Search for dissertations about: "classification accuracy"
Showing result 16 - 20 of 215 swedish dissertations containing the words classification accuracy.
-
16. Semi-supervised learning with self-supervision for closed and open sets
Abstract : Semi-supervised learning (SSL) is a learning framework that enables the use of unlabeled data with labeled data. These methods play a crucial role in reducing the burden of human labeling in training deep learning models. Many methods for SSL learn from unlabeled data through confidence-based pseudo-labeling. READ MORE
-
17. Ulnar fractures and ligament injuries of the wrist
Abstract : Falling over on an outstretched hand with the wrist extended is a common accident that can cause a multitude of injuries in the wrist. Research has mainly focused on distal radius fractures while injuries of the distal ulna and adjacent ligaments have taken a back seat. READ MORE
-
18. From Science to Policy : Improving environmental risk assessment andmanagement of chemicals
Abstract : A complex process like risk assessment and the subsequent risk management decision makingshould be regularly evaluated, in order to assess the need to improve its workings. In this thesisthree related matters are addressed: evaluation of environmental risk management strategies,evaluation of environmental risk assessments, and how ecotoxicity data from the open scientificliterature can be used in a systematic way in regulatory risk assessments. READ MORE
-
19. Bioinformatics tools for discovery and evaluation of biomarkers : Applications in clinical assessment of cancer
Abstract : Cancer is a disease characterized by abnormal proliferation of cells in the body and ranks as the second leading cause of death worldwide. In order to improve cancer patient care, a major focus of cancer research is to discover biomarkers. READ MORE
-
20. Image-based quantitative infrared analysis and microparticle characterisation for pulp and paper applications
Abstract : Measurements of process variations and particle morphology are widely employed in the pulp and paper industry. Two techniques with high potential, infrared thermography and microparticle characterisation, are mainly used qualitatively. READ MORE