Viser treff 745-764 av 942

    • Segmentation of PMSE data using random forests 

      Jozwicki, Dorota; Sharma, Puneet; Mann, Ingrid; Hoppe, Ulf-Peter Jürgen (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-06-22)
      EISCAT VHF radar data are used for observing, monitoring, and understanding Earth’s upper atmosphere. This paper presents an approach to segment Polar Mesospheric Summer Echoes (PMSE) from datasets obtained from EISCAT VHF radar data. The data consist of 30 observations days, corresponding to 56,250 data samples. We manually labeled the data into three different categories: PMSE, Ionospheric ...
    • Selecting principal attributes in multimodal remote sensing for sea ice characterization 

      Khachatrian, Eduard; Chlaily, Saloua; Eltoft, Torbjørn; Marinoni, Andrea (Chapter; Bokkapittel, 2021)
      Automatic ice charting cannot be achieved using only SAR modalities. It is fundamental to combine information from other remote sensors with different characteristics for more reliable sea ice characterization. In this paper, we employ principal feature analysis (PFA) to select significant information from multimodal remote sensing data. PFA is a simple yet very effective approach that can be applied ...
    • Selective Imputation for Multivariate Time Series Datasets with Missing Values 

      Blazquez-Garcia, Ane; Wickstrøm, Kristoffer Knutsen; Yu, Shujian; Mikalsen, Karl Øyvind; Boubekki, Ahcene; Conde, Angel; Mori, Usue; Jenssen, Robert; Lozano, Jose A. (Journal article; Tidsskriftartikkel, 2023-01-31)
      Multivariate time series often contain missing values for reasons such as failures in data collection mechanisms. Since these missing values can complicate the analysis of time series data, imputation techniques are typically used to deal with this issue. However, the quality of the imputation directly affects the performance of downstream tasks. In this paper, we propose a selective imputation ...
    • Self-Constructing Graph Convolutional Networks for Semantic Labeling 

      Liu, Qinghui; Kampffmeyer, Michael; Jenssen, Robert; Salberg, Arnt-Børre (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-02-17)
      Graph Neural Networks (GNNs) have received increasing attention in many fields. However, due to the lack of prior graphs, their use for semantic labeling has been limited. Here, we propose a novel architecture called the Self-Constructing Graph (SCG), which makes use of learnable latent variables to generate embeddings and to self-construct the underlying graphs directly from the input features ...
    • Self-constructing graph neural networks to model long-range pixel dependencies for semantic segmentation of remote sensing images 

      Liu, Qinghui; Kampffmeyer, Michael; Jenssen, Robert; Salberg, Arnt Børre (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-06-16)
      Capturing global contextual representations in remote sensing images by exploiting long-range pixel-pixel dependencies has been shown to improve segmentation performance. However, how to do this efficiently is an open question as current approaches of utilising attention schemes, or very deep models to increase the field of view, increases complexity and memory consumption. Inspired by recent work ...
    • A self-guided anomaly detection-inspired few-shot segmentation network 

      Salahuddin, Suaiba Amina; Hansen, Stine; Gautam, Srishti; Kampffmeyer, Michael; Jenssen, Robert (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-11-13)
      Standard strategies for fully supervised semantic segmentation of medical images require large pixel-level annotated datasets. This makes such methods challenging due to the manual labor required and limits the usability when segmentation is needed for new classes for which data is scarce. Few-shot segmentation (FSS) is a recent and promising direction within the deep learning literature designed ...
    • Self-similar transport processes in a two-dimensional realization of multiscale magnetic field turbulence 

      Milovanov, Alexander V.; Chiaravalloti, Francesco; Zimbardo, Gaetano (Journal article; Tidsskriftartikkel; Peer reviewed, 2004-12-14)
      We present the results of a numerical investigation of charged-particle transport across a synthesized magnetic configuration composed of a constant homogeneous background field and a multiscale perturbation component simulating an effect of turbulence on the microscopic particle dynamics. Our main goal is to analyze the dispersion of ideal test particles faced to diverse conditions in the turbulent ...
    • Self-Supervised Few-Shot Learning for Ischemic Stroke Lesion Segmentation 

