This thesis explores the relationship between influence and memorization of training data in deep learning models. Influence metrics aim to quantify the impact of individual training examples on model predictions, while memorization scores assess how much specific data points are retained by the model. Understanding the connection between these two concepts is important for both interpretability and ...

Background: In Norway, there are estimated to be 250,000 people with type 2 diabetes. According to Folkehelseinstituttet, there are around 14,000 to 18,000 new diagnoses of type 2 diabetes every year in Norway. Type 2 diabetes is considered to be a lifestyle disease, and there are steps someone with type 2 diabetes can take to manage their condition, like changing their diet and exercise. Mobile ...

<p>Accurate left ventricular (LV) linear measurements are critical for cardiac function assessment in echocardiography. However, manual measurements are time-consuming and prone to variability due to anatomical complexity and operator dependency. While deep learning (DL) models have automated landmark detection, existing fully automated B-mode approaches often produce inaccurate predictions caused ...

<p>Healthcare-associated infections are of grave concern in healthcare facilities as these acquired infections pose a significant threat to the quality of life across the globe. Healthcare-associated infections are often related to the use of medical devices like catheters, joint prostheses, and implants. Medical devices are especially prone to bacterial growth, which can result in possible ...

<p>Rapid ongoing climate change includes warmer sea surface temperatures, salinity changes, reduced sea ice cover, and melting ice sheets in the polar regions. This has consequences for climate and society regionally and globally. However, there are large knowledge gaps regarding the sensitivity of these systems. Records of past changes in polar climate and ocean-cryosphere interactions can provide ...

Abstract Background – Norwegian health trusts face significant challenges translating complex regulatory requirements from GDPR, the Medical Devices Regulation, the AI Act, NIS2, and public procurement law into concrete technical specifications for AI procurement. Current "one-size-fits-all" templates and prescriptive specifications often stifle innovation, overlook algorithmic risks, and expose ...

This master’s thesis investigates how cybersecurity risks in the Norwegian agricultural sector influence national food security and self-sufficiency, and what strategies can be implemented to address these challenges. This study adopts a qualitative approach, relying on in-depth interviews with informants from three key groups in the agricultural value chain: farmers and producers, researchers and ...

Arctic sea ice plays a vital role in the climate system, influencing atmospheric circulation, oceanic processes, and Arctic ecosystems. Thin sea ice is particularly important, as it governs seasonal transitions and contributes to feedback mechanisms such as Arctic amplification. Reliable estimates of sea ice thickness (SIT), especially within the thin ice regimes (less than 1 m), are essential for ...

The increasing density of space debris poses a growing threat to satellite operations and future missions. While sub-millimeter debris is studied through impact craters and objects larger than 0.5 cm are tracked by ground-based radar, debris in the 1–3.2 mm range remains largely unmonitored. This thesis investigates the feasibility of using space-based techniques to estimate the flux of millimeter-scale ...

Denne studien undersøker hvordan dagens forebyggende tiltak mot ungdomskriminalitet fungerer i en norsk kontekst. Problemstillingen utforskes gjennom tre forskningsspørsmål som retter søkelyset mot sentrale aktører og deres strategier, hvordan forebygging praktiseres i hverdagen, og hvilke utfordringer som oppstår i det tverrsektorielle samarbeidet. Studien er avgrenset til en konkret delbydel som ...