Blar i Institutt for datateknologi og informatikk på tittel
Viser treff 4129-4148 av 6569
-
Multi-feature-based crowd video modeling for visual event detection
(Peer reviewed; Journal article, 2020)We propose a novel method for modeling crowd video dynamics by adopting a two-stream convolutional architecture which incorporates spatial and temporal networks. Our proposed method cope with the key challenge of capturing ... -
Multi-Formalism Modelling of a Submarine Combat System Test Facility: an Application of DEVS
(Master thesis, 2006)This thesis aims at applying and exploring the DEVS-based theory for the purpose of gaining experiences and recommendations with regards to the usefulness of DEVS in the analysis of a submarine combat system and in ... -
Multi-GPU Maximum Flow Using the Groute Framework
(Master thesis, 2020)Maks flyt problemet er et kjerneproblem innen grafteori og algoritmer for å løse problemet har utviklet seg siden Ford og Fulkerson publiserte sin løsning i 1956. Dette problemet dukker opp i forskjellige flytproblemer i ... -
Multi-GPU sliding tile puzzle solving with GA*, Groute and Abstract Zobrist Hashing
(Master thesis, 2018)The A* algorithm has been a key search algorithm and part of AI literature for a long time. It has applications in computational biology, natural lan- guage processing, pathfinding, puzzle solving, and more. The complexity ... -
Multi-image detection and tracking of cracks in ship tanks
(Master thesis, 2021)Denne masteroppgaven omhandler bruk av romlig-temporal informasjon som er tilgjengelig i enkeltbildene til en video, for å forbedre sprekkdeteksjon i skipstanker. Hovedideen er å bevegelses-kompensere tidligere bilder til ... -
Multi-Instrument Automatic Music Transcription with Deep Learning
(Master thesis, 2021)Automatisk transkribering av musikk går ut på å bruke datamaskiner til å transformere lydfiler til en symbolsk representasjon, som MIDI-filer («Musical Instrument Digital Interface») eller noter. Denne oppgaven er den ... -
Multi-label classification of a real-world image dataset
(Master thesis, 2017)Deep neural networks have shown increasing performance in image classification recent years. However, most of the methods developed in research are created, trained and compared on standard, general image collections. While ... -
Multi-label image classification with language-image models: an approach for a fine-grained domain-specific dataset
(Master thesis, 2022)Nylige framskritt innen selvveiledede bildemodeller (self-supervised pre-trained image models) har gjort det mulig å bygge gode modeller for oppgavespesifikk (task-specific) bildeklassifisering lettere og med mindre ... -
Multi-level contrast filtering in image difference metrics
(Journal article; Peer reviewed, 2013)In this paper, we present a new metric to estimate the perceived difference in contrast between an original image and a reproduction. This metric, named weighted-level framework Δ E E (WLF-DEE), implements a multilevel ... -
Multi-level grounding and self-organization of behaviour through evolution, development, learning and culture
(Doktoravhandlinger ved NTNU, 1503-8181; 2005:43, Doctoral thesis, 2005)The research topic of this PhD concerns the production of intelligent adaptive behaviour from the embodied perspective. The intelligence seen in biological organisms arises as an emergent property of a complex system ... -
Multi-modal Bayesian knowledge tracing
(Master thesis, 2022)I dette forskningsprosjektet sammenlignes Bayesian knowledge tracing (BKT) med en ny versjon av algoritmen, hvor innsikt fra multi-modal data (MMD) om studenters kognitive, affektive og atferdsmessige tilstander benyttes. ... -
Multi-modal Bayesian knowledge tracing
(Master thesis, 2022)I dette forskningsprosjektet sammenlignes Bayesian knowledge tracing (BKT) med en ny versjon av algoritmen, hvor innsikt fra multi-modal data (MMD) om studenters kognitive, affektive og atferdsmessige tilstander benyttes. ... -
Multi-modality quality assessment for unconstrained biometric samples
(Doctoral theses at NTNU;2018:171, Doctoral thesis, 2018)The aim of this research is to investigate multi-modality biometric image quality assessment methods for unconstrained samples. Studies of biometrics noted the significance of sample quality for a recognition system or a ... -
Multi-Objective Animal Migration Optimization - A Metaheuristic Optimization Algorithm
(Master thesis, 2018)Metaheuristic optimization has received a lot of attention over the last couple of decades. Some optimization problems are just too computationally heavy to solve with traditional search techniques, especially when there ... -
Multi-objective Discrete Quantum PSO for dynamic environments
(Master thesis, 2020)Dynamiske miljøer og flere objektiver er gjentagende problemer i den virkelige verden. Det er ikke gjort grundig forskning på en kombinasjon av disse problemene. I oppgaven blir det lagt frem en modell som kombinerer den ... -
Multi-objective Discrete Quantum PSO for dynamic environments
(Master thesis, 2020)Dynamiske miljøer og flere objektiver er gjentagende problemer i den virkelige verden. Det er ikke gjort grundig forskning på en kombinasjon av disse problemene. I oppgaven blir det lagt frem en modell som kombinerer den ... -
Multi-objective Genetic Algorithm for Engineering Design Optimization
(Master thesis, 2020)Denne rapporten utforsker hvordan evolusjonær databehandling metoder blir brukt for strukturell optimalisering, med et fokus på bruk av genetiske algoritmer til design av jacketer. Jacketer er fagverksplattformer bygget i ... -
A Multi-Objective Genetic Algorithm for Jacket Optimization
(Chapter, 2021)In this paper, we describe underlying concepts related to the problem of jacket design as well as previous research on jacket design optimization. Motivated by the complexity of the problem, including the multiple objectives ... -
Multi-Objective Neuroevolution in Super Mario Bros.
(Master thesis, 2013)This thesis explores how to use Multi-Objective Evolutionary Algorithms (MOEA)to solve problems that are not explicitly defined as multi-objective problems. Aneuroevolution technique consisting of combining a multi-objective ... -
Multi-Parameter Performance Modeling Based on Machine Learning with Basic Block Features
(Chapter, 2020)Considering the increasing complexity and scale of HPC architecture and software, the performance modeling of parallel applications on large-scale HPC platforms has become increasingly important. It plays an important role ...