Sökning: "vector fields"
Visar resultat 1 - 5 av 69 uppsatser innehållade orden vector fields.
1. Planet-NeRF : Neural Radiance Fields for 3D Reconstruction on Satellite Imagery in Season Changing Environments
Master-uppsats, Linköpings universitet/DatorseendeSammanfattning : This thesis investigates the seasonal predictive capabilities of Neural Radiance Fields (NeRF) applied to satellite images. Focusing on the utilization of satellite data, the study explores how Sat-NeRF, a novel approach in computer vision, per- forms in predicting seasonal variations across different months. LÄS MER
2. Randomized Diagonal Estimation
Master-uppsats, KTH/Matematik (Avd.)Sammanfattning : Implicit diagonal estimation is a long-standing problem that is concerned with approximating the diagonal of a matrix that can only be accessed through matrix-vector products. It is of interest in various fields of application, such as network science, material science and machine learning. LÄS MER
3. Designing a Novel RPL Objective Function & Testing RPL Objective Functions Performance
Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)Sammanfattning : The use of Internet of Things systems has increased to meet the need for smart systems in various fields, such as smart homes, intelligent industries, medical systems, agriculture, and the military. IoT networks are expanding daily to include hundreds and thousands of IoT devices, which transmit information through other linked devices to reach the network sink or gateway. LÄS MER
4. EVALUATING PERFORMANCE OF GENERATIVE MODELS FOR TIME SERIES SYNTHESIS
Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : Motivated by successes in the image generation domain, this thesis presents a novel Hybrid VQ-VAE (H-VQ-VAE) approach for generating realistic synthetic time series data with categorical features. The primary motivation behind this work is to address the limitations of existing generative models in accurately capturing the underlying structure and patterns of time series data, especially when dealing with categorical features. LÄS MER
5. Machine Learning-based MIMO Indoor Positioning
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : The most widely used positioning system is Global Navigation Satellite System (GNSS), which uses traditional positioning techniques and cannot achieve satisfactory positioning performance in indoor scenarios due to Non-Line-of-Sight (NLoS) transmission. Fingerprinting is a non-traditional positioning technique that is robust to NLoS transmission in indoor scenarios. LÄS MER