      Tomasetti, Luca; Hansen, Stine; Khanmohammadi, Mahdieh; Engan, Kjersti; Høllesli, Liv Jorunn; Kurz, Kathinka Dæhli; Kampffmeyer, Michael Christian (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-09-01)
      Precise ischemic lesion segmentation plays an essential role in improving diagnosis and treatment planning for ischemic stroke, one of the prevalent diseases with the highest mortality rate. While numerous deep neural network approaches have recently been proposed to tackle this problem, these methods require large amounts of annotated regions during training, which can be impractical in the medical ...
    • 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; Tidsskriftartikkel; Peer reviewed, 2021-08-12)
      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 of current methods is the heavy dependence on the manual categorization of data samples. As a solution, we propose a novel semi-supervised deep learning method leveraging a few ...
    • seMLP: Self-Evolving Multi-Layer Perceptron in Stock Trading Decision Making 

      Jun, S.W; Sekh, Arif Ahmed; Quek, Chai; Prasad, Dilip K. (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-02-24)
      There is a growing interest in automatic crafting of neural network architectures as opposed to expert tuning to fnd the best architecture. On the other hand, the problem of stock trading is considered one of the most dynamic systems that heavily depends on complex trends of the individual company. This paper proposes a novel self-evolving neural network system called self-evolving Multi-Layer ...
    • Sensitive on-chip methane detection with a cryptophane-A cladded Mach-Zehnder interferometer 

      Dullo, Firehun Tsige; Lindecrantz, Susan; Jagerska, Jana; Hansen, Jørn H; Engqvist, Stig Olov Magnus; Solbø, Stian; Hellesø, Olav Gaute (Journal article; Tidsskriftartikkel; Peer reviewed, 2015-11-24)
      We report a methane sensor based on an integrated Mach-Zehnder interferometer, which is cladded by a styrene-acrylonitrile film incorporating cryptophane-A. Cryptophane-A is a supramolecular compound able to selectively trap methane, and its presence in the cladding leads to a 17-fold sensitivity enhancement. Our approach, based on 3 cm-long low-loss Si3N4 rib waveguides, results in a detection limit ...
    • Separation and characterisation of mineral oil slicks and newly formed sea ice in L-band synthetic aperture radar 

      Johansson, Malin; Espeseth, Martine; Brekke, Camilla; Skrunes, Stine (Journal article; Tidsskriftartikkel; Peer reviewed, 2019-11-14)
      Maritime activities in the Arctic Ocean is increasing and consequently the risk for an oil spill there is rising. Synthetic Aperture Radar (SAR) is used operationally to detect and monitor oil slicks and for sea ice monitoring and observations. Leads are often used for ship routing and within the leads newly formed sea ice is often present. Separation between the low backscatter areas that constitutes ...
    • Serial Raman spectroscopy of particles trapped on a waveguide 

      Løvhaugen, Pål; Ahluwalia, Balpreet Singh; Huser, Thomas Rolf; Hellesø, Olav Gaute (Journal article; Tidsskriftartikkel; Peer reviewed, 2013)
      We demonstrate that Raman spectroscopy can be used to characterize and identify particles that are trapped and propelled along optical waveguides. To accomplish this, microscopic particles on a waveguide are moved along the waveguide and then individually addressed by a focused laser beam to obtain their characteristic Raman signature within 1 second acquisition time. The spectrum is used to distinguish ...
    • Shearlets as feature extractor for semantic edge detection: The model-based and data-driven realm: Shearlets for Semantic Edge Detection 

      Andrade-Loarca, Héctor; Kutyniok, Gitta Astrid Hildegard; Öktem, Ozan (Journal article; Tidsskriftartikkel; Peer reviewed, 2020-11-25)
      Semantic edge detection has recently gained a lot of attention as an image-processing task, mainly because of its wide range of real-world applications. This is based on the fact that edges in images contain most of the semantic information. Semantic edge detection involves two tasks, namely pure edge detection and edge classification. Those are in fact fundamentally distinct in terms of the level ...
    • Shock location and CME 3D reconstruction of a solar type II radio burst with LOFAR 

