Sökning: "level sets"

Visar resultat 1 - 5 av 532 uppsatser innehållade orden level sets.

  1. 1. A space-time shape for easier spatiotemporal visualization in traffic networks

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknik

    Författare :David Smeds; [2024]
    Nyckelord :;

    Sammanfattning : Modern big data systems are enabling new possibilities that never were thought possible in the past. The ability to gather massive data on an individual level has made fields like space-time geography bloom in the latest decennia. The usage of shapes in a 3D space allows us to visualize certain phenomena over time. LÄS MER

  2. 2. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models

    Master-uppsats, Umeå universitet/Institutionen för datavetenskap

    Författare :Sofia Leksell; [2024]
    Nyckelord :Federated Learning; Adversarial Attacks; Regression; Classification;

    Sammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving  a noticeable gap in FL research specifically for regression models. LÄS MER

  3. 3. Using GIS and satellite data to assess access of green area for children living in growing cities

    Master-uppsats, Lunds universitet/Institutionen för naturgeografi och ekosystemvetenskap

    Författare :Rebecca Borg; [2024]
    Nyckelord :Geography; GIS; Geographical Information System; Urban green space; children; schools; Malmö; Earth and Environmental Sciences;

    Sammanfattning : Urban green space (UGS) refers to open spaces within an urban context that are filled with greenery and nature. These can range from very small vegetation to expansive park areas. The common denominator is that they have proven to be beneficial for human health and well-being. Access to green spaces is also important for children. LÄS MER

  4. 4. Attack Strategies in Federated Learning for Regression Models : A Comparative Analysis with Classification Models

    Master-uppsats, Umeå universitet/Institutionen för tillämpad fysik och elektronik

    Författare :Sofia Leksell; [2024]
    Nyckelord :Federated Learning; Adversarial Attacks; Regression; Classification;

    Sammanfattning : Federated Learning (FL) has emerged as a promising approach for decentralized model training across multiple devices, while still preserving data privacy. Previous research has predominantly concentrated on classification tasks in FL settings, leaving  a noticeable gap in FL research specifically for regression models. LÄS MER

  5. 5. A Structural Analysis of the Fracture Sets in Gothenburg, Sweden: A Remote Sensing and Manual Lineament Approach

    Master-uppsats, Göteborgs universitet/Institutionen för geovetenskaper

    Författare :Jacek Krysik; [2023-05-22]
    Nyckelord :Remote sensing; Manual lineament analysis; Fractal analysis; Structural; Regional geology; LiDAR; Gothenburg region;

    Sammanfattning : The fracture-valley landscape within the Gothenburg region was analysed based on LiDAR-derived hillshade images as well as several sources of orthomosaics. Using a manual lineament interpretation approach and complimented with an objective fractal analysis software (FROST), the objective of the study was to characterise the regional fracture sets as well as attempt to link the sets to the complex regional geological history. LÄS MER