Sökning: "Compressed Sensing"

Visar resultat 1 - 5 av 15 uppsatser innehållade orden Compressed Sensing.

1. 1. Over-the-Air Federated Learning with Compressed Sensing

   Master-uppsats, Linköpings universitet/Kommunikationssystem

   Författare :Adrian Edin; [2023]
   Nyckelord :machine learning; ML; Federated Learning; FL; Over-the-air; Over-the-air computation; OtA; OtA computation; AirComp; Compressed sensing; CS; Iterative Hard thresholding; IHT;

   Sammanfattning : The rapid progress with machine learning (ML) technology has solved previously unsolved problems, but training these ML models requires ever larger datasets and increasing amounts of computational resources. One potential solution is to enable parallelization of the computations and allow local processing of training data in distributed nodes, such as Federated Learning (FL). LÄS MER

3. 2. Reconstruction of Accelerated Cardiovascular MRI data

   Master-uppsats, Linköpings universitet/Statistik och maskininlärning

   Författare :Hussnain Khalid; [2023]
   Nyckelord :medical imaging; deep learning; CNN; Magnetic resonance imaging; MRI; Cardiac MRI; Cardiac; Cardiovascular; reconstruction; 4D flow MRI; Parallel Imaging; Compressed Sensing; FlowVN; Flow Variational Network; K-space; Reference images; sensitivity maps; Respiratory motion; undersampled images;

   Sammanfattning : Magnetic resonance imaging (MRI), is a noninvasive medical imaging testing techniquewhich is used to produce detailed images of internal structure of the human body, includingbones, muscles, organs, and blood vessels. MRI scanners use large magnets and radiowaves to create images of the body. LÄS MER

4. 3. LDPC DropConnect

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

   Författare :Xi Chen; [2023]
   Nyckelord :Bayesian approach; Machine learning; Coding theory; Measurement uncertainty; Algorithms; Bayesiansk metod; Maskininlärning; Kodningsteori; Mätosäkerhet; Algoritmer;

   Sammanfattning : Machine learning is a popular topic that has become a scientific research tool in many fields. Overfitting is a common challenge in machine learning, where the model fits the training data too well and performs poorly on new data. LÄS MER

5. 4. Reconstruction of Hyperspectral Images Using Generative Adversarial Networks

   Master-uppsats, Linköpings universitet/Reglerteknik

   Författare :Jacob Eek; [2021]
   Nyckelord :Coded aperture snapshot spectral imaging; CASSI; Raman; Raman spectroscopy; Explosive; Detection; Hyperspectral Image; HSI; Compressed sensing; Compressive Sensing; CS; Machine Learning; Reconstruction; Inverse problem; Generative Adversarial Network; GAN; CGAN; BEGAN; Latent variable optimization;

   Sammanfattning : Fast detection and identification of unknown substances is an area of interest for many parties. Raman spectroscopy is a laser-based method allowing for long range no contact investigation of substances. LÄS MER

7. 5. Reduction of streak artifacts in radial MRI using CycleGAN

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

   Författare :Amanda Ullvin; [2020]
   Nyckelord :MRI; Cardiovascular; CMR; Medical Imaging; Radial k-space sampling; Sub-Nyquist sampling; Golden Angle; GRASP; Compressed Sensing; Artificial Intelligence; Neural Network; Deep Learning; GAN; CycleGAN;

   Sammanfattning : One way of reducing the examination time in magnetic resonance imaging (MRI) is to reduce the amount of raw data acquired, by performing so-called undersampling. Conventionally, MRI data is acquired line-by-line on a Cartesian grid. LÄS MER