Browsing NR vitenarkiv by Document Types "Chapter"
Now showing items 21-39 of 39
-
Large-Scale Vegetation Height Mapping from Sentinel Data Using Deep Learning
(Chapter, 2020)The deep learning revolution in computer vision has enabled a potential for creating new value chains for Earth observation that significantly enhances the analysis of satellite data for tasks like land cover mapping, ... -
The Link between Inclusive Design and Innovation: Some Key Elements
(Chapter, 2013)It is often said that universal design and similar approaches can be a source of innovation. In this paper key elements in inclusive design are identified, and examples of innovations related to inclusive design are ... -
The Multi-Color Contrast Checker (M3C)
(Chapter, 2023)Accessible and readable contrast of text and graphical elements is a key requirement of the universal design of digital interfaces for people with and without disabilities. Many manual and automatic tools have been developed ... -
Multi-View Self-Constructing Graph Convolutional Networks With Adaptive Class Weighting Loss for Semantic Segmentation
(Chapter, 2020)We propose a novel architecture called the Multi-view Self-Constructing Graph Convolutional Networks (MSCG-Net) for semantic segmentation. Building on the recently proposed Self-Constructing Graph (SCG) module, which makes ... -
Named Entity Recognition without Labelled Data: A Weak Supervision Approach
(Chapter, 2020)Named Entity Recognition (NER) performance often degrades rapidly when applied to target domains that differ from the texts observed during training. When in-domain labelled data is available, transfer learning techniques ... -
Privacy-preserving greater-than integer comparison without binary decomposition
(Chapter, 2020)Common for the overwhelming majority of privacy-preserving greater-than integer comparison schemes is that cryptographic computations are conducted in a bitwise manner. To ensure secrecy, each bit must be encoded in such ... -
Reproducible Data Management and Analysis using R
(Chapter, 2020)Standardizing and documenting computational analyses is necessary to ensure reproducible results. We describe an R-based implementation of data management and preprocessing that is well integrated with the analysis tools ... -
Self-Constructing Graph Convolutional Networks for Semantic Labeling
(Chapter, 2020)Graph Neural Networks (GNNs) have received increasing attention in many fields. However, due to the lack of prior graphs, their use for semantic labeling has been limited. Here, we propose a novel architecture called the ... -
Signals of Death - Post-Diagnostic Single Gene Expression Trajectories in Breast Cancer - A Proof of Concept
(Chapter, 2020)Using the time-dependent dynamics of gene expression from immune cells in blood, we aimed to explore single gene expression trajectories as biomarkers for death after a diagnosis of breast cancer introducing a new statistical ... -
skweak: Weak Supervision Made Easy for NLP
(Chapter, 2021)We present skweak, a versatile, Python-based software toolkit enabling NLP developers to apply weak supervision to a wide range of NLP tasks. Weak supervision is an emerging machine learning paradigm based on a simple idea: ... -
Social Contact for Older People with Visual Impairment Through Mastery of Smartphones: Barriers and Suggested Solutions
(Chapter, 2021)Older people with visual impairment are more prone to feeling lonely than their seeing peers. Research suggests that learning to use smartphones can improve psychological well-being in older adults. We seek to further ... -
The 1st Agriculture-Vision Challenge: Methods and Results
(Chapter, 2020) -
Toward AI-Based Scenario Management for Cyber Range Training
(Chapter, 2021)There is an immediate need for a greater number of highly skilled cybersecurity personnel to meet intensified cyber attacks. We propose a cyber range exercise management architecture that employs machine reasoning to ... -
Universally Designed Augmented Reality (AR) for the School of the Future
(Chapter, 2023)Augmented Reality (AR), together with other technologies collectively referred to as eXtended Reality (XR), can offer opportunities in education for experiential learning and the visualization of abstract concepts. However, ... -
Universally Designed Augmented Reality (AR) for the School of the Future
(Chapter, 2023)Augmented Reality (AR), together with other technologies collectively referred to as eXtended Reality (XR), can offer opportunities in education for experiential learning and the visualization of abstract concepts. However, ...