• Automated Lung Sound Analysis 

      Grønnesby, Morten (Master thesis; Mastergradsoppgave, 2016-06-01)
      Lungs sounds has been used as a diagnostic tool for centuries. The usefulness of listening to lung sounds, or pulmonary auscultation, as a definite diagnostic method has been diminished by advances in medical imaging such as chest X-Ray, but these advanced methods also bring a higher monetary and time cost. In addition, when the severity of pulmonary conditions changes, audible symptoms change ...
    • Automatic algorithm for determining bone and soft-tissue factors in dual-energy subtraction chest radiography 

      Do, Quan; Seo, Wontaek; Shin, Choul Woo (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-11-11)
      Lung cancer is currently the first leading cause of worldwide cancer deaths since the early stage of lung cancer detection is still a challenge. In lung diagnosis, nodules sometimes overlap with ribs and tissues on lung chest radiographic images, which are complex for doctors and radiologists. Dual-energy subtraction (DES) is a suitable solution to solve those issues. This article will develop an ...
    • Automatic Image Tagging based on Context Information 

      Evertsen, Martin Hætta (Master thesis; Mastergradsoppgave, 2010-06)
      People love to take images, but are not so willing to annotate the images af-terwards with relevant tags. Manually tagging images is both subjective (dependent on annotator) and time consuming. It would be nice if the tag-ging process could be done automatically. A requirement for effective searching and retrieval of images in rapid growing online image databases is that each image has accurate and ...
    • Automatic thumbnail selection for soccer videos using machine learning 

      Husa, Andreas; Midoglu, Cise; Hammou, Malek; Hicks, Steven; Johansen, Dag; Kupka, Tomas; Riegler, Michael; Halvorsen, Pål (Chapter; Bokkapittel, 2022-08-05)
      Thumbnail selection is a very important aspect of online sport video presentation, as thumbnails capture the essence of important events, engage viewers, and make video clips attractive to watch. Traditional solutions in the soccer domain for presenting highlight clips of important events such as goals, substitutions, and cards rely on the manual or static selection of thumbnails. However, such ...
    • Automatic Unsupervised Clustering of Videos of the Intracytoplasmic Sperm Injection (ICSI) Procedure 

      Storås, Andrea; Riegler, Michael Alexander; Haugen, Trine B.; Thambawita, Vajira L B; Hicks, Steven Alexander; Hammer, Hugo Lewi; Kakulavarapu, Radhika; Halvorsen, Pål; Stensen, Mette Haug (Chapter; Bokkapittel, 2023-02-02)
      The in vitro fertilization procedure called intracytoplasmic sperm injection can be used to help fertilize an egg by injecting a single sperm cell directly into the cytoplasm of the egg. In order to evaluate, refine and improve the method in the fertility clinic, the procedure is usually observed at the clinic. Alternatively, a video of the procedure can be examined and labeled in a time-consuming ...
    • AutoMon. Automatic monitoring and problem detection for distributed systems 

      Wikstad, Magnus (Master thesis; Mastergradsoppgave, 2016-05-15)
      When working with distributed systems, detecting faults can be a difficult task, as abnormalities isn't necessarily immediately evident by warnings or system crashes. This is especially true with subtle faults, such as variations in performance of a running program, it is not necessarily its own fault, but could rather be from a different source, somewhere in the cluster, using a lot of resources ...
    • Autostrata: Improved Automatic Stratification for Coarsened Exact Matching 

      Arnes, Jo Inge; Hapfelmeier, Alexander; Horsch, Alexander (Chapter; Bokkapittel, 2022-08-22)
      We commonly adjust for confounding factors in analytical observational epidemiologyto reduce biases that distort the results. Stratification and matching are standard methods for reducing confounder bias. Coarsened exact matching (CEM) is a recent method using stratification to coarsen variables into categorical variables to enable exact matching of exposed and nonexposed ...
    • Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts 

      Agarwal, Rohit; Prasad, Dilip Kumar; Horsch, Ludwig Alexander; Gupta, Deepak Kumar (Journal article; Tidsskriftartikkel; Peer reviewed, 2023)
      Many real-world applications based on online learning produce streaming data that is haphazard in nature, i.e., contains missing features, features becoming obsolete in time, the appearance of new features at later points in time and a lack of clarity on the total number of input features. These challenges make it hard to build a learnable system for such applications, and almost no work exists in ...
    • Auxiliary Network: Scalable and agile online learning for dynamic system with inconsistently available inputs 

      Agarwal, Rohit; Agarwal, Krishna; Horsch, Alexander; Prasad, Dilip K. (Journal article; Tidsskriftartikkel, 2022-04-13)
      Streaming classification methods assume the number of input features is fixed and always received. But in many real-world scenarios, some features are reliable while others are unreliable or inconsistent. We propose a novel online deep learning-based model called Auxiliary Network (Aux-Net), which is scalable and agile and can handle any number of inputs at each time instance. The Aux-Net model is ...
    • Áika: A Distributed Edge System for AI Inference 

