Search results for "VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550"
showing 10 items of 469 documents
HL7 FHIR with SNOMED-CT to Achieve Semantic and Structural Interoperability in Personal Health Data: A Proof-of-Concept Study
2022
Heterogeneity is a problem in storing and exchanging data in a digital health information system (HIS) following semantic and structural integrity. The existing literature shows different methods to overcome this problem. Fast healthcare interoperable resources (FHIR) as a structural standard may explain other information models, (e.g., personal, physiological, and behavioral data from heterogeneous sources, such as activity sensors, questionnaires, and interviews) with semantic vocabularies, (e.g., Systematized Nomenclature of Medicine—Clinical Terms (SNOMED-CT)) to connect personal health data to an electronic health record (EHR). We design and develop an intuitive health coaching (eCoach…
Widely Acclaimed but Lowly Utilized: Congruencing ODL Utilization with its Wide Acclaim
2019
World over, open distance learning (ODL) is widely articulated and vouchered as a panacea pedagogy for increased access and flexibility to higher education. In reality, however, the actual use of ODL approaches in higher institutions of learning in developing regions is unexpectedly low and not in tandem with its wide favorable regional and international vouchering. This paper has the goal to suggest a framework for congruencing the low utilization levels of ODL approaches with their wide acclaim. Using a cross sectional survey, an inquiry was conducted among faculty across institutions of higher learning in Uganda to establish: i) the factors explaining the wide acclaim for ODL; ii) the ut…
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…
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…
Deep Convolutional Neural Networks for Semantic Segmentation of Multi-Band Satellite Images
2018
Master's thesis Information- and communication technology IKT590 - University of Agder 2018 Semantic segmentation of images is of increasing interest in the eld of computer vision and machine learning. Accurate and e cient segmentation methods is required for many of todays modern applications. This the- sis provides a review of deep learning methods for semantic segmentation of satellite images. Firstly, we compare di erent state-of-the-art methods. Next, we explore the bene ts of using multiple spectral bands of data as compared to the traditional RGB bands. Finally, a look at future possibil- ities with segmentation using capsule networks.
Combining Deep Privacy with an Attribute-driven Generative Adversarial Network to Preserve Gender and Age in De-identified CCTV Footage
2021
Master's thesis in Information- and communication technology (IKT590) A surveillance camera is an efficient solution to prohibit crimes for both small and big businesses, and is broadly utilized in big cities. Today, the police force can only access the camera footage for further investigation after an act of crime. In order to observe, find patterns, and react appropriately to an event, the Oslo Police wants to use its own CCTV cameras and analyze such footage in real-time. To investigate real-time CCTV footage and share such footage with a third-party for analyzing, the people in the footage need to be de-identified. In this thesis, we focus on de-identification of CCTV footage, preservin…
Hand Gestures Recognition using Thermal Images
2021
Master's thesis in Information- and communication technology (IKT590) Hand gesture recognition is important in a variety of applications, including medical systems and assistive technologies, human-computer interaction, human-robot interaction, industrial automation, virtual environment control, sign language translation, crisis and disaster management, en-tertainment and computer games, and robotics. RGB cameras are usually used for most of these applications. However, their performance is limited especially in low-light conditions. It is challenging to accurately classify the hand gestures in dark conditions. In this thesis, we propose the robust hand gestures recognition based on high re…