Young individuals with chronic diseases living in rural areas might face additional problems in their everyday life compared to those in the same position living closer to the cities. Living far away from friends, relatives, other in the same situation, or even general practitioners and specialists may act as an extra burden in their process through their situation. This project is meant to aid ...

Fully supervised semantic segmentation models require pixel-level annotations that are costly to obtain. As a remedy, weakly supervised semantic segmentation has been proposed, where image-level labels and class activation maps (CAM) can detect discriminative regions for specific class objects. In this paper, we evaluated several CAM methods applied to different convolutional neural networks (CNN) ...

Ship icing may lead the ship and crew in great jeopardy. Usually, predictions of such ice build-up are based on the modelling of the heat fluxes capable of freezing sea water originated from wave-ship interactions. This study, on the other hand, follows a different and more general approach by investigating the relationship between the weather situation and icing both using observed parameters from ...

This thesis provides a detailed outlook on research in telementoring, identifying the fundamental limitations hindering its smooth integration into clinical practice. The findings are based on literature reviews and user involvement, minimizing the gap between research and actual use of the system. To address the identified shortcomings, a service-oriented approach to clinical VC systems was proposed. ...

The Helmholtz equation has been used for modeling the sound pressure field under a harmonic load. Computing harmonic sound pressure fields by means of solving Helmholtz equation can quickly become unfeasible if one wants to study many different geometries for ranges of frequencies. We propose a machine learning approach, namely a feedforward dense neural network, for computing the average sound ...

The thesis is done in co-operation with DNV GL Harstad and Schlumberger. DNV GL has provided access to historical accidents data, by using technical documents. Schlumberger has provided technical information about well testing and hazards related to such an event, and an internal risk analysis document, which they use in their operations. This document is modified to suit, and account, for arctic ...

The main research question in this research project was "what are the characteristics of mathematical creativity?" It was investigated both qualitatively and quantitatively and the findings are presented in four articles. In the first article, three high achieving students were given an unfamiliar trigonometric problem. The findings indicate strongly that the student’s way of thinking is strongly ...

For the third time in a decade, solar energy pricing records are tumbling in the Persian Gulf. As each previous wave of new records was met with incredulity, only for these prices to become the new normal around the world within a few years, it would be unwise to once again dismiss low prices as unrepresentative outliers. In this study, we show how local conditions and global macroeconomic factors ...

The increasing use of mobile health (mHealth) tools for self-management is considered to be important to improve health effects for patients with chronic NCDs (noncommunicable diseases). This development is supported by an increasing number of available mHealth apps. The apps range from disease management apps (e.g., diabetes diary) to health and fitness apps (e.g., dietary apps and workout ...

Bio-inspired optimization algorithms have been successfully applied to solve many problems in engineering, science, and economics. In computer science bio-inspired optimization has different applications in different domains such as software engineering, networks, data mining, and many others. However, some applications may not be appropriate or even correct. In this paper we study this phenomenon ...