English
norskBlar i tittel Artikler, rapporter og annet (fysikk og teknologi)
Viser treff 904-923 av 942
-
Unsupervised domain adaptation for automatic estimation of cardiothoracic ratio
(Journal article; Tidsskriftartikkel; Peer reviewed, 2018-09-26)The cardiothoracic ratio (CTR), a clinical metric of heart size in chest X-rays (CXRs), is a key indicator of cardiomegaly. Manual measurement of CTR is time-consuming and can be affected by human subjectivity, making it desirable to design computer-aided systems that assist clinicians in the diagnosis process. Automatic CTR estimation through chest organ segmentation, however, requires large amounts ... -
Unsupervised Estimation of the Equivalent Number of Looks in PolSAR Image with High Heterogeneity
(Journal article; Tidsskriftartikkel; Peer reviewed, 2017-03-01)Equivalent Number of Looks (ENL) is an important parameter in statistical modelling of multi-look Polarimetric SAR (PolSAR) data. In some automated applications of PolSAR images, it is necessary to estimate the ENL in an unsupervised way without any manual intervention. The existing unsupervised estimation of ENL can not obtain accurate estimates for the images with high heterogeneity. To address ... -
Unsupervised Feature Extraction – A CNN-Based Approach
(Peer reviewed; Book; Chapter, 2019-05-12)Working with large quantities of digital images can often lead to prohibitive computational challenges due to their massive number of pixels and high dimensionality. The extraction of compressed vectorial representations from images is therefore a task of vital importance in the field of computer vision. In this paper, we propose a new architecture for extracting such features from images in an ... -
Unsupervised Image Regression for Heterogeneous Change Detection
(Journal article; Tidsskriftartikkel; Peer reviewed, 2019-08-14)Change detection (CD) in heterogeneous multitemporal satellite images is an emerging and challenging topic in remote sensing. In particular, one of the main challenges is to tackle the problem in an unsupervised manner. In this paper, we propose an unsupervised framework for bitemporal heterogeneous CD based on the comparison of affinity matrices and image regression. First, our method quantifies ... -
An unsupervised method for equivalent number of looks estimation in complex SAR scenes
(Journal article; Tidsskriftartikkel; Peer reviewed, 2015-11-12)This paper introduces a novel unsupervised estimator of equivalent number of looks (ENL) that can be applied to an arbitrary image. It avoids the assumption that homogeneous speckle will dominate the investigated image that is followed by current unsupervised ENL estimators but not always valid, especially for the complex SAR scenes with high mixture and texture. Incorporating the statistical ... -
Unsupervised Mixture-Eliminating Estimation of Equivalent Number of Looks for PolSAR Data
(Journal article; Tidsskriftartikkel; Peer reviewed, 2017-08-22)This paper addresses the impact of mixtures between classes on equivalent number of looks (ENL) estimation. We propose an unsupervised ENL estimator for polarimetric synthetic aperture radar (PolSAR) data, which is based on small sample estimates but incorporates a mixture-eliminating (ME) procedure to automatically assess the uniformity of the estimation windows. A statistical feature derived from ... -
Unsupervised supervoxel-based lung tumor segmentation across patient scans in hybrid PET/MRI
(Journal article; Tidsskriftartikkel; Peer reviewed, 2020-11-29)Tumor segmentation is a crucial but difficult task in treatment planning and follow-up of cancerous patients. The challenge of automating the tumor segmentation has recently received a lot of attention, but the potential of utilizing hybrid positron emission tomography (PET)/magnetic resonance imaging (MRI), a novel and promising imaging modality in oncology, is still under-explored. Recent ... -
Uptake and Degradation of Bacteriophages by Liver Sinusoidal Endothelial Cells
(Conference object; Konferansebidrag, 2018)<p>Bacteriophages (briefly, “phages”) are viruses which target bacteria, and are non-infectious to eukaryotic cells. It is estimated that more than 30 billion phages cross into the human body from the gut each day1, and eventually need to be cleared from the blood circulation. The liver plays a central role in pathogen clearance, and liver sinusoidal endothelial cells (LSECs), which form the lining ... -
Urban land cover classification with missing data modalities using deep convolutional neural networks
(Journal article; Tidsskriftartikkel; Peer reviewed, 2018-06-14)Automatic urban land cover classification is a fundamental problem in remote sensing, e.g., for environmental monitoring. The problem is highly challenging, as classes generally have high interclass and low intraclass variances. Techniques to improve urban land cover classification performance in remote sensing include fusion of data from different sensors with different data modalities. However, ... -
USE OF EISCAT 3D FOR OBSERVATIONS OF SPACE DEBRIS
