Xiuzhu Ye

Xiuzhu Ye
Beijing Institute of Technology | BIT · School of Information and Electronics

PhD

About

60
Publications
3,157
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
307
Citations
Introduction
1. Microwave biomedical imaging 2. Computational imaging methods 3. Machine learning methods and traditional optimization methods 4. Antenna Engineering and related measurement issue
Additional affiliations
June 2019 - July 2020
Beijing Institute of Technology
Position
  • Professor (Associate)
December 2013 - present
Beihang University (BUAA)
Position
  • Professor (Assistant)
January 2012 - January 2013
National University of Singapore
Position
  • Research Associate
Education
August 2008 - May 2012
National University of Singapore
Field of study
  • electromagnetics, inverse scattering problem

Publications

Publications (60)
Article
In this paper, a unified learning-based approach is introduced to solve inverse scattering problems (ISPs) with mixed boundary conditions. The scattering behavior of hybrid dielectric and perfect electric conductors (PEC) scatterers is modeled by the T-matrix method. A rough image of the zero-order T-matrix coefficients for unknown scatterers is fi...
Article
The mechanism of reflective electromagnetic metasurfaces has potential applications in information transfer and electromagnetic scattering suppression. In the present research, the relation between the geometric entropy of the electromagnetic metasurface pattern and the scattering entropy of the metasurface is studied by introducing the power spect...
Article
The end-to-end scalable cascaded convolutional neural networks (SC-CNNs) are proposed to solve inverse scattering problems (ISPs), and the high-resolution image can be directly obtained from the scattered field with the guiding by multiresolution labels in the cascaded blocks. To alleviate the difficulty of solving the ISPs via a full-wave way, the...
Article
In this work, we introduce a learning-based method to achieve high-quality reconstructions for inverse scattering problems (ISPs). Particularly, the proposed method decouples the full-wave reconstruction model into two steps, including coarse imaging of dielectric profiles by the back-propagation scheme, and a resolution enhancement of coarse resul...
Article
Wideband operation ability becomes an obstacle for many metamaterial applications since they are generally based on effective material (medium) hypothesis, which is intrinsically functional on single frequency or narrowband. Effective biological camouflage strategies involve concealment under sunlight with multiple frequency (color) components, for...
Article
The repetitive computation of the forward problem in distorted Born iterative method (DBIM)-typed inversion method is time-consuming and memory-costly, especially in dealing with three-dimensional (3-D) inverse scattering problem. An improved subspace-regularized DBIM is proposed for the efficient solution of the 3-D inverse problem, which introduc...
Article
Deep learning based inverse scattering (DL-IS) methods attract much attention in recent years due to advantages of fast speed and high-quality reconstruction. The loss functions of neural networks in DL-IS methods are commonly based on a pixel-wise mean squared error (MSE) between the reconstructed image and its reference one. In this paper, we int...
Article
A deep learning-based inversion algorithm is developed to solve the inhomogeneous background inverse scattering problem (ISP). To alleviate the burden of nonlinearity and ill-posedness of the ISP, a noniterative method called the distorted-Born backpropagation scheme is introduced to quantitatively reconstruct a rough image of the unknown object in...
Article
Full-text available
Without phase information of the measured field data, the phaseless data inverse scattering problems (PD-ISPs) counter more serious nonlinearity and ill-posedness compared to full data ISPs (FD-ISPs). In this paper, we propose a learning-based inversion approach in the frame of the U-net convolutional neural network (CNN) to quantitatively image un...
Article
Various natural and artificial materials are anisotropic. The inverse scattering problem of anisotropic scatterers is widely involved in oil detection, nondestructive evaluation of composite materials and microscopic imaging of biological tissue. In this contribution, the two-dimensional inverse scattering problem of biaxial anisotropic scatterers...
Article
This paper presents a 1-D frequency diverse guided-wave imaging technique based on a surface-wave Goubau line. It employs frequency diversity to capture spatial information of the scatterers with an almost realtime speed, which is much faster than mechanical scanning or electronic scanning approaches. The surface-wave Goubau line is used because it...
Article
In this communication, a rectangular dielectric resonator antenna (DRA) is integrated with a backed cavity to enlarge the DRA side length by 1.8 times. The backed cavity also reduces the sensitivity of the DRA resonance to the DRA size, resulting in a relaxed fabrication tolerance. Based on the enlarged DRA design, a stacked DRA (sDRA) is proposed...
Article
circular aperture box-horn array antenna operating in W-band, with sum and difference radiation beams, is presented in this paper. The circular aperture provides maximum usage efficiency of the area, which is well-suited for rotational platform. A non-uniform power distribution is applied for the radiating elements, contributing to a radiation patt...
Article
