Fakultet for naturvitenskap og teknologi: Nye registreringer
Viser treff 1-20 av 5278
-
Categorization of phenotype trajectories utilizing transformers on clinical time-series
(Chapter; Bokkapittel, 2024-09-11)Patients being admitted to a hospital will most often be associated with a certain clinical development during their stay. However, there is always a risk of patients being subject to the wrong diagnosis or to a certain treatment not pertaining to the desired effect, potentially leading to adverse events. Thus, there is a need to develop an anomaly detection system for deviations from expected ... -
Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-01-23)Polyps are well-known cancer precursors identified by colonoscopy. However, variability in their size, appearance, and location makes the detection of polyps challenging. Moreover, colonoscopy surveillance and removal of polyps are highly operator-dependent procedures and occur in a highly complex organ topology. There exists a high missed detection rate and incomplete removal of colonic polyps. To ... -
PSAIR: A Neuro-Symbolic Approach to Zero-Shot Visual Grounding
(Chapter; Bokkapittel, 2024-09-09)Supervised methods for Visual Grounding often require costly annotations of paired sentences and images with ground truth boxes. Recent zero-shot approaches to visual grounding such as ReCLIP and ChatRef aim to avoid the need for costly annotation of paired sentences and images with ground truth boxes. However, these approaches leverage an inflexible detect-then-reasoning paradigm, which leads to a ... -
Multi-modal data analysis for enhanced nautical skill development
(Chapter; Bokkapittel, 2024)This paper explores the innovative application of multi-modal data analysis for nautical skill development process. By examining the potential of integrating diverse data sources e.g., ship motion, visual, auditory and sensor data, the possibility of obtaining performance insights could be enhanced, and the decision-making processes in complex navigational environments can be made more transparent. ... -
Reinforcement Learning for Fishing Route Planning and Optimization
(Chapter; Bokkapittel, 2024-08-09)Pelagic fishing is one of the primary economic activities in the Arctic, especially in the Barents Sea region. Optimizing fishing vessel voyage planning is a feasible avenue for enhancing efficiency, profitability, and sustainability while mitigating accidental risks posed by adverse weather conditions and reducing environmental impact through decreased fuel consumption. Currently, fishing voyage ... -
GridWatch: A Smart Network for Smart Grid
(Chapter; Bokkapittel, 2024-11-04)The adoption of decentralized energy market models facilitates the exchange of surplus power among local nodes in peer-to-peer settings. However, decentralized energy transactions within untrusted and non-transparent energy markets in modern Smart Grids expose vulnerabilities and are susceptible to attacks. One such attack is the False Data Injection Attack, where malicious entities intentionally ... -
AC Microgrid Modeling and Adaptive Control Using Biomimetic Valence Learning: An AI-Based Approach
(Chapter; Bokkapittel, 2024-11-04)AC microgrids play a crucial role in integrating distributed energy resources and facilitating localized power management in contemporary power networks. Nevertheless, conventional droop control methods in these microgrids have constraints in guaranteeing precise power distribution, stability of voltage/frequency, and flexibility in response to changing operating conditions. This study introduces ... -
Interrogating Sea Ice Predictability with Gradients
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-02-14)Predicting sea ice concentration (SIC) is an important task in climate analysis. The recently proposed deep learning system IceNet is the state-of-the-art sea ice prediction model. IceNet takes high-dimensional climate simulations and observational data as input features and forecasts SIC for the next 6 months over a spatial grid over the northern hemisphere. The model has proven to be particularly ... -
Geochemical and mineralogical characteristics of fjord sediments in Arctic Svalbard: insights into Holocene glacial activity and weathering variability
(Journal article; Tidsskriftartikkel; Peer reviewed, 2025-03-18)The Svalbard archipelago at the border of the Arctic Ocean experiences substantial glacier retreat due to global warming, resulting in a retreat of glacier termini from the marine to terrestrial settings. However, the impact of these transitions on marine environments remains poorly understood. To improve our understanding of how Arctic Svalbard responds to fluctuations in climate and glaciers, we ... -
AI-Based Cropping of Sport Videos Using SmartCrop
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-08-27)In the rapidly evolving landscape of digital platforms, the need for optimizing media representations to cater to various aspect ratios is palpable. In this paper, we pioneer an approach that utilizes object detection, scene detection, outlier detection, and interpolation for smart cropping. Using soccer as a case study, our primary goal is to capture the frame salience using object (player and ball) ... -
Cold Seeps and Coral Reefs in Northern Norway: Carbon Cycling in Marine Ecosystems With Coexisting Features
(Journal article; Tidsskriftartikkel; Peer reviewed, 2025-03-20)Cold seeps and cold-water corals (CWCs) coexist on Northern Norway's continental shelf at the Hola trough between Lofoten and Vesterålen. Here, cold seeps release methane from the seabed, yet none reaches the sea surface. Instead, the methane dissolves and disperses in the ocean where it is ultimately consumed by methane-oxidizing microorganisms. These microorganisms metabolize methane and release ... -
Recurrent Lorentzian Weyl Spaces
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-07-02)We find the local form of all non-closed Lorentzian Weyl manifolds (M,c,∇) with recurrent curvature tensor. The recurrent curvature tensor turns out to be weighted parallel, i.e., the obtained spaces provide certain generalization of locally symmetric affine spaces for the Weyl geometry. If the dimension of the manifold is greater than 3, then the conformal structure is flat, and the recurrent Weyl ... -
Addressing the Impact of Complex English Use in Communicating Climate Change in Nigerian Communities Through Contextual Understanding.
