Sökning: "Uncertainty quantification"
Visar resultat 1 - 5 av 41 uppsatser innehållade orden Uncertainty quantification.
1. Uncertainty Quantification in Deep Learning for Breast Cancer Classification in Point-of-Care Ultrasound Imaging
Master-uppsats, Lunds universitet/Matematik LTHSammanfattning : Breast cancer is the most common type of cancer worldwide with an estimate of 2.3 million new cases in 2020, and the number one cause of cancer-related deaths in women. LÄS MER
2. Propagation of Nuclear Data Uncertainties for Reactor Physics Parameters in Fluorine-19-based Molten Salt Reactors
Master-uppsats, Uppsala universitet/Tillämpad kärnfysikSammanfattning : It could be argued that a renaissance is taking place for the global interest in nuclear power - especially for the development of the next generation of reactor systems that aim at solving the problems with contemporary energy production with nuclear technology. One such proposed concept for Gen IV nuclear power is a Molten Salt Reactor (MSR), in which the nuclear fuel is in solution of a salt - often based on fluorine or chlorine. LÄS MER
3. Verifiering av ny extraktionsmetod för analys på oljeindex
Uppsats för yrkesexamina på grundnivå, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)Sammanfattning : Huvudsyftet med detta examensarbete var att verifiera en ny metod för extraktion av olja från jord-, slam-, och sedimentprover som ska ersätta företagets befintliga metod. Extraktionen sker på ett skakbord som förbehandling innan den extraherade oljan sätts på en GC-FID för att analysera dess oljeindex mellan C10-C40 samt dess olika specifika delfraktioner. LÄS MER
4. Uncertainty Estimation in Volumetric Image Segmentation
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The performance of deep neural networks and estimations of their robustness has been rapidly developed. In contrast, despite the broad usage of deep convolutional neural networks (CNNs)[1] for medical image segmentation, research on their uncertainty estimations is being far less conducted. LÄS MER
5. Modeling and quantifying uncertainty in bus arrival timeprediction
Master-uppsats, Linköpings universitet/Statistik och maskininlärningSammanfattning : Public transportation operates in an environment which, due to its nature of numerous possibly influencing factors, is highly stochastic. This makes predictions of arrival times difficult, yet it’s important to be accurate in order to adhere to travelers expectations. LÄS MER