Image reconstruction for electrical impedance tomography (EIT) with improved Wasserstein generative adversarial network (WGAN)

H Zhang, Q Wang, R Zhang, X Li, X Duan… - IEEE Sensors …, 2022 - ieeexplore.ieee.org
The image reconstruction of electrical impedance tomography (EIT) is highly ill-posed and
nonlinear. Because of the poor nonlinear fitting ability of analytical algorithms, reconstructed …

Application of a generative adversarial network in image reconstruction of magnetic induction tomography

D Yang, J Liu, Y Wang, B Xu, X Wang - Sensors, 2021 - mdpi.com
Image reconstruction of Magnetic induction tomography (MIT) is an ill-posed problem. The
non-linear characteristics lead many difficulties to its solution. In this paper, a method based …

Interior void classification in liquid metal using multi-frequency magnetic induction tomography with a machine learning approach

I Muttakin, M Soleimani - IEEE Sensors Journal, 2021 - ieeexplore.ieee.org
Identification of gas bubble, void detection and porosity estimation are important factors in
many liquid metal processes. In steel casting, the importance of flow condition and phase …

A deep neural network method for arterial blood flow profile reconstruction

D Yang, Y Wang, B Xu, X Wang, Y Liu, T Cheng - Entropy, 2021 - mdpi.com
Arterial stenosis will reduce the blood flow to various organs or tissues, causing
cardiovascular diseases. Although there are mature diagnostic techniques in clinical …

Conditional Diffusion Model for Electrical Impedance Tomography

D Shi, W Zheng, D Guo, H Liu - arXiv preprint arXiv:2501.05769, 2025 - arxiv.org
Electrical impedance tomography (EIT) is a non-invasive imaging technique, which has
been widely used in the fields of industrial inspection, medical monitoring and tactile …

Graph Fusion and Propagation for Fault Diagnosis in Industrial Robots with Limited Labeled Data

Z Wang, H Liang, C Chen, T Wang… - IEEE Sensors …, 2024 - ieeexplore.ieee.org
Deep learning has propelled the advancement of fault diagnosis modeling for industrial
robots. However, the scarcity of fault samples in industrial robot datasets constrains the …

Improved Forward Problem Modeling in Magnetic Induction Tomography for Biomedical Applications

H Yazdanian - arXiv preprint arXiv:2206.07906, 2022 - arxiv.org
The main contribution of this thesis is to investigate the incorporating skin and proximity
effects in magnetic induction tomography (MIT) coils and present an improved model for the …