A neural network approach to the microwave inverse scattering problem with edge-preserving regularization

Radio Science ◽  
2001 ◽  
Vol 36 (5) ◽  
pp. 825-832
Author(s):  
Xing Gong ◽  
Yuanmei Wang
Keyword(s):  
Neural Network ◽  
Inverse Scattering ◽  
Scattering Problem ◽  
Inverse Scattering Problem ◽  
Network Approach ◽  
Neural Network Approach ◽  
Edge Preserving

Neural network application to the inverse scattering problem in high-resolution X-ray diffraction

2001 ◽  
Vol 34 (3) ◽  
pp. 336-342 ◽  
Author(s):  
Christ Glorieux ◽  
Emil Zolotoyabko
Keyword(s):  
Neural Network ◽  
High Resolution ◽  
Inverse Scattering ◽  
Scattering Problem ◽  
Inverse Scattering Problem ◽  
X Ray Diffraction ◽  
Near Surface ◽  
X Ray ◽  
Neural Network Algorithm ◽  
Performance Statistics

The complicated inverse scattering problem of reconstructing depth-dependent lattice parameters from high-resolution X-ray diffraction spectra is analysed by using neural networks. Attention is paid to the practically important case of structural modifications in the near-surface layers of ion-implanted single crystals. The feasibility of a neural network algorithm is assessed on the basis of the performance statistics on a large number of simulated examples. The performance of the method on experimental data is tested using high-resolution X-ray diffraction spectra taken from He-implanted lithium niobate crystals.

scholarly journals A neural network method for the inverse scattering problem of impenetrable cavities

2020 ◽  
Vol 28 (2) ◽  
pp. 1123-1142
Author(s):  
Weishi Yin ◽  
◽  
Jiawei Ge ◽  
Pinchao Meng ◽  
Fuheng Qu ◽  
...  
Keyword(s):  
Neural Network ◽  
Inverse Scattering ◽  
Scattering Problem ◽  
Inverse Scattering Problem ◽  
Neural Network Method ◽  
Network Method

scholarly journals Complex-Valued Pix2pix—Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering

Electronics ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 752
Author(s):  
Liang Guo ◽  
Guanfeng Song ◽  
Hongsheng Wu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Inverse Scattering ◽  
Scattering Problem ◽  
Computational Cost ◽  
Inverse Scattering Problem ◽  
Generative Adversarial Network ◽  
Realistic Interaction ◽  
Complex Valued ◽  
Electromagnetic Inverse Scattering

Nonlinear electromagnetic inverse scattering is an imaging technique with quantitative reconstruction and high resolution. Compared with conventional tomography, it takes into account the more realistic interaction between the internal structure of the scene and the electromagnetic waves. However, there are still open issues and challenges due to its inherent strong non-linearity, ill-posedness and computational cost. To overcome these shortcomings, we apply an image translation network, named as Complex-Valued Pix2pix, on the inverse scattering problem of electromagnetic field. Complex-Valued Pix2pix includes two parts of Generator and Discriminator. The Generator employs a multi-layer complex valued convolutional neural network, while the Discriminator computes the maximum likelihoods between the original value and the reconstructed value from the aspects of the two parts of the complex: real part and imaginary part, respectively. The results show that the Complex-Valued Pix2pix can learn the mapping from the initial contrast to the real contrast in microwave imaging models. Moreover, due to the introduction of discriminator, Complex-Valued Pix2pix can capture more features of nonlinearity than traditional Convolutional Neural Network (CNN) by confrontation training. Therefore, without considering the time cost of training, Complex-Valued Pix2pix may be a more effective way to solve inverse scattering problems than other deep learning methods. The main improvement of this work lies in the realization of a Generative Adversarial Network (GAN) in the electromagnetic inverse scattering problem, adding a discriminator to the traditional Convolutional Neural Network (CNN) method to optimize network training. It has the prospect of outperforming conventional methods in terms of both the image quality and computational efficiency.

Sign in / Sign up

Export Citation Format

Share Document