      Zucca, P; Morosan, D; Rouillard, A; Fallows, Richard; Gallagher, P. T.; Magdalenic, J; Klein, K-L; Mann, G; Vocks, C; Carley, E. P.; Bisi, M. M.; Kontar, E. P.; Rothkaehl, Hanna; Dabrowski, B; Krankowski, A; Anderson, James; Asgekar, A; Bell, M. E.; Bentum, M. J.; Best, P; Blaauw, R; Breitling, F.; Broderick, J. W.; Brouw, W. N.; Brüggen, M.; Butcher, H. R.; Ciardi, B.; de Geus, E.; Deller, A.; Duscha, S.; Eislöffel, J.; Garrett, M. A.; Grießmeier, J. M.; Gunst, A. W.; Heald, G.; Hoeft, M.; Hörandel, J.; Iacobelli, M.; Juette, E; Karastergiou, A.; van Leeuwen, J.; McKay, Derek; Mulder, H.A.; Munk, H.; Nelles, A.; Orru, E.; Paas, H.; Pandey, V. N.; Pekal, R.; Pizzo, R.; Polatidis, A. G.; Reich, W.; Rowlinson, A.; Schwarz, D. J.; Shulevski, A.; Sluman, J.; Smirnov, O.V.; Sobey, C.; Soida, M.; Thoudam, S.; Toribio, M. C.; Vermeulen, R.; van Weeran, R. J.; Wucknitz, O.; Zarka, P. (Journal article; Tidsskriftartikkel; Peer reviewed, 2018-07-19)
      <p><i>Context - </i>Type II radio bursts are evidence of shocks in the solar atmosphere and inner heliosphere that emit radio waves ranging from sub-meter to kilometer lengths. These shocks may be associated with coronal mass ejections (CMEs) and reach speeds higher than the local magnetosonic speed. Radio imaging of decameter wavelengths (20–90 MHz) is now possible with the Low Frequency Array ...
    • Short-Term Load Forecasting with Missing Data using Dilated Recurrent Attention Networks 

      Choi, Changkyu; Bianchi, Filippo Maria; Kampffmeyer, Michael; Jenssen, Robert (Conference object; Konferansebidrag, 2020-02-06)
      Forecasting the dynamics of time-varying systems is essential to maintaining the sustainability of the systems. Recent studies have discovered that Recurrent Neural Networks(RNN) applied in the forecasting tasks outperform conventional models that include AutoRegressive Integrated Moving Average(ARIMA). However, due to the structural limitation of vanilla RNN which holds unit-length internal ...
    • Short-Term Load Forecasting with Missing Data using Dilated Recurrent Attention Networks 

      Choi, Changkyu; Bianchi, Filippo Maria; Kampffmeyer, Michael; Jenssen, Robert (Journal article; Tidsskriftartikkel; Peer reviewed, 2020-02-06)
      Forecasting the dynamics of time-varying systems is essential to maintaining the sustainability of the systems. Recent studies have discovered that Recurrent Neural Networks(RNN) applied in the forecasting tasks outperform conventional models that include AutoRegressive Integrated Moving Average(ARIMA). However, due to the structural limitation of vanilla RNN which holds unit-length internal ...
    • Short-Term Load Forecasting with Missing Data using Dilated Recurrent Attention Networks 

      Choi, Changkyu; Kampffmeyer, Michael; Jenssen, Robert (Conference object; Konferansebidrag, 2020)
      Data without annotation are easy to obtain in the real-world, however, established supervised learning methods are not applicable to analyze them. Several learning approaches have been proposed in recent years to exploit the underlying structure of the data without requiring annotations. Semi-supervised learning aims to improve the predictive performance of these unsupervised approaches, by exploiting ...
    • Short-Time Ice Drift and Deformation Measurements Using Multi-Mission Synethetic Aperture Radar 

      Kræmer, Thomas; Brekke, Camilla (Journal article; Tidsskriftartikkel, 2015-06)
      Norway is in a good position regarding frequent access to synthetic aperture radar data. A Norwegian– Canadian agreement provides large quotas of RADARSAT-2 images used operationally by e.g. the Norwegian Ice Service. More recently, Norway’s participation in the Copernicus program also allows rapid access to SENTINEL-1A data. By combining these data sources we can get satellite time series ...
    • Should humans work? 

      Santos Hernandez, Sergio; Kissamitaki, Maritsa; Chiesa, Matteo (Journal article; Tidsskriftartikkel; Peer reviewed, 2020-02-01)
      Should humans work? A simple question at a time when the advent of AI, automation and robotics claims a privileged position in the future of work. The question is perplexing and confusing however once we enquire into the meaning of technology and work as such: some claim that human jobs and well-being might be threatened by technological advances while others predict an increase in high skilled ...