Institutt for datateknologi og informatikk
Recent Submissions
-
A Way to Lay Out Argument Maps
(Master thesis, 2023)Forfatteren har gjennomført et masterprosjekt i samarbeid med Disputas AS, en norsk oppstartsbedrift som spesialiserer seg innen visualisering av uformell logikk. Målet med prosjektet var å utvikle en graflayoutalgoritme ... -
KNITTIR - Semantic Text Indexing
(Master thesis, 2023)Med den økende mengden data tilgjengelig gjennom nettet, står brukere overfor ut- fordringen med å utføre analytiske oppgaver på tekst. Dette inkluderer å trekke ut lignende tekstområder med relevant informasjon, samt ... -
Predicting Personality in Job Interviews By leveraging Emotion Recognition from Multi-Modal Sentiment Analysis Models
(Master thesis, 2023)Den økende bruken av digitale intervjuer i ansettelsesprosessen har akselerert forskning på metoder som kan forbedre deres effektivitet. Rekrutterere benytter seg av AI-metoder for å få en dypere forståelse av kandidater ... -
MARF: The Medial Atom Ray Field object representation
(Peer reviewed; Journal article, 2023)We propose Medial Atom Ray Fields (MARFs), a novel neural object representation that enables accurate differentiable surface rendering with a single network evaluation per camera ray. Existing neural ray fields struggle ... -
Registration techniques for navigation in laparascopic surgery
(Doctoral theses at NTNU;2023:411, Doctoral thesis, 2023)In minimally invasive surgery, where a direct sight of the treated organ or structures is not feasible but with a laparoscope, image guided systems have been developed to provide the surgeon with real time information of ... -
Beyond Traditional Boundaries: Exploiting Open Dimensions for Enhancing Fake News Detection with Artificial Immune Systems
(Master thesis, 2023)I den digitale revolusjonens tidsalder har den raske spredningen av informasjon, spesielt falske nyheter, skapt betydelige utfordringer. Nesten halvparten av voksne i USA brukte sosiale medier som kilde for nyheter i 2021, ... -
Enabling data-driven decision support in healthcare
(Doctoral theses at NTNU;2023:448, Doctoral thesis, 2023)Healthcare professionals make decisions every day. These decisions can have a profound impact on those they concern, such as a decision on how to treat a patient. Patients and their families can experience prolonged illness ... -
Concept-based reasoning in medical imaging
(Peer reviewed; Journal article, 2023)Purpose As concept-based reasoning for improving model interpretability becomes promising, the question of how to define good concepts becomes more pertinent. In domains like medical, it is not always feasible to access ... -
Topic Modeling With Text and Images Using Pretrained Embeddings
(Master thesis, 2023)Mengden data som blir skapt er økende, og det å finne nye måter å analysere denne dataen blir stadig et viktigere problem. Videre kan denne dataen fremkomme med flere modaliteter, som tekst og bilde. Et forskningsområde ... -
Reflectance Imaging spectroscopy: Fusion of VNIR and SWIR for Cultural Heritage Analysis
(Doctoral theses at NTNU;2023:423, Doctoral thesis, 2023)Reflectance Imaging Spectroscopy, often referred to as hyperspectral imaging, is an imaging technique that enables the simultaneous capture of spatial and spectral information from a scene without physical contact and in ... -
Image Quality Assessment of Hyperspectral and Conventional Imaging for Cultural Heritage Artifacts
(Doctoral theses at NTNU;2023:356, Doctoral thesis, 2023)Preserving historical artifacts is crucial as they carry cultural significance beyond their artistic value and offer insight into their creation for future generations. Digitalization of cultural heritage artifacts preserves ... -
The Personality of Depression - Utilizing Big Five Personality Traits to Detect Depression on Social Media
(Master thesis, 2023)Omtrent 5% av den voksne befolkningen lider av depresjon, noe som gjør den psykiske lidelsen til en ledende bidragsyter til den totale sykdomsbyrden i verden. Selv om effektiv behandling finnes, får mindre en 25% av folk ... -
Autonomous Vehicles: 3D Object Detection Using Dual Sensor Input of LiDAR Point Clouds and 3-channel LiDAR Images
(Master thesis, 2023)Autonome kjøretøy har vært en futuristisk visjon som folk har drømt om i flere tiår. De siste årene har det blitt gjort enorme fremskritt mot autonomi med introduksjonen av konvolusjonsnettverk og transformere i kombinasjon ... -
A Study of Transformers for Cross-Corpus Native Language Identification
(Master thesis, 2023)Førstespråksidentifisering har som mål å finne en persons førstespråk basert på noe de har kommunisert på sitt andrespråk. Dette er et fagfelt som først ble etablert i 2005, og har siden da vært et tema på en rekke ... -
NUBA: Non-Uniform Bandwidth GPUs
(Chapter, 2023)The parallel execution model of GPUs enables scaling to hundreds of thousands of threads, which is a key capability that many modern high-performance applications exploit. GPU vendors are hence increasing the compute and ... -
Variance-Based Exploration for Learning Model Predictive Control
(Peer reviewed; Journal article, 2023)The combination of model predictive control (MPC) and learning methods has been gaining increasing attention as a tool to control systems that may be difficult to model. Using MPC as a function approximator in reinforcement ... -
The Potential of Generative Artificial Intelligence Across Disciplines: Perspectives and Future Directions
(Peer reviewed; Journal article, 2023)In a short span of time since its introduction, generative artificial intelligence (AI) has garnered much interest at both personal and organizational levels. This is because of its potential to cause drastic and widespread ... -
Uncovering the dark side of AI-based decision-making: A case study in a B2B context
(Peer reviewed; Journal article, 2023)Over the last decade, many organizations worldwide have been assimilating Artificial Intelligence (AI) technologies to increase their productivity and attain a competitive advantage. As with any technology, intelligence ... -
A framework for software vendor selection by applying Inconsistency and Conflict Removal (ICR) method
(Peer reviewed; Journal article, 2023)In a software ecosystem, companies’ stakeholders make various decisions and perform various tasks to ensure the strategic and architectural goals of the company. Analyzing vendor capabilities and making decisions to select ...