Now showing items 1-10 of 47
Arctic Field Summer Schools: training and awareness in the Arctic
(Conference object; Konferansebidrag, 2020-01)
A series of three summer schools engaged nearly fifty graduate students in exploring science questions related to current Arctic challenges, and brought together leading Arctic researchers from the partner institutions. Each partner organised a Field School and each had their own unique styles and emphasis. This collaboration aimed to deepen the Arctic knowledge of the young generation, and to create ...
How and why develop scenarios for training students to use their knowledge in practice?
(Conference object; Konferansebidrag, 2021-09)
To be able to handle crisis and risks there is a need for different skills. We will focus on learning by combining theory and practice. Since NEEDS is a disaster management community, scenarios in line with this theme are wanted.<p> <p>This colloquium can be an experience transfer between educators that work with scenario-based training and want to develop this further. Drawing on different ...
International collaboration for meeting the challenges of huge and cascading disasters
(Conference object; Konferansebidrag, 2021-09)
Some crisis have an international impact. How is it possible to enhance collaboration between nations in huge and cascading disasters? We will present Barents Rescue (BR) as an inspiration for our Student Barents Rescue (SBR) and thereafter show examples from a student pilot with an international scenario.
Multi-View Self-Constructing Graph Convolutional Networks With Adaptive Class Weighting Loss for Semantic Segmentation
(Conference object; Konferansebidrag, 2020-07-28)
We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. Building on the recently proposed Self-Constructing Graph (SCG) module, which makes use of learnable latent variables to self-construct the underlying graphs directly from the input features without relying on manually built prior knowledge graphs, we leverage ...
Up-to-the-minute Data Policy Updates for Participatory Studies
(Conference object; Konferansebidrag, 2021-06-14)
High spatial and temporal resolution L- and C-band Synthetic Aperture Radar data analysis from the yearlong MOSAiC expedition
(Conference object; Konferansebidrag, 2021-04)
In the yearlong MOSAIC expedition (2019-2020) R/V Polarstern drifted with sea ice through the Arctic Ocean, with the goal to continually monitor changes in the coupled ocean-ice-atmosphere system throughout the seasons. A substantial amount of synthetic aperture radar (SAR) satellite images overlapping the campaign was collected. Here, we investigate the change in polarimetric features over sea ice ...
Accountable Human Subject Research Data Processing using Lohpi
(Conference object; Konferansebidrag, 2021-06)
In human subject research, various data about the studied individuals are collected. Through re-identification and statistical inferences, this data can be exploited for interests other than the ones the subjects initially consented to. Such exploitation must be avoided to maintain trust with the researched population. We argue that keeping data-access policies up-to-date and building accountability ...
Learning Nanoscale Motion Patterns of Vesicles in Living Cells
(Conference object; Konferansebidrag, 2020-08-05)
Detecting and analyzing nanoscale motion patterns of vesicles, smaller than the microscope resolution (~250 nm), inside living biological cells is a challenging problem. State-of-the-art CV approaches based on detection, tracking, optical flow or deep learning perform poorly for this problem. We propose an integrative approach, built upon physics based simulations, nanoscopy algorithms, and shallow ...
Short-Term Load Forecasting with Missing Data using Dilated Recurrent Attention Networks
(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 ...
Condition Monitoring System for Internal Blowout Prevention (IBOP) in Top Drive Assembly System using Discrete Event Systems and Deep Learning Approaches
(Conference object; Konferansebidrag, 2020-07-19)
<p>Offshore oil drilling is a complex process that requires careful coordination of hardware and control systems. Fault monitoring systems play an important role in such systems for safe and profitable operations. Thus, predictive maintenance and monitoring operating conditions of drilling systems are critical to the overall production cycle. In this paper, we are addressing the topic of condition ...