      Alslie, Joakim Aalstad; Ovesen, Aril Bernhard; Nordmo, Tor-Arne Schmidt; Johansen, Håvard D.; Halvorsen, Pål; Riegler, Michael; Johansen, Dag (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-06-17)
      Video monitoring and surveillance of commercial fisheries in world oceans has been proposed by the governing bodies of several nations as a response to crimes such as overfishing. Traditional video monitoring systems may not be suitable due to limitations in the offshore fishing environment, including low bandwidth, unstable satellite network connections and issues of preserving the privacy of crew ...
    • BacklinkDB: A Purpose-Built Backlink Database Management System 

      Jørgensen, Marius Løvold (Master thesis; Mastergradsoppgave, 2023-02-15)
      In order to compile a list of all the backlinks for a given webpage, we need knowledge about all the outgoing links on the web. Traversing the web and storing all the backlink data in a database allows us to efficiently retrieve the list of backlinks for a web page on demand. However, the web consists of billions of backlinks which translates to terabytes of data. As the web is continuously evolving, ...
    • The Beauty of Complex Designs 

      Arnes, Jo Inge; Bongo, Lars Ailo (Chapter; Bokkapittel, 2020-12-08)
      The increasing use of omics data in epidemiology enables many novel study designs, but also introduces challenges for data analysis. We describe the possibilities for systems epidemiological designs in the Norwegian Women and Cancer (NOWAC) study and show how the complexity of NOWAC enables many beautiful new study designs. We discuss the challenges of implementing designs and analyzing data. Finally, ...
    • Behavioural change in green transportation: Micro-economics perspectives and optimization strategies 

      Bordin, Chiara; Tomasgard, Asgeir (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-06-22)
      The increasing demand for Electric Vehicle (EV) charging is putting pressure on the power grids and capacities of charging stations. This work focuses on how to use indirect control through price signals to level out the load curve in order to avoid the power consumption from exceeding these capacities. We propose mathematical programming models for the indirect control of EV charging that aim at ...
    • Beneath the snow – Developing a wireless sensor node for remote locations in the Arctic 

      Tveito, Øystein (Master thesis; Mastergradsoppgave, 2020-05-15)
      In this thesis we describe how we designed, built, deployed, and improved upon a robust hardware- and software solution, tailor-made to this scientific question. During the course of this project, we created three distinct versions and we have conducted two deployments of the sensor nodes in the Arctic tundra. The node is able to measure CO2 , temperature, and humidity, in addition to monitoring an ...
    • Beyond the hospital walls - Extramural mobile communication with CallMeSmart 

      Hanssen, Bård Johan (Master thesis; Mastergradsoppgave, 2015-06-01)
      Physicians, nurses and other people who work at hospitals and in the healthcare sector often move around a lot. As they also frequently need to contact each other, mobile communication devices like pagers and wireless phones are important tools for letting them maintain contact. This can lead to problems as personnel are constantly interrupted during their work because coworkers don't know whether ...
    • Bilder og stedsinformasjon 

      Bjørnenak, Kai Arne (Master thesis; Mastergradsoppgave, 2006-12-15)
      Enorme mengder informasjon er tilgjengelig på internett for browsing og søk for folk på jakt etter informasjon. En økende del av denne informasjonsmengden er bilder, video og audio. Disse media-typene er ikke så lette å kategorisere og beskrive som en tekstlig ressurs. Vi trenger derfor nye metoder for å takle utfordringene denne fremveksten av nye media gir oss. Digitalt fotografi har hatt ...
    • Breathing as user interface for pulmonary rehabilitation : respiration tracking using the Wii remote controller 

      Guirao Aguilar, Julian (Master thesis; Mastergradsoppgave, 2010-06-01)
      INTRODUCTION: Respiration exercises are an important part of the pulmonary rehabilitation in COPD (chronic obstructive pulmonary disease) patients. Furthermore, there is evidence that showing feedback about their respiration pattern helps them to improve their breathing skills. This study tests the feasibility of monitoring respiration using the Wiimote's infrared camera and showing BPM (breaths per ...
    • Budget-aware scheduling algorithm for scientific workflow applications across multiple clouds. A Mathematical Optimization-Based Approach 

      Ziagham Ahwazi, Amin (Master thesis; Mastergradsoppgave, 2022-05-16)
      Scientific workflows have become a prevailing means of achieving significant scientific advances at an ever-increasing rate. Scheduling mechanisms and approaches are vital to automating these large-scale scientific workflows efficiently. On the other hand, with the advent of cloud computing and its easier availability and lower cost of use, more attention has been paid to the execution and scheduling ...
    • Building a Neighborhood Resource Map for IoT and Cyber-Physical systems in Resource-Constrained Environments 

      Sønvisen, Sindre (Master thesis; Mastergradsoppgave, 2022-05-12)
      Creating and maintaining a shared resource map between observation nodes that have a behavior where they are mostly sleeping, and have a wake up schedule that are determined at each node locally is challenging. This thesis looks at these challenges, and possible solutions have been proposed to overcome them. Previous research on the topic of constrained IoT networks have looked at the network, ...
    • Building agent applications using wrappers 

      Sudmann, Nils P.; Johansen, Dag (Research report; Forskningsrapport, 2001-01-11)
      For the past seven years, the TACOMA project has investigated software support for mobile agents. Several prototypes have been developed, with experiences in distributed applications directing the effort. This paper presents a new mechanism that supports implementing agent applications by creating troops of agents using wrappers. This solution requires little extra support from the agent system, and ...