https://github.com/spatialaudio/data-driven-eit-imaging-using-recurrent-neural-networks
Increasing the Reliability of Absolute EIT Imaging using an LSTM-VAE Model Approach
https://github.com/spatialaudio/data-driven-eit-imaging-using-recurrent-neural-networks
Last synced: 11 months ago
JSON representation
Increasing the Reliability of Absolute EIT Imaging using an LSTM-VAE Model Approach
- Host: GitHub
- URL: https://github.com/spatialaudio/data-driven-eit-imaging-using-recurrent-neural-networks
- Owner: spatialaudio
- License: mit
- Created: 2023-10-06T06:25:50.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-12-18T12:24:46.000Z (about 2 years ago)
- Last Synced: 2025-01-07T22:43:11.801Z (about 1 year ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 88.3 MB
- Stars: 1
- Watchers: 6
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: citation.cff
Awesome Lists containing this project
README
# Improved Data-Driven EIT Imaging for Temporal Sequences using Recurrent Neural Networks
**Abstract:** Data-driven reconstruction techniques using
deep neural network (DNN) architectures are applied more
frequently in the field of electrical impedance tomography
(EIT). The solution of the underlying ill-posed inverse problem
may benefit from the possibilities of machine learning
(ML). This contribution demonstrates, how knowledge on
recurring sequences of EIT measurements (e.g. breathing
cycles) may be used to improve the reconstruction. A combination
of a Long Short-Term Memory (LSTM) and an
Variational Autoencoder (VAE) is used.
