Institutt for fysikk og teknologi: Nye registreringer
Viser treff 221-240 av 1294
-
Critical echo state network dynamics by means of Fisher information maximization
(Chapter; Bokkapittel, 2017-07-03)The computational capability of an Echo State Network (ESN), expressed in terms of low prediction error and high short-term memory capacity, is maximized on the so-called “edge of criticality”. In this paper we present a novel, unsupervised approach to identify this edge and, accordingly, we determine hyperparameters configuration that maximize network performance. The proposed method is ... -
Temporal overdrive recurrent neural network
(Chapter; Bokkapittel, 2017-07-03)In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics. The proposed network is composed by several recurrent groups of neurons that are trained to separately adapt to each timescale, in order to improve the system identification process. We test our framework on time series prediction tasks ... -
Large-Scale Mapping of Small Roads in Lidar Images Using Deep Convolutional Neural Networks
(Chapter; Bokkapittel, 2017-05-19)Detailed and complete mapping of forest roads is important for the forest industry since they are used for timber transport by trucks with long trailers. This paper proposes a new automatic method for large-scale mapping forest roads from airborne laser scanning data. The method is based on a fully convolutional neural network that performs end-to-end segmentation. To train the network, a large set ... -
Eddy Detection in the Marginal Ice Zone with Sentinel-1 Data Using YOLOv5
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-04-24)The automatic detection and analysis of ocean eddies in the marginal ice zone via remote sensing is a very challenging task but of critical importance for scientific applications and anthropogenic activities. Therefore, as one of the first steps toward the automation of the eddy detection process, we investigated the potential of applying YOLOv5, a deep convolutional neural network architecture, to ... -
SAR and Passive Microwave Fusion Scheme: A Test Case on Sentinel-1/AMSR-2 for Sea Ice Classification
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-02-14)The most common source of information about sea ice conditions is remote sensing data, especially images obtained from synthetic aperture radar (SAR) and passive microwave radiometers (PMR). Here we introduce an adaptive fusion scheme based on Graph Laplacians that allows us to retrieve the most relevant information from satellite images. In a first test case, we explore the potential of sea ice ... -
Droner som FKT - bruk av droner som forebyggende tiltak i beitenæringen
(Research report; Forskningsrapport, 2023)Utmarksbeitende dyr er utsatt for angrep fra fredet rovvilt. I oppdrag fra rovviltnemnda i region 6 Midt-Norge undersøker vi den mulige nytteverdien av droner i åpen kategori som forebyggende- og konfliktdempende tiltak (FKT). Utredningen er basert på informasjon fra intervjuer, faglitteratur og dronetestflygninger.Droner som FKT kan brukes under (1) tilsyn, (2) flytting av dyr fra rovdyrutsatte ... -
Label-free superior contrast with c-band ultra-violet extinction microscopy
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-03-03)In 1934, Frits Zernike demonstrated that it is possible to exploit the sample’s refractive index to obtain superior contrast images of biological cells. The refractive index contrast of a cell surrounded by media yields a change in the phase and intensity of the transmitted light wave. This change can be due to either scattering or absorption caused by the sample. Most cells are transparent at visible ... -
Rapid prototyping of 1xN multifocus gratings via additive direct laser writing
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-04-05)Multifocus gratings (MFGs) enable microscopes and other imaging systems to record entire Z-stacks of images in a single camera exposure. The exact grating shape depends on microscope parameters like wavelength and magnification and defines the multiplexing onto a grid of MxN Z-slices. To facilitate the swift production and alteration of MFGs for a system and application at hand, we have developed ... -
Deep Semi-Supervised Semantic Segmentation in Multi-Frequency Echosounder Data
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-02-01)Multi-frequency echosounder data can provide a broad understanding of the underwater environment in a non-invasive manner. The analysis of echosounder data is, hence, a topic of great importance for the marine ecosystem. Semantic segmentation, a deep learning based analysis method predicting the class attribute of each acoustic intensity, has recently been in the spotlight of the fisheries and aquatic ... -
Studentaktiv læring med store studentgrupper – fordeler og ulemper med gruppediskusjon i pollbasert undervisning
(Conference object; Konferansebidrag, 2023-03)To viktige prinsipper for å øke studentenes læring i undervisning er aktiv deltagelse og formativ vurdering. Innføring av disse prinsippene i undervisning med store studentgrupper kan imidlertid by på utfordringer. Løsningen kan være å bruke flervalgsoppgaver i undervisningen med påfølgende formativ vurdering av faglæreren, en undervisningsform som vi her kaller pollbasert undervisning. I dette ... -
