English
norskInstitutt for informatikk
Bla i:
Enhetens samlinger
Nye registreringer
-
An individually adjusted approach for communicating epidemiological results on health and lifestyle to patients
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-02-08)If scientific research on modifiable risk factors was more accessible to the general population there is a potential to prevent disease and promote health. Mobile applications can automatically combine individual characteristics and statistical models of health to present scientific information as individually tailored visuals, and thus there is untapped potential in incorporating scientific ... -
Visual explanations for polyp detection: How medical doctors assess intrinsic versus extrinsic explanations
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-05-31)Deep learning has achieved immense success in computer vision and has the potential to help physicians analyze visual content for disease and other abnormalities. However, the current state of deep learning is very much a black box, making medical professionals skeptical about integrating these methods into clinical practice. Several methods have been proposed to shed some light on these black ... -
Performance Evaluation of Lightweight Stream Ciphers for Real-Time Video Feed Encryption on ARM Processor
(Journal article; Tidsskriftartikkel; Peer reviewed, 2024-07-25)In resource-intensive Internet of Things applications, Lightweight Stream Ciphers (LWSCs) play a vital role in influencing both the security and performance of the system. Numerous LWSCs have been proposed, each offering certain properties and trade-offs that carefully balance security and performance requirements. This paper presents a comprehensive evaluation of prominent LWSCs, with a focus on ... -
Integration of programming in Norwegian schools: The effects of prior programming experience on students in a university-level programming course
(Master thesis; Mastergradsoppgave, 2024-06-03)In 2020 a curriculum renewal in Norway integrated programming into multiple subjects at both elementary schools and upper secondary schools. This was done with the hopes of improving deep learning and introducing computational thinking to pupils attending the schools. Some criticism has been raised against the decision, with some declaring that this will hurt deep learning and that programming is ... -
AquaTrace: Secure Federated Identifiers for Product Tracing using Blockchain
(Master thesis; Mastergradsoppgave, 2024-05-31)This thesis proposes a secure and resilient system for generating and managing unique identification number series for tracing food products within the Norwegian fishing industry, without relying on a central authority. Given the context of mutual mistrust among stakeholders and the threat of hostile entities, this project proposes a blockchain-based solution to ensure the uniqueness and security ... -
AI Chatbots in Health: Implementing an LLM-Based Solution to Promote Physical Activity
(Mastergradsoppgave; Master thesis, 2024-06-16)With the emergence of powerful generative AI models comes the possibility of creating knowledgeable and engaging chatbots, which have the potential to significantly enhance several areas of the user’s life. This thesis focuses on the design and implementation of FysBot, an application with an integrated chatbot that aims to increase the user’s physical activity levels. In collaboration with a PhD ... -
Evaluating Continuous End-to-End Communication at Sea with Multi-Hop MANET Routing, Using AIS Data
(Mastergradsoppgave; Master thesis, 2024-06-03)The marine sector has unique and challenging problems supporting high bandwidth, low-latency internet connectivity, often unavailable or only avail able through satellite services. Multi-hop manets that utilise low-cost com modity hardware potentially offer a cost-effective solution compared to satellite services but come with their own limitations. This thesis is motivated by the need for reliable ... -
Haddock: A Smart-Contract Command Bus for the Fishing Industry
(Mastergradsoppgave; Master thesis, 2024-06-02)The global fishing industry, a critical food source, faces significant challenges due to criminal activities such as illegal fishing and over-exploitation. Traditional surveillance methods can be susceptible to tampering and cannot fully ensure the integrity of recorded events. This thesis introduces Haddock, a shared, distributed logging system leveraging a two-phase dissemination protocol and the ... -
Fault-Tolerant Distributed Declarative Programs
(Mastergradsoppgave; Master thesis, 2024-06-02)In our increasingly interconnected digital landscape, the constant generation and consumption of data on various computing devices present challenges for ensuring constant accessibility, particularly in intermittent network scenarios. The emerging focus on distributed systems is aimed at not only managing substantial data volumes but also guaranteeing storage on devices for low latency and high ... -
A Data Gathering System for the Arctic Tundra
(Mastergradsoppgave; Master thesis, 2024-06-02)Climate change has emerged as an important topic over the past decade, and one of the areas most susceptible to change is the Arctic Tundra. Monitoring the environment features a variety of challenges; it’s remote location, manual monitoring equipment and required permission to depart on expeditions. A solution to this is the use of a wireless sensor network to allow more automatic gathering ... -
