Blar i Institutt for elektroniske systemer på tittel
Viser treff 470-489 av 2289
-
Decentralized Graph Federated Multitask Learning for Streaming Data
(Annual Conference on Information Sciences and Systems (CISS);56, Chapter, 2022)In federated learning (FL), multiple clients connected to a single server train a global model based on locally stored data without revealing their data to the server or other clients. Nonetheless, the current FL architecture ... -
Decentralized PMU-Assisted Power System State Estimation With Reduced Interarea Communication
(Journal article; Peer reviewed, 2018)This paper presents a decentralized approach to multiarea power system state estimation using a combination of conventional measurement devices and newer phasor measurement units (PMU). We employ a reduced-order approach ... -
Decision Algorithm for Parking Sensors
(Master thesis, 2020)Studier viser at opptil en tredjedel av all urbane overbelastning er forårsaket av sjåfører som leter etter et sted å parkere. Amerikanske sjåfører bruker gjennomsnittlig 17 timer i året på å søke etter gratis parkeringsplasser ... -
Decision Fusion for Carbon Dioxide Release Detection from Pressure Relief Devices
(Peer reviewed; Journal article, 2022)This work investigates the distributed detection of carbon dioxide (CO 2 ) release from storage tanks caused by the opening of pressure relief devices via inexpensive sensor devices in an industrial context. A realistic ... -
Deep Complex Convolutional Recurrent Network for Multi-Channel Speech Enhancement and Dereverberation
(Chapter, 2021)This paper proposes a neural network based system for multi-channel speech enhancement and dereverberation. Speech recorded indoors by a far field microphone, is invariably degraded by noise and reflections. Recent single ... -
Deep Learning based Classification of Cardiac Events in Echocardiography
(Master thesis, 2022)Abstract will be available on 2023-01-29 -
Deep Learning Based FPGA-CPU Acceleration
(Master thesis, 2019)Formålet med dette prosjektet er å fortsette å utforske nye måter å akselerere sequentialcomputer kode, og finne ut om maskinens læringsteknikker tilgjengelig i dag er i stand til å hjelpe oss med denne oppgaven. Kjerneideen ... -
Deep Learning Based People Estimation on 2D Ultra-Wideband Radar Data
(Master thesis, 2023)Denne masteroppgaven undersøker ytelsen til tre typer maskinlæringsmodeller, Convolutional Neural Network (CNN), Residual Network (ResNet), og Convolutional Neural Network med Gated Recurrent Units (CNN+GRU), i oppgaven ... -
Deep Learning Based Ultrasound Volume Registration for Interventional Applications
(Master thesis, 2020)Med den nylige utviklingen av ny teknologi kan minimalt invasive intervensjoner utføres med like gode utfall sammenlignet med konvensjonell åpen hjertekirurgi. Den økende aksepten for perkutane kateterbaserte intervensjoner ... -
Deep Learning for Deformation Analysis in Echocardiography
(Master thesis, 2021)Hjartesjukdom er ei av dei leiande dødsårsakene i verda. Tidleg deteksjon av risikofaktorar er avgjerande for effektiv og nøyaktig behandling. I dag blir undersøkingar av pasientar oftast utført ved hjelp av hjarte-ultralyd, ... -
Deep Learning for Polyp Detection from Synthetic Narrow-Band Imaging
(Master thesis, 2022)Kolorektal kreft (CRC) har blitt en utbredt krefttype i utviklide land, og screeningprogrammer har blitt populære på grunn av sin beviselig preventive effekt. Koloskopi er ansett som den beste screeningmetoden for CRC, og ... -
Deep Learning-Based Vehicle Classification for Low Quality Images
(Peer reviewed; Journal article, 2022)This study proposes a simple convolutional neural network (CNN)-based model for vehicle classification in low resolution surveillance images collected by a standard security camera installed distant from a traffic scene. ... -
Deep Neural Network Inference Acceleration: FPGA vs. GPU
(Master thesis, 2022)De siste årene har dype nevrale nettverk stadig blitt tatt mer i bruk i en stor variasjon av industrier, for å utnytte det store potensiale maskinlæringsteknologi tar med seg i form av effektivitet av databehandling. En ... -
Defect Pixel Correction
(Master thesis, 2010)A problem with image sensors today, is that they contain defect pixels. By utilizing an image processing algorithm for defect pixel correction, image quality can be increased and costs per produced sensor can be reduced.This ... -
Defective Pixel Correction
(Master thesis, 2010)When using CMOS technology for image sensors, there is a possibility that any givenpixel is defective and will thus produce a value that does not correlate to the amount oflight it was subject to. As such, the processing ... -
Delay-Fault BIST in Low-Power CMOS Devices
(Master thesis, 2008)Devices such as microcontrollers are often required to operate across a wide range of voltage and temperature. Delay variation in different temperature and voltage corners can be large, and for deep submicron geometries ... -
Delta Sigma Modulators with Beamformers for Application in Medical Ultrasound Imaging
(Doctoral theses at NTNU;2017:52, Doctoral thesis, 2017)Portable medical ultrasound solutions require a high degree of compactness and low power consumption, without sacrificing image quality. In this dissertation we investigate the feasibility of employing a continuous time ... -
Demonstration of Spatial Interweave Cognitive Radio
(Master thesis, 2010)In the last few decades the number of wireless communication systems has grown exponentially making the electromagnetic spectrum more and more crowded. One approach to solve the problem is through Cognitive Radio. This ... -
Demping av maskinstøy for mikrofon montert på utsiden av kjøretøy
(Master thesis, 2012)Målinger, analyse og filtrering av maskinstøy fra et militært kjøretøy, der hovedfokuset i oppgaven er å skape best mulige forhold for forståelse av tale. -
Density functional theory investigations of octahedral connectivity in [001] and [111] directional perovskite superlattices
(Master thesis, 2018)To be able to exploit the magnetic properties of antiferromagnetic transition metal oxide perovskites in spintronic devices, as magnetic random access memory (MRAM) devices, a better understanding of how these magnetic ...