Sökning: "Nätverksmodell"

Visar resultat 1 - 5 av 34 uppsatser innehållade ordet Nätverksmodell.

1. 1. Assessing the Effectiveness of Urban Trees with Skeletal Soils in Flood Risk Mitigation

   Master-uppsats, KTH/Hållbar utveckling, miljövetenskap och teknik

   Författare :Molly Boberg; [2024]
   Nyckelord :Flood Management; Climate Adaptation; Nature-Based Solutions NBS ; Urban Trees; Skeletal Soil; Hydrologic Modelling; MIKE; Översvämningshantering; Klimatanpassning; Naturbaserade lösningar; Stadsträd; Skelettjord; Hydrologisk modellering; MIKE;

   Sammanfattning : With increased urbanization and climate change, heavy rainfall events and urban floods are becoming more frequent. To meet the demands for effective climate adaptation strategies and mitigation measures, Nature-Based Solutions (NBS) have received increased attention. LÄS MER

3. 2. Predicting Patent Data using Wavelet Regression and Bayesian Machine Learning

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Mattias Martinsen; [2023]
   Nyckelord :Wavelet; Regression; Bayesian network; Prediction; Patent; Machine Learning; Wavelet; Regression; Bayesiskt nätverk; Predicering; Patent; Maskininlärning;

   Sammanfattning : Patents are a fundamental part of scientific and engineering work, ensuringprotection of inventions owned by individuals or organizations. Patents areusually made public 18 months after being filed to a patent office, whichmeans that current publicly available patent data only provides informationabout the past. LÄS MER

4. 3. Developing a Neural Network Model for Semantic Segmentation

   M1-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

   Författare :Ronny Westphal; [2023]
   Nyckelord :Semantic segmentation; neural network; Unity Barracuda; PyTorch; augmented reality; Semantisk segmentering; neurala nätverk; Unity Barracuda; PyTorch; augmenterad verklighet;

   Sammanfattning : This study details the development of a neural network model designed for real-time semantic segmentation, specifically to distinguish sky pixels from other elements within an image. The model is incorporated into a feature for an Augmented Reality application in Unity, leveraging Unity Barracuda—a versatile neural network inference library. LÄS MER

5. 4. Anomaly Detection in the EtherCAT Network of a Power Station : Improving a Graph Convolutional Neural Network Framework

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Niklas Barth; [2023]
   Nyckelord :Unsupervised Learning; Multivariate Time Series; Graph Convolutional Neural Networks; Anomaly Detection; Industrial Control System; EtherCAT; Power Station; Electricity Grid;

   Sammanfattning : In this thesis, an anomaly detection framework is assessed and fine-tuned to detect and explain anomalies in a power station, where EtherCAT, an Industrial Control System, is employed for monitoring. The chosen framework is based on a previously published Graph Neural Network (GNN) model, utilizing attention mechanisms to capture complex relationships between diverse measurements within the EtherCAT system. LÄS MER

7. 5. Prediction of 5G system latency contribution for 5GC network functions

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Ziyu Cheng; [2023]
   Nyckelord :Network model; End-to-end delay; 5GC; Prediction model; CPU load; Nätverksmodell; Slutanvändare; latens; 5GC; Modell för prediktering; CPU-last;

   Sammanfattning : End-to-end delay measurement is deemed crucial for network models at all times as it acts as a pivotal metric of the model’s effectiveness, assists in delineating its performance ceiling, and stimulates further refinement and enhancement. This premise holds true for 5G Core Network (5GC) models as well. LÄS MER