Predicting the Destination Port of Fishing Vessels
(Mastergradsoppgave; Master thesis, 2024-06-02)Regulating the catch of fishing vessels is crucial for maintaining sustainable fish populations, preventing illegal fishing, and ensuring the quality of the fish being delivered. One effective method of controlling the catch is to have controllers physically present at the port where the catch is being delivered. However, vessels do not always report their destination port in a timely manner, which ... -
Large Language Models for Managing Online Fingerprint
(Mastergradsoppgave; Master thesis, 2024-06-01)Today, many are unaware of how much of their personal information is publicly available on the web, which has become an increasingly important issue among internet users. This thesis builds on the work of the preceding Capstone project and uses the open-source Online Privacy Pilot tool as a case study to explore how large language models can be incorporated into the tool to enhance its functionality ... -
Variable Dependency Graph Summarization
(Mastergradsoppgave; Master thesis, 2024-05-31)In personalized software, collected user data is used to give a tailored user experience. A user might be interested in understanding how their data (inputs) resulted in their personalized output. The Variable Dependency Graph (VDG) can explain how inputs of a program flow to the output. However, with increasing program size, there is a need for summarizing the VDGs and understanding these ... -
A before B: Investigations into how best to perform Temporal Health Queries
(Mastergradsoppgave; Master thesis, 2024-05-15)Querying and exploring health data can lead to the discovery of new rela- tions between conditions, medications, hospital events, etc. For this purpose, temporal health queries are useful since the order in which events happen is important. Many of the querying tools available do not address the unique needs of temporal health queries, making these queries difficult and time-consuming to ... -
Integrating and Validating Heart Health Calculators in Medical Platforms
(Mastergradsoppgave; Master thesis, 2024-05-15)We believe the underutilization of clinically validated algorithms for heart health assessment in current medical platforms undermines patient confidence in using associated screening instruments. The importance of earlier detection and improved health outcomes in heart disease motivated the development of these screening instruments. Available risk assessment tools are stand-alone online apps or ... -
Reducing Memory Overhead in CRDT for Collaborative Editing
(Mastergradsoppgave; Master thesis, 2024-05-12)For peer-to-peer collaborative editing systems utilizing the Conflict-free Replicated Data Type memory consumption can become a significant issue, particularly when handling large files with extensive editing histories. It can lead to performance problems and hinder user productivity, especially in environments with limited resources. This thesis addresses the problem of excessive memory usage and ... -
Label Propagation in Machine Learning Systems: Providing End-to-End Traceability with Explainable Artificial Intelligence
(Mastergradsoppgave; Master thesis, 2024-05-15)Artificial Intelligence (AI) and the underlying Machine Learning (ML) technology is experiencing increased applications in various areas. The training of ML models requires significant amounts of data, and data might contain restrictions regarding their permitted usage. High-performant models are often called black-boxes because of their complex decision-making process. Thus, ML applications threaten ... -
Bootstrapping the Integrity of Sensor Data Labels at the Microcontroller Level Using Physically Unclonable Functions: Addressing Physical Vulnerabilities in the IoT Domain
(Mastergradsoppgave; Master thesis, 2024-05-15)Modern decision-making processes across industries today increasingly rely on data-driven insights derived from various sources. As smart devices, sensor tech- nology, and the IoT (Internet of Things) evolve, organizations are progressively leveraging these technologies for data-driven decision-making. However, with the introduction of regulations such as the General Data Protection Regulation (GDPR) ... -
Training and Model Parameters to Defend against Tabular Leakage Attacks
(Mastergradsoppgave; Master thesis, 2024-05-15)Federated Learning (FL) is a privacy-preserving approach to train machine learning models on distributed datasets across different organizations. This is particularly beneficial for domains like healthcare and finance, where user data is often sensitive and tabular (e.g., hospital records and financial transactions). However, recent research like Tableak highlighted vulnerabilities that can exploit ... -
Configuring edge device provenance through messaging middleware
(Master thesis; Mastergradsoppgave, 2024-05-15)Integrity of data is important in today as more of societies structure today are distributed and becomes vulnerable to dishonest entities on their edge devices. Using provenance to prove integrity over edge devices and distributed networks is difficult, as it often produces big amounts of data which fills up storage without having a need to be used. Comm2Prov seeks to fix this by combining the ...
RSS 1.0