Exploring the Behavior of Open-Source Diffusion Model Inpainting Algorithms
(Master thesis; Mastergradsoppgave, 2023-01-26)The present study aimed to examine the performance of an open-source diffusion model inpainting algorithm under varying conditions of inpainting strength and mask radius. However, the results obtained were unexpected and raise significant concerns. Our findings indicate that the algorithm not only modifies the pixels within the designated mask, as intended, but also alters pixels out side of the ... -
Raman-spectroscopy and of optically trapped nanoparticles
(Mastergradsoppgave; Master thesis, 2022-11-06)The present work begins a large layer of experiments on the study of Raman radiation from extracellular vesicles. It is a promising method that provides unique information about the global biomolecular composition of a single vesicle or a small number of vesicles. Two physical phenomena are present in this work, Raman scattering and optical trapping. In Raman scattering, the scattered radiation ... -
On the Exploitation of Heterophily in Graph-Based Multimodal Remote Sensing Data Analysis
(Journal article; Tidsskriftartikkel; Peer reviewed, 2022)The field of Earth observation is dealing with increasingly large, multimodal data sets. An important processing step consists of providing these data sets with labels. However, standard label propagation algorithms cannot be applied to multimodal remote sensing data for two reasons. First, multimodal data is heterogeneous while classic label propagation algorithms assume a homogeneous network. ... -
Modeling Solar Orbiter dust detection rates in the inner heliosphere as a Poisson process
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-02-20)Context. Solar Orbiter provides dust detection capability in the inner heliosphere, but estimating physical properties of detected dust from the collected data is far from straightforward.<p> <p>Aims. First, a physical model for dust collection considering a Poisson process is formulated. Second, it is shown that dust on hyperbolic orbits is responsible for the majority of dust detections with ... -
CIRFA Cruise 2022. Cruise report.
(Research report; Forskningsrapport, 2022)This report gives a complete record of all data sets that were collected during the CIRFA cruise 22 April - 9 May 2022, with RV Kronprins Haakon, to the western Fram Strait and the East Greenland Sea. IMR cruise ID 2022704. The CIRFA-cruise 2022 was funded by UiT the Arctic University of Norway, the European Space Agency (RFP Response No 3-17845), the Research Council of Norway (RCN project ... -
The Kernelized Taylor Diagram
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-02-02)This paper presents the kernelized Taylor diagram, a graphical framework for visualizing similarities between data populations. The kernelized Taylor diagram builds on the widely used Taylor diagram, which is used to visualize similarities between populations. However, the Taylor diagram has several limitations such as not capturing non-linear relationships and sensitivity to outliers. To address ... -
A new spectral harmonization algorithm for Landsat-8 and Sentinel-2 remote sensing reflectance products using machine learning: a case study for the Barents Sea (European Arctic)
(Journal article; Tidsskriftartikkel; Peer reviewed, 2022-12-12)The synergistic use of Landsat-8 operational land imager (OLI) and Sentinel-2 multispectral instrument (MSI) data products provides an excellent opportunity to monitor the dynamics of aquatic ecosystems. However, the merging of data products from multisensors is often adversely affected by the difference in their spectral characteristics. In addition, the errors in the atmospheric correction (AC) ... -
Axial and radial development of the hot electron distribution in a helicon plasma source, measured by a retarding field energy analyzer (RFEA)
(Journal article; Tidsskriftartikkel; Peer reviewed, 2022-02-10)The information about the electron population of a helicon source plasma that expands along a magnetic nozzle is important for understanding the plasma acceleration across the potential drop that forms in the nozzle. The electrons need an energy higher than the potential drop to escape from the source. At these energies the signal of a Langmuir probe is less accurate. An inverted RFEA measures the ... -
Modulation of polar mesospheric summer echoes (PMSEs) with high-frequency heating during low solar illumination
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-02-14)Polar mesospheric summer echo (PMSE) formation is linked to charged dust/ice particles in the mesosphere. We investigate the modulation of PMSEs with radio waves based on measurements with EISCAT VHF radar and EISCAT heating facility during low solar illumination. The measurements were made in August 2018 and 2020 around 20:02 UT. Heating was operated in cycles with intervals of 48 s on and 168 ... -
A self-guided anomaly detection-inspired few-shot segmentation network
(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 ...