Construct Deep Neural Networks Based on Direct Sampling Methods for Solving Electrical Impedance Tomography
arXiv:2009.08024
Abstract
This work investigates the electrical impedance tomography (EIT) problem when only limited boundary measurements are available, which is known to be challenging due to the extreme ill-posedness. Based on the direct sampling method (DSM), we propose deep direct sampling methods (DDSMs) to locate inhomogeneous inclusions in which two types of deep neural networks (DNNs) are constructed to approximate the index function(functional): fully connected neural network(FNN) and convolutional neural network (CNN). The proposed DDSMs are easy to be implemented, capable of incorporating multiple Cauchy data pairs to achieve high-quality reconstruction and highly robust with respect to large noise. Additionally, the implementation of DDSMs adopts offline-online decomposition, which helps to reduce a lot of computational costs and makes DDSMs as efficient as the conventional DSM. The numerical experiments are presented to demonstrate the efficacy and show the potential benefits of combining DNN with DSM.
References in corpus (7)
- Deep D-bar: Real time Electrical Impedance Tomography Imaging with Deep Neural Networks
- Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
- Solving Electrical Impedance Tomography with Deep Learning
- A Group of Immersed Finite Element Spaces For Elliptic Interface Problems
- A Convergent Adaptive Finite Element Method for Electrical Impedance Tomography
- A Fixed Mesh Method With Immersed Finite Elements for Solving Interface Inverse Problems
- A Direct Sampling Method for Simultaneously Recovering Inhomogeneous Inclusions of Different Nature