English
norskMastergradsoppgaver i teknologi - anvendt fysikk
Vis alle innførsler i samlingen sortert på
Nye registreringer
-
Leveraging Explainability Maps for Group-unsupervised Robustness to Spurious Correlations
(Master thesis; Mastergradsoppgave, 2023-08-22)Shortcut learning, the tendency for models to rely on spurious correlations, is a widespread issue in deep learning. Although being a known issue, uncovering the shortcuts present in a dataset can be a difficult task. Over the last few years, explainability methods have been leveraged to find previously unknown shortcuts within mainstream datasets. However, how to best mitigate a model’s reliance ... -
Propagating information like waves in GNNs
(Master thesis; Mastergradsoppgave, 2024-05-31)Various deep learning architectures are appearing in the field of machine learning with the goal of being able to handle various types of data, or solving inherent problems within the networks. In this thesis, we propose the idea of creating architectures based on physics partial differential equations (PDEs), where we transfer the known properties of PDEs as a method of introducing inductive bias ... -
Uncertainty Guided Polygon Generation for Building Detection
(Mastergradsoppgave; Master thesis, 2024-06-01)Enhanced accuracy of building detection algorithms has the potential to benefit a wide array of applications, including urban planning, environmental monitoring, and disaster response efforts. However, building extraction algorithms struggle with robustness due to among others, occlusions from vegetation and shadows of nearby tall buildings, complex building shapes, and a large distributional shift ... -
Unsupervised segmentation of submarine recordings
(Mastergradsoppgave; Master thesis, 2023-06-01)The thesis focuses on the unsupervised segmentation of submarine recordings collected by the Norwegian Polar Institute (NPI) using hydrophones. These recordings consists of various mammal species, along with other phenomena like vessel engines, seismic activity, and moving sea ice. With sparse labeling of the data, a supervised learning approach is not feasible, necessitating the application of ... -
Towards automation in the fish processing industry using machine learning
(Master thesis; Mastergradsoppgave, 2023-04-11)This master project was inspired by challenges faced by commercial fisheries in the north of Norway of controlling food quality and food safety. In this thesis, four different ML models’ ability to do object and keypoint detection on specific anatomy parts of fish, has been studied. With the aim of recommending a suitable model to be part of a CV system for an industrial fish gutting machine that ... -
Exploring the Behavior of Open-Source Diffusion Model Inpainting Algorithms
(Master thesis; Mastergradsoppgave, 2023-01-26)The present study aimed to examine the performance of an open-source diffusion model inpainting algorithm under varying conditions of inpainting strength and mask radius. However, the results obtained were unexpected and raise significant concerns. Our findings indicate that the algorithm not only modifies the pixels within the designated mask, as intended, but also alters pixels out side of the ... -
Towards population counting of marine mammals based on drone images
(Mastergradsoppgave; Master thesis, 2022-07-11)In marine science, there is a need for tools for population counting of species. Through this thesis we aim to achieve the follow three objectives: first, briefly discuss the state-of-the-art object detectors that can be used for the detection of porpoises in drone images/videos. Second, test and compare a few stateof-the-art object detectors in both quantitative and qualitative manner. Third, based ... -
Deep Representation-aligned Graph Multi-view Clustering for Limited Labeled Multi-modal Health Data
(Mastergradsoppgave; Master thesis, 2022-06-01)Today, many fields are characterised by having extensive quantities of data from a wide range of dissimilar sources and domains. One such field is medicine, in which data contain exhaustive combinations of spatial, temporal, linear, and relational data. Often lacking expert-assessed labels, much of this data would require analysis within the fields of unsupervised or semi-supervised learning. Thus, ... -
Inference Guided Few-Shot Segmentation
(Master thesis; Mastergradsoppgave, 2022-06-22)Few-shot segmentation has in recent years gotten a lot of attention. The reason is its ability to segment images from classes based on only a handful of labeled support images. This opens up many possibilities when the need for a big dataset is removed. To do this a few-shot segmentation network need to extract as much quality information from each support image as possible. In this thesis we ... -
Machine Learning for Classifying Marine Vegetation from Hyperspectral Drone Data in the Norwegian coast
(Master thesis; Mastergradsoppgave, 2022-05-30)Along the Norwegian coasts the presence of blue forests are the key marine habitats. Due to increased anthropogenic activity and climate change, the health and extent of the blue forests is threatened. However, no low-cost, reliable system for monitoring blue forests exists in Norway at this time. This thesis studied machine learning methods to classify marine vegetation from hyperspectral data ... -
Validating Uncertainty-Aware Virtual Sensors For Industry 4.0
