Browsing NTNU Open by Author "Mengshoel, Ole Jakob"
Now showing items 1-20 of 43
-
Adaptive Stress Testing for Safety Validation of Maritime Autonomous Collision Avoidance Systems
Vatle, Jan-Marius (Master thesis, 2022)Forskningen innen maritime autonome fartøy har økt i løpet av det siste tiåret. I sammenheng med dette, utvikler et selskap kalt Zeabuz et autonomt fergesystem og ønsker å utføre "state-of-the-art" sikkerhetsvalidering av ... -
Adaptive Stress Testing: Finding Likely Failure Events with Reinforcement Learning
Lee, Ritchie; Mengshoel, Ole Jakob; Saksena, Anshu; Gardner, Ryan; Genin, Daniel; Silbermann, Joshua; Owen, Michael; Kochenderfer, Mykel J. (Peer reviewed; Journal article, 2020)Finding the most likely path to a set of failure states is important to the analysis of safety-critical systems that operate over a sequence of time steps, such as aircraft collision avoidance systems and autonomous cars. ... -
Ambulance Allocation Optimization and Simulation with Incident Urgency and Demand Prediction
Mohn, Erik (Master thesis, 2023)Mange hendelser som krever assistanse fra medisinsk personell er tidskritiske. Det er derfor nødvendig at utrykningskjøretøy når frem til hendelsesstedet så raskt som mulig for å gi pasienten den behandlingen de trenger. ... -
Anomaly detection for industrial time series
Einang, Embrik Tvenge; Rønning, Alfred Sollie (Master thesis, 2020)Karbonanoder er en avgjørende komponent i elektrolyseprosessen for aluminiumsproduksjon. Overvåkning av strømtilførselen gjennom hengeren karbonanoden er festet på gjør det mulig for operatører å spore og kontrollere ... -
Automatic Topic Generation for Broadcasters: Usable Metadata from Topic Models on Systematically Preprocessed TV Subtitles
Rushfeldt, Magnus Reier (Master thesis, 2022)Hos Norsk Rikskringkasting (NRK), fører økende digitalisering og endringer i hvordan folk leser nyheter, ser på TV og hører på radio på til nye utfordringer. Skattebetalende innbyggere i Norge (og dermed «kunder» av NRKs ... -
Bayesian Feature Construction for Case-Based Reasoning: Generating Good Checklists
Flogard, Eirik Lund; Mengshoel, Ole Jakob; Bach, Kerstin (Chapter, 2021)Checklists are used to aid the fulfillment of safety critical activities in a variety of different applications, such as aviation, health care or labour inspections. However, optimizing a checklist for a specific purpose ... -
Creating Dynamic Checklists via Bayesian Case-Based Reasoning: Towards Decent Working Conditions for All
Flogard, Eirik Lund; Mengshoel, Ole Jakob; Bach, Kerstin (Peer reviewed; Journal article, 2022)Every year there are 1.9 million deaths world-wide attributed to occupational health and safety risk factors. To address poor working conditions and fulfill UN's SDG 8, "protect labour rights and promote safe working ... -
Creating Explainable Dynamic Checklists via Machine Learning to Ensure Decent Working Environment for All: A Field Study with Labour Inspections
Flogard, Eirik Lund; Mengshoel, Ole Jakob; Theisen, Ole Magnus; Bach, Kerstin (Chapter, 2023)To address poor working conditions and promote United Nations’ sustainable development goal 8.8, “protect labour rights and promote safe working environments for all workers [...]”, government agencies around the world ... -
A Dataset for Efforts Towards Achieving the Sustainable Development Goal of Safe Working Environments
Flogard, Eirik Lund; Mengshoel, Ole Jakob (Peer reviewed; Journal article, 2022)Among United Nations' 17 Sustainable Development Goals (SDGs), we highlight SDG 8 on Decent Work and Economic Growth. Specifically, we consider how to achieve subgoal 8.8, "protect labour rights and promote safe working ... -
Deep Neural Network Architectures for Detection and Segmentation of Solar Farms in Satellite Imagery
