared Spectroscopic Detection of Molecular Gases 

      Vlk, Marek (Doctoral thesis; Doktorgradsavhandling, 2021-06-18)
      Fields like medical diagnostics, urban and industrial environmental monitoring or basic microbiological research greatly benefit from advances in chemical and biological sensing. These applications require rapid sample analysis, reduced needs for sample handling, or good sensor network. Such demands can be met with miniaturised sensors utilising methods which secure sufficient sensitivity and ...