(Mastergradsoppgave; Master thesis, 2022-01-26)In industry 4.0 manufacturing, sensors provide information about the state, behavior, and performance of processes. Therefore, one of the main goals of Industry 4.0 is to collect high-quality data to realize its business goal, namely zero-defect manufacturing, and high-quality products. However, hardware sensors cannot always gather quality data due to several factors. First, industrial 4.0 deploys ... -
ConvMixerSeg: Weakly Supervised Semantic Segmentation for CT Liver Images
(Mastergradsoppgave; Master thesis, 2021-12-17)The predictive power of modern deep learning approaches is posed to revolutionize the medical imaging field, however, their usefulness and applicability are severely limited by the lack of well annotated data. Liver segmentation in CT images is an application that could benefit particularly well from less data hungry methods and potentially lead to better liver volume estimation and tumor detection. ... -
Imputation and classification of time series with missing data using machine learning
(Mastergradsoppgave; Master thesis, 2021-06-21)This work is about classifying time series with missing data with the help of imputation and selected machine learning algorithms and methods. The author has used imputation to replace missing values in two data sets, one containing surgical site infection (SSI) data of 11 types of blood samples of patients over 20 days, and another data set called uwave which contain 3D accelerometer data of several ... -
Investigating the Impact of Susceptibility Artifacts on Adjacent Tumors in PET/MRI through Simulated Tomography Experiments
(Mastergradsoppgave; Master thesis, 2021-06-01)For quantitative PET imaging, attenuation correction (AC) is mandatory. Currently, all main vendors of hybrid PET/MRI systems apply a segmentation-based approach to compute a Dixon AC-map based on fat and water images derived from in- and opposed-phase MR-images. Changes in magnetic susceptibility pose major problems for MRI, which may lead to artifacts resulting in tissue misclassification in the ... -
Extracting Information from Multimodal Remote Sensing Data for Sea Ice Characterization
(Mastergradsoppgave; Master thesis, 2021-06-01)Remote sensing is the discipline that studies acquisition, preparation and analysis of spectral, spatial and temporal properties of objects without direct touch or contact. It is a field of great importance to understanding the climate system and its changes, as well as for conducting operations in the Arctic. A current challenge however is that most sensory equipment can only capture one or fewer ... -
MIR-based in-situ measurement of Silicon crystal-melt interface
(Master thesis; Mastergradsoppgave, 2020-06-29)The project explores the a proposed MIR-based measurement system for measuring the deflection of the interface between the crystal and melt during production of mono-crystalline Silicon in the Czochralski process. The absorption spectrum is modeled and the specific absorption for a select set of wavelengths is estimated for temperatures approching 1687K. It was estimated that the intrinsic absorption ... -
Wideband Self-Interference Cancellation Using Multi-Tap Filter in Radar Front End
(Mastergradsoppgave; Master thesis, 2020-12-14)The largest hurdle in full duplex wireless systems is the self-interference introduced by the transmitted signal into the received signal. In multi antenna systems this interference is caused by the direct coupling between the transmitting and receiving antennas. In systems where the transmitter and receiver uses the same antenna the interference is caused by inadequate isolation between the ... -
Introducing Soft Option-Critic for Blood Glucose Control in Type 1 Diabetes : Exploiting Abstraction of Actions for Automated Insulin Administration
(Master thesis; Mastergradsoppgave, 2020-07-15)Type 1 Diabetes (T1D) is an autoimmune disease where the insulin-producing cells are damaged and unable to produce sufficient amounts of insulin, causing an inability to regulate the body's blood sugar levels. Administrating insulin is necessary for blood glucose regulation, requiring diligent and continuous care from the patient to avoid critical health risks. The dynamics governing insulin-glucose ... -
Numerical and experimental investigation of absorbing polymer films suitable for boundary photoacoustic imaging
(Master thesis; Mastergradsoppgave, 2020-07-13)One of the main challenges in conventional photoacoustic methods, is that thin biological samples typically have low optical absorption in the visible region. Therefore, it is often necessary to stain or label the sample with a color which provide sufficient absorption for the laser wavelength used in the scanning system. Unfortunately, the labeling often introduce unwanted properties to the biological ... -
Deep Learning of Oriented Bounding Box Regression Networks for Ship Detection in Optical Satellite Images
(Master thesis; Mastergradsoppgave, 2020-05-31)Maritime surveillance is important for management of maritime traffic and to prevent activities like illegal fishing, hazardous cargo transportation, piracy, and smuggling of goods and humans. Remote sensing is frequently used for positioning vessels that are not transmitting via the Automatic Identification System (AIS). Modern optical remote sensing instruments provide high-resolutional imagery, ...
RSS 1.0