• Acoustic classification in multifrequency echosounder data using deep convolutional neural networks 

      Brautaset, Olav; Waldeland, Anders Ueland; Johnsen, Espen; Malde, Ketil; Eikvil, Line; Salberg, Arnt-Børre; Handegard, Nils Olav (Journal article; Peer reviewed, 2020)
      Acoustic target classification is the process of assigning observed acoustic backscattering intensity to an acoustic category. A deep learning strategy for acoustic target classification using a convolutional network is ...
    • Adaptive registration of remote sensing images using supervised learning 

      Eikvil, Line; Holden, Marit; Huseby, Ragnar Bang (Peer reviewed; Journal article, 2009)
      This paper describes a system for co-registration of time series satellite images which uses a learning-based strategy. During a training phase, the system learns to recognize regions in an image suited for registration. ...
    • Automatic Fish Age Determination across Different Otolith Image Labs Using Domain Adaptation 

      Ordonez, Alba; Eikvil, Line; Salberg, Arnt-Børre; Harbitz, Alf; Elvarsson, Bjarki Thor (Journal article; Peer reviewed, 2022)
      The age determination of fish is fundamental to marine resource management. This task is commonly done by analysis of otoliths performed manually by human experts. Otolith images from Greenland halibut acquired by the ...
    • Explaining decisions of deep neural networks used for fish age prediction 

      Ordonez, Alba; Eikvil, Line; Salberg, Arnt-Børre; Harbitz, Alf; Murray, Sean Meling; Kampffmeyer, Michael (Peer reviewed; Journal article, 2020)
    • Machine Learning + Marine Science: Critical Role of Partnerships in Norway 

      Handegard, Nils Olav; Eikvil, Line; Jenssen, Robert; Kampffmeyer, Michael; Salberg, Arnt Børre; Malde, Ketil (Others, 2021)
      In this essay, we review some recent advances in developing machine learning (ML) methods for marine science applications in Norway. We focus mostly on deep learning (DL) methods and review the challenges we have faced in ...
    • A mammography classification model trained from image labels only 

      Dahl, Fredrik Andreas; Holden, Marit; Brautaset, Olav; Eikvil, Line (Journal article; Peer reviewed, 2022)
    • Multi-sensor and time-series approaches for monitoring of snow parameters 

      Solberg, Rune; Amlien, Jostein; Koren, Hans; Eikvil, Line; Malnes, Eirik; Storvold, Rune (Chapter, 2004)
      Frequent mapping of snow parameters, like snow cover area (SCA) and snow surface wetness (SSW), is important for applications in hydrology, meteorology and climatology. In this study, we have developed a few general ...
    • Semi-supervised target classification in multi-frequency echosounder data 

      Choi, Changkyu; Kampffmeyer, Michael; Handegard, Nils Olav; Salberg, Arnt Børre; Brautaset, Olav; Eikvil, Line; Jenssen, Robert (Journal article; Peer reviewed, 2021)
      Acoustic target classification in multi-frequency echosounder data is a major interest for the marine ecosystem and fishery management since it can potentially estimate the abundance or biomass of the species. A key problem ...
    • A two-stage mammography classification model using explainable-AI for ROI detection 

      Dahl, Fredrik Andreas; Brautaset, Olav; Holden, Marit; Eikvil, Line; Larsen, Marthe; Hofvind, Solveig Sand-Hanssen (Journal article; Peer reviewed, 2023)
      This study introduces an enhanced version of a two-stage modelling approach using artificial intelligence (AI) for breast cancer detection in mammography screening. Leveraging a large dataset of 2,863,175 mammograms from ...
    • User-Intended Doppler Measurement Type Prediction Combining CNNs With Smart Post-Processing 

      Gilbert, Andrew David; Holden, Marit; Eikvil, Line; Rakhmail, Mariia; Babic, Aleksandar; Aase, Svein Arne; Samset, Eigil; Mcleod, Kristin (Journal article; Peer reviewed, 2020-10)
      Spectral Doppler measurements are an important part of the standard echocardiographic examination. These measurements give insight into myocardial motion and blood flow providing clinicians with parameters for diagnostic ...