Search results for "SJ"

Pietarsaari

1763

A Lite Romanian BERT: ALR-BERT

2022

Large-scale pre-trained language representation and its promising performance in various downstream applications have become an area of interest in the field of natural language processing (NLP). There has been huge interest in further increasing the model’s size in order to outperform the best previously obtained performances. However, at some point, increasing the model’s parameters may lead to reaching its saturation point due to the limited capacity of GPU/TPU. In addition to this, such models are mostly available in English or a shared multilingual structure. Hence, in this paper, we propose a lite BERT trained on a large corpus solely in the Romanian language, which we cal…

Single-channel speech enhancement using implicit Wiener filter for high-quality speech communication

2022

AbstractSpeech enables easy human-to-human communication as well as human-to-machine interaction. However, the quality of speech degrades due to background noise in the environment, such as drone noise embedded in speech during search and rescue operations. Similarly, helicopter noise, airplane noise, and station noise reduce the quality of speech. Speech enhancement algorithms reduce background noise, resulting in a crystal clear and noise-free conversation. For many applications, it is also necessary to process these noisy speech signals at the edge node level. Thus, we propose implicit Wiener filter-based algorithm for speech enhancement using edge computing system. In the proposed algor…

Modelling, Identification and Control of a 5-DOF Shotcrete Robot : Development of a Framework for Automatic Application of Shotcrete for AMV 4200H

2019

Master's thesis Mechatronics MAS500 - University of Agder 2019 Today, process automation is the primary area of development in the shotcrete industry. Automaticshotcrete operations can yield an increase in operational efficiency and personnel safety as well asreductions in cost and environmental impact. This thesis develops a framework for automaticapplication of shotcrete using the AMV 4200H and provides an automatic spraying mode usinginteroceptive sensing. The shotcrete vehicle is equipped with a five degrees-of-freedom manipulatorand is currently operated manually. Our contributions include solving the forward kinematicsthrough the Denavit-Hartenberg convention, and the inverse kinemati…

Bi-objective multi-layer location–allocation model for the immediate aftermath of sudden-onset disasters

2019

International audience; Locating distribution centers is critical for humanitarians in the immediate aftermath of a sudden-onset disaster. A major challenge lies in balancing the complexity and uncertainty of the problem with time and resource constraints. To address this problem, we propose a location–allocation model that divides the topography of affected areas into multiple layers; considers constrained number and capacity of facilities and fleets; and allows decision-makers to explore trade-offs between response time and logistics costs. To illustrate our theoretical work, we apply the model to a real dataset from the 2015 Nepal earthquake response. For this case, our method results in…

Long-term resource utilisation and associated costs of exercise during (neo)adjuvant oncological treatment: the Phys-Can project

2022

Background Exercise during oncological treatment is beneficial to patient health and can counteract the side effects of treatment. Knowledge of the societal costs associated with an exercise intervention, however, is limited. The aims of the present study were to evaluate the long-term resource utilisation and societal costs of an exercise intervention conducted during (neo)adjuvant oncological treatment in a randomised control trial (RCT) versus usual care (UC), and to compare high-intensity (HI) versus low-to-moderate intensity (LMI) exercise in the RCT. Methods We used data from the Physical Training and Cancer (Phys-Can) project. In the RCT, 577 participants were randomised to HI or to …

Satisfied or Frustrated? A Qualitative Analysis of Need Satisfying and Need Frustrating Experiences of Engaging With Digital Health Technology in Chr…

2020

Introduction: Digital health technologies such as self-monitoring devices and apps are becoming increasingly important as tools to promote healthy habits and support individuals in their self-care. There is still a scarcity of research that builds on motivational theory to better understand the functioning of digital health technologies. The self-determination theory (SDT) is a macro theory of motivation that delineates three basic psychological needs that are linked to different types of motivation and lead to well-being when satisfied and illbeing when frustrated. Objective: To explore how the use of a digital tool for self-monitoring and communication with healthcare satisfies or frustra…

Fotballklubbers forankring og betydning i det norske samfunn : en casestudie av Viking fotballklubb

2008

Masteroppgave i idrettsvitenskap- Universitetet i Agder 2008 Fotballklubbers lokale forankring og betydning vil ses nærmere på gjennom teoretisk refleksjon og empirisk observasjon der Viking FK er case. Teorien som anvendes er Luhmanns systemteori og det som danner det empiriske materialet er dokumenter og kvalitative intervjuer. Ifølge Luhmann (2000a) er sosiale fenomen, som eksemplifisert ved Viking FK i denne avhandlingen, sosiale system som danner seg selv gjennom å skille seg fra omverden. Skille mellom systemet selv og dets omverden danner en unik betraktning av seg selv som noe forskjellig fra omverden. Det utgjør systemets realitetsforståelse, dets mening som uttrykkes gjennom forve…

Real-Life Experiments based on IQRF IoT Testbed: From Sensors to Cloud

2018

Master's thesis Information- and communication technology IKT590 - University of Agder 2018 Internet of things (IoT) is the next generation internet technology which connects devices and objects intelligently to control data collected by diverse types of sensors, radio frequency identification and other physical objects. To address the challenges in IoT such as integrating artificial intelligent techniques with IoT concept, developing green IoT technologies and combining IoT and cloud computing, various platforms which support reliable and low power wireless connectivity are required. IQRF is a recently developed platform for wireless connectivity. It provides low power, low speed, reliable…

Feasibility analysis for forecasting inflow of unplanned work using machine learning techniques

2021

Master´s thesis in Information and Communication Technology (IKT590), University of Agder, Grimstad