(Conference object; Konferansebidrag, 2017-06)We investigate the capabilities of the next generation ionospheric research radar EISCAT 3D (E3D) for observations of space objects. The radar is multi-static, and is therefore capable of observing instantaneous threedimensional vector velocity and position by observing round-trip delay and Doppler shift between the transmitter and three receiver sites. The radar is to be located in Northern ... -
Using a large open clinical corpus for improved ICD-10 diagnosis coding
(Journal article; Tidsskriftartikkel, 2023)With the recent advances in natural language processing and deep learning, the development of tools that can assist medical coders in ICD-10 diagnosis coding and increase their efficiency in coding discharges ummaries is significantly more viable than before. To that end, one important component in the development of these models is the datasets used to train them. In this study, such datasets are ... -
Using anchors from free text in electronic health records to diagnose postoperative delirium
(Journal article; Tidsskriftartikkel; Peer reviewed, 2017-09-19)Objectives:<br> Postoperative delirium is a common complication after major surgery among the elderly. Despite its potentially serious consequences, the complication often goes undetected and undiagnosed. In order to provide diagnosis support one could potentially exploit the information hidden in free text documents from electronic health records usin ... -
Using radar beam-parks to characterize the Kosmos-1408 fragmentation event
(Journal article; Tidsskriftartikkel; Peer reviewed, 2022-10-22)We describe the use of radar beam-park experiments to characterize the space debris resulting from a recent fragmentation event, the deliberate demolition of the defunct Kosmos-1408 satellite. We identify the Kosmos-1408 fragments and present distribution of measurement parameters as well as proxy orbit parameters. We present and apply a novel technique to estimate the size of objects by matching ... -
Using Silver Nano-Particle Ink in Electrode Fabrication of High Frequency Copolymer Ultrasonic Transducers: Modeling and Experimental Investigation
(Journal article; Tidsskriftartikkel; Peer reviewed, 2015-04-20)High frequency polymer-based ultrasonic transducers are produced with electrodes thicknesses typical for printed electrodes obtained from silver (Ag) nano-particle inks. An analytical three-port network is used to study the acoustic effects imposed by a thick electrode in a typical layered transducer configuration. Results from the network model are compared to experimental findings for the implemented ... -
Validation of Multistatic Meteor Radar Analysis Using Modeled Mesospheric Dynamics: An Assessment of the Reliability of Gradients and Vertical Velocities
(Journal article; Tidsskriftartikkel; Peer reviewed, 2022-02-28)A virtual meteor radar system based on the upper-atmosphere extension of the high-resolution ICOsahedral Non-hydrostatic general circulation model is constructed to validate multistatic specular meteor radar (SMR) analyses. The virtual radar system examines the validity of mean winds and gradients estimation techniques used in multistatic SMRs. The study is motivated by unexpected mean values and ... -
Validation of SAR Iceberg Detection with Ground-Based Radar and GPS Measurements
(Peer reviewed; Chapter; Bokkapittel, 2018-11-05)Calving of icebergs at the tidewater glacier fronts is a component of the mass loss in Polar regions. Studying the regional distribution of icebergs, their volume, motion, and interaction with the environment is of interest. Here, we present the results from a fieldwork campaign conducted in Kongsfjorden, Svalbard in April 2016, where both satellite and ground-based remote sensing instruments were ... -
Velocity distribution of Gold nanoparticles trapped on an optical waveguide
(Journal article; Tidsskriftartikkel; Peer reviewed, 2005) -
Velocity scaling for filament motion in scrape-off layer plasmas
(Journal article; Tidsskriftartikkel; Peer reviewed, 2011) -
Video trajectory analysis using unsupervised clustering and multi-criteria ranking
(Journal article; Tidsskriftartikkel; Peer reviewed, 2020-05-13)Surveillance camera usage has increased significantly for visual surveillance. Manual analysis of large video data recorded by cameras may not be feasible on a larger scale. In various applications, deep learning-guided supervised systems are used to track and identify unusual patterns. However, such systems depend on learning which may not be possible. Unsupervised methods relay on suitable features ... -
View it like a radiologist: Shifted windows for deep learning augmentation of CT images
(Journal article; Tidsskriftartikkel; Peer reviewed, 2023-10-23)Deep learning has the potential to revolutionize medical practice by automating and performing important tasks like detecting and delineating the size and locations of cancers in medical images. However, most deep learning models rely on augmentation techniques that treat medical images as natural images. For contrast-enhanced Computed Tomography (CT) images in particular, the signals producing the ...