Olweus, Erling (Master thesis, 2023)In response to the urgent global call for renewable energy alternatives, as dictated by the Paris Agreement, there is an increasing need to accurately map and monitor the growth of solar farms around the world. A critical ... -
Deep Reinforcement Learning for Supporting Ambulance Dispatch Decisions
Moen, Jon Elias (Master thesis, 2023)Denne master avhandlingen utforsker bruken av forsterkningslæring og \acrfull{ppo} til ambulanseutsendelse-problemet, som et mulig beslutningsstøtteverktøy for Akutt medisin sentralen (AMK) i Oslo og Akershus, Oslo ... -
EvoLP.jl: A Playground for Evolutionary Computation in Julia
Sánchez-Diaz, Xavier F. C.; Mengshoel, Ole Jakob (Peer reviewed; Journal article, 2023)Optimisation is highly relevant in many problems in artificial intelligence, machine learning, engineering and statistics. In these situations, optimisation by means of evolutionary computation becomes especially relevant ... -
Evolutionary algorithms for generating interesting fighting game character mechanics
Skjærseth, Eirik H.; Vinje, Harald (Master thesis, 2020)Abstract: Procedural content generation (PCG) is the process of generating video game content through algorithms and has been used in the game industry for a long time. "Content" refers to elements in a game such as levels, ... -
Evolutionary algorithms for generating interesting fighting game character mechanics
Skjærseth, Eirik H.; Vinje, Harald (Master thesis, 2020)Prosesuell generering (Procedural Content Generation, PCG på engelsk) er en metode brukt i spillutvikling for å generere spillinnhold ved bruk av algoritmer fremfor menneskelig arbeid. Spillinnhold er elementer som for ... -
Evolutionary algorithms for generating interesting fighting game character mechanics
Skjærseth, Eirik H.; Vinje, Harald (Master thesis, 2020)Prosesuell generering (Procedural Content Generation, PCG på engelsk) er en metode brukt i spillutvikling for å generere spillinnhold ved bruk av algoritmer fremfor menneskelig arbeid. Spillinnhold er elementer som for ... -
Evolutionary Computation with Islands: Extending EvoLP.jl for Parallel Computing
Sánchez Diaz, Xavier Fernando Cuauhtémoc; Mengshoel, Ole Jakob (Peer reviewed; Journal article, 2023)The use of evolutionary computation for optimisation is a relevant area of research in many fields of science and the industry, where complex problems are frequently encountered. As an effort to support the research in ... -
Evolving video game opponents with NEAT and evaluating its impact on brain activity with fMRI
Tveiten, Kristian; Hallan, Martin Sondov (Master thesis, 2023)Neuroevolusjon, spesielt Neuroevolution of Augmenting Topologies (NEAT), har lovende potensial innen videospill for utvikling av dynamiske og engasjerende kunstige motstandere. Dens innvirkning på spill-opplevelsen ble ... -
Exploring data assignment schemes when training deep neural networks using data parallelism
Håland, André; Birkeland, Bjørnar (Master thesis, 2020)Den stadig økende størrelsen på datasett har gjort det mulig for dype nevrale nettverk å utføre mange vanskelige oppgaver. Samtidig har enda større modeller vist seg å forbedre ytelsen til dype nevrale nettverk. Derimot ... -
Exploring data assignment schemes when training deep neural networks using data parallelism
Håland, André; Birkeland, Bjørnar (Master thesis, 2020)Den stadig økende størrelsen på datasett har gjort det mulig for dype nevrale nettverk å utføre mange vanskelige oppgaver. Samtidig har enda større modeller vist seg å forbedre ytelsen til dype nevrale nettverk. Derimot ... -
Forecasting Ambulance Demand in Oslo and Akershus
Van De Weijer, Erling; Owren, Odd André (Master thesis, 2022)Evnen til å forutsi ambulanseetterspørsel er et kritisk verktøy innen akuttmedisin for å kunne fordele ressursene så effektivt som mulig. I denne oppgaven benytter vi et datasett gitt av Oslo Universitetssykehus for å ...