Sökning: "Graph convolutional neural networks"

Visar resultat 6 - 10 av 29 uppsatser innehållade orden Graph convolutional neural networks.

1. 6. Trigger-Level Multiple Electron Event Classification with LDMX using Artificial Neural Networks

   Master-uppsats, Lunds universitet/Partikel- och kärnfysik; Lunds universitet/Fysiska institutionen

   Författare :Jacob Lindahl; [2023]
   Nyckelord :LDMX; ANN; CNN; GNN; RNN; DM; Physics and Astronomy;

   Sammanfattning : Artificial neural networks is a powerful tool for classifying and identifying patterns in large amounts of data. One of the possible tasks of these networks is classification of data into categories. LÄS MER

3. 7. Design and Implementation of Cellular Network Hotspot Forecast Using Graph Convolutional Neural Networks

   Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Adrià Correas I Grifoll; [2022]
   Nyckelord :;

   Sammanfattning : This project proposes a type of (Recurrent) Graph Neural Network (RGNN) to predict future hotspots in cellular network data. Current state-of-the-art algorithms process each antenna (celldata )’s in isolation, ignoring the performance of nearby cells and cell locations. LÄS MER

4. 8. Human Skeleton-based Transfer Learning on Personalized Rehabilitation Training Recognition

   Master-uppsats, Uppsala universitet/Institutionen för informationsteknologi

   Författare :Ying Peng; [2022]
   Nyckelord :;

   Sammanfattning : Personalized rehabilitation training programs depend on the patient’s physical condition and the physiotherapist’s diagnosis, which varies for different people. As a patient, achieving a good training effect requires multiple periods, but rehabilitation training at home is often ineffective due to a lack of supervision and guidance. LÄS MER

5. 9. Labelling Customer Actions in an Autonomous Store Using Human Action Recognition

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

   Författare :Oskar Areskog; [2022]
   Nyckelord :artificial intelligence; ai; human action recognition; graph-convolutional neural network;

   Sammanfattning : Automation is fundamentally changing many industries and retail is no exception. Moonshopis a South African venture trying to solve the problem of autonomous grocery storesusing cameras and computer vision. This project is the continuation of a hackathon heldto explore different methods for Human Action Recognition in Moonshop’s stores. LÄS MER

7. 10. Observation Based Modeling of Liquid Slosh in Drop Tests

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Victor Ekblad; Axl Roos; [2022]
   Nyckelord :Sloshing; Fluid Dynamics; Image Segmentation; 3D reconstruction; Machine Learning; U-Net; CNN; GCN; LSTM; Mathematics and Statistics;

   Sammanfattning : Tetra Pak® is a world leading food packaging company with a large variety of paperboard beverage packages. In the development of paperboard packages, an essential component is utilizing simulation models long before physical prototypes are manufactured. This speeds up the development process and allows quick evaluation of new designs. LÄS MER