(Journal article; Tidsskriftartikkel; Peer reviewed, 2025-03-09)The effective implementation of preparedness and response strategies toward climate change resilience has evolved into a technical, sociopolitical, and communication issue. We argue that, for climate communication to effectively contribute to community resilience, it demands meaningful dialogue and engagement to facilitate understanding. Using the risk communication theory, we assessed the impact ... -
Transition metal azahemiporphycenes as singlet oxygen sensitizers
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024)Using free-base tris( p -X-phenyl)corrole (X = H, Me, OMe) as starting materials and 4-aminotriazole as the nitrogen source, we used a DDQ-mediated, room-temperature strategy for generating isocorroles to obtain the corresponding 6-azahemiporphycenes, H2[X-AHP], one of which was structurally characterized with single-crystal X-ray diffraction analysis. The free-base ligands were readily derivatized ... -
Variational density functional perturbation theory for metals
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-01-30)Density functional perturbation theory (DFPT) is a well-established method to study responses of molecules and solids, especially responses to atomic displacements or to different perturbing fields (electric, magnetic). Like for density functional theory (DFT), the treatment of metals is delicate, due to the Fermi-Dirac (FD) statistics and electronic bands crossing the Fermi energy. At zero temperature, ... -
GUNet++: guided-U-Net-based compact image representation with an improved reconstruction mechanism
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-09-26)The invention of microscopy- and nanoscopy-based imaging technology opened up different research directions in life science. However, these technologies create the need for larger storage space, which has negative impacts on the environment. This scenario creates the need for storing such images in a memory-efficient way. Compact image representation (CIR) can solve the issue as it targets storing ... -
Tailored multi-layer graphene arrays for precision detection of neurotransmitter
(Journal article; Tidsskriftartikkel, 2024-05-22)The development of sensitive dopamine (DA) sensors has significantly contributed to our understanding of DA-related disorders and has enabled advancements in medical diagnostics and neuroscience research. Therefore, in the present work, a novel electrochemical sensing platform was developed using multi-layer graphene arrays (MGA) modified electrodes for the selective detection of DA. The preparation ... -
Basal Melting and Oceanic Observations Beneath Central Fimbulisen, East Antarctica
(Journal article; Tidsskriftartikkel; Peer reviewed, 2025-03-11)Basal melting of ice shelves is fundamental to Antarctic ice sheet mass loss, yet direct observations remain sparse. We present the first year-round melt record (2017–2021) from a phase-sensitive radar on Fimbulisen, one of the fastest flowing ice shelves in Dronning Maud Land, East Antarctica. The observed long-term mean ablation rate at 350 m depth below the central ice shelf was 1.0 ± 0.5 m ... -
Pigghåtoktet 2024 - Et samarbeidstokt mellom Havforskningsinstituttet og Måløy Videregående Skole, med opplæringsfartøyet MS Skulebas
(Research report; Forskningsrapport, 2025)Pigghå er en datafattig og rødlistet art som historisk har gitt grunnlag for et stort fiskeri med årlige landinger på mer enn 40 000 tonn i mer enn 40 år. Etter langvarig overfiske og etterfølgende bestandssammenbrudd har det nå i en del år vært tegn til vekst i bestanden. I 2020 tok Måløy videregående skole, som eier en autoline/garnbåt, kontakt med Havforskningsinstituttet og presenterte et ønske ... -
Nano-cerium zinc molybdate embedded with activated graphene for detection of levofloxacin in polluted water resources
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-05-28)Antibiotics have widespread applications in personal care, animal muscle growth, and aquaculture, yet their pervasive use gives rise to substantial risks for human health and the ecosystem. Consequently, the imperative lies in developing accurate and highly sensitive detection techniques for analyzing levofloxacin (LFX). This research focuses on the hydrothermal synthesis of unique three-dimensional ...