Detail publikace

Image Reconstruction in Electrical Impedance Tomography through 1D-Convolutional Neural Network

KOUAKOUO NOMVUSSI, S. MIKULKA, J.

Originální název

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

This paper presents a comparative analysis of image reconstruction performance using a 1D-Convolutional Neural Network (1D-CNN) against the Total Variation algorithm and the Gauss-Newton algorithm. The evaluation, conducted across multiple tests conditions, demonstrates that the 1D-CNN consistently outperforms both conventional methods in terms of correlation coefficient and structural similarity index (SSIM). In noise-free scenarios, the 1D-CNN achieves significantly higher correlation and SSIM values, indicating superior reconstruction accuracy. Furthermore, in the presence of noise (30 dB and 60 dB), the performance of the Total Variation and Gauss-Newton algorithms deteriorates considerably, whereas the 1D-CNN maintains high correlation and SSIM values, demonstrating strong robustness to noise. These findings highlight the effectiveness of deep learning-based approaches for image reconstruction, making the 1D-CNN a promising alternative to traditional reconstruction techniques.

Klíčová slova

1D- convolutional Neural Network, Total Variation, Newton-Gauss, EIT

Autoři

KOUAKOUO NOMVUSSI, S.; MIKULKA, J.

Vydáno

29. 4. 2025

Místo

Brno

ISBN

978-80-214-6321-9

Kniha

Proceedings II of the 31st Conference STUDENT EEICT 2025

Strany počet

BibTex

@inproceedings{BUT198079,
  author="Serge Ayme {Kouakouo Nomvussi} and Jan {Mikulka}",
  title="Image Reconstruction in Electrical Impedance Tomography through 1D-Convolutional Neural Network",
  booktitle="Proceedings II of the 31st Conference STUDENT EEICT 2025",
  year="2025",
  pages="5",
  address="Brno",
  isbn="978-80-214-6321-9"
}