Advanced search
Showing result 16 - 20 of 194 essays matching the above criteria.
-
16. Optic nerve sheath diameter semantic segmentation and feature extraction
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Traumatic brain injury (TBI) affects millions of people worldwide, leading to significant mortality and disability rates. Elevated intracranial pressure (ICP) resulting from TBI can cause severe complications and requires early detection to improve patient outcomes. READ MORE
-
17. Segmentation and Valuation in Stockholm Housing Market : Spatial Continuous and Discontinuous Submarkets Evaluating by Hedonic Price Model and XGBoost Model
University essay from KTH/Fastighetsekonomi och finansAbstract : The housing market segmentation could provide a reference for more targeted policymaking and investment strategies. Although there have been many studies, there are no consistent submarkets delineating methods because of a lack of theoretical support and subjective evaluation. In this paper, two market segmentation methods are introduced. READ MORE
-
18. Improving Change Point Detection Using Self-Supervised VAEs : A Study on Distance Metrics and Hyperparameters in Time Series Analysis
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This thesis addresses the optimization of the Variational Autoencoder-based Change Point Detection (VAE-CP) approach in time series analysis, a vital component in data-driven decision making. We evaluate the impact of various distance metrics and hyperparameters on the model’s performance using a systematic exploration and robustness testing on diverse real-world datasets. READ MORE
-
19. Real-time Unsupervised Domain Adaptation
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Machine learning systems have been demonstrated to be highly effective in various fields, such as in vision tasks for autonomous driving. However, the deployment of these systems poses a significant challenge in terms of ensuring their reliability and safety in diverse and dynamic environments. READ MORE
-
20. Self-supervised pre-training of an attention-based model for 3D medical image segmentation
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Accurate segmentation of anatomical structures is crucial for radiation therapy in cancer treatment. Deep learning methods have been demonstrated effective for segmentation of 3D medical images, establishing the current standard. However, they require large amounts of labelled data and suffer from reduced performance on domain shift. READ MORE