This paper presents a new method to simultaneously image the perfect electric conductor (PEC) and dielectric scatterers together, which is based on the inversion algorithm subspace‐based distorted‐Born iterative method (S‐DBIM). Simulation results show that method is able to distinguish the PEC and dielectric and can retrieve the relative permittiv...
Article
A structure for the design of dual-band dualpolarized quasi-elliptic frequency selective surfaces (FSSs) is proposed in this letter, whose unit cell is comprised of multiple arrays of cylindrical dielectric resonators with capped annular ring resonators, inserted in a perforated metallic plate. The designed FSS provides quasi-elliptic filtering res...
Article
In this paper, a fast solution for microwave through wall imaging (TWI) with nonlinear inversion is proposed to reconstruct the unknown targets embedded in an inhomogeneous background medium. We treat inhomogeneous background, i.e., the wall around bounded in a finite domain as a known scatterer, which has the advantage of avoiding the time-consumi...
Article
A novel printed loop antenna with hybrid-coupled split ring resonators (SRRs) is proposed to realise multi-band and impedance-enhanced performances. Design guidelines and a step-by-step derivation of the proposed antenna based on SRRs are given in detail. On the basis of a one-wavelength rectangular loop, by splitting the left-/right-hand sides of...
Article
Full-text available
The electromagnetic inverse scattering problem can be effectively handled by means of the so-called distorted-Born iterative method (DBIM). A new method, denoted as the subspace-based distorted-Born iterative method (S-DBIM), is proposed. It updates the Green's function for the inhomogeneous background at each step of the iterative procedure, like...
Article
Full-text available
This paper proposes a multimode feed horn applied to a Cassegrain antenna operating at W-band. The horn is easily fabricated due to the simple structure. Comparisons are made between the performances of a 4-mode feed horn and a 7-mode feed horn. The 7-mode feed horn is finally adopted for two reasons. Firstly, the construction size is larger and th...
Conference Paper
Electromagnetic Inverse scattering problem has attracted vast attentions due to its wide application in geological exploration, security check, medical imaging and through wall imaging. The problem is commonly equivalent into a nonlinear optimization problem and regularization method is used to stabilize the ill-conditioned problem.
Article
An innovative methodology is proposed to solve quantitative three-dimensional microwave imaging problems formulated within the contrast source framework. The introduced technique is based on the combination of an efficient iterative multiscaling strategy aimed at mitigating local minimum issue arising in inverse scattering problems, and a local sea...
Conference Paper
A T-matrix based inversion algorithm is proposed to image the perfect electric conductor (PEC). The magnitude of the T-matrix serves as the parameter representing the scatterer. The method does not require any prior information such as the shape, location and number of the scatterers. Numerical result shows that the T-matrix method is able to clear...
Article
Full-text available
Based on optical frequency comb (OFC), a photonic-assisted ultra-broadband microwave signal down-converting method is proposed. In the proposed scheme, microwave signal at 2~20GHz can be down-converted to 0~1GHz intermediate frequency (IF) signals by an OFC of 2GHz frequency space at different order of comb lines. By slightly switching the frequenc...
Article
Full-text available
This paper introduces a general inversion method to simultaneously reconstruct scatterers with different boundary conditions such as Dirichlet, Neumann, Robin, and transmission boundaries without a priori information on their locations, shapes, or physical properties. The forward scattering of mixed scatterers is modeled by a unified framework of T...
Article
Full-text available
The practical problem of imaging scatterers enclosed by separable obstacles with mixed boundary is addressed. Both the unknown scatterers and the known obstacle media can be mixture of dielectric and perfect electric conducting (PEC) materials. The scattering phenomenon of such problem is well modeled by T-matrix method. By usage of separable prior...
Article
In this paper, a fast method for calculating full vectorial reflection and transmission near-fields of arbitrary finite sized beams through multilayer uniaxial anisotropic media is proposed. The method combines Transfer Matrix method and optical fast-Fourier-transform based angular spectrum (FFT-AS) method. This calculation method can be used in th...
Article
The fabrication precision of designed compact antenna test range (CATR) impacts the performance of quiet zone, especially in millimeter wave range. In this paper, several surface deviations of the reflector and their influence on the quiet zone are analyzed. Comparing the data of deviated reflector with those of the ideal reflector, it is found tha...
Article
Full-text available
A T-matrix method is proposed to solve the mixed boundary inverse scattering problem, i.e., perfect electric conductors (PEC) and dielectric scatterers are simultaneously reconstructed under the two-dimensional transverse magnetic (TM) illumination setting. Both the dipole and monopole elements of the T-matrix are chosen to accurately describe the...
Article
Full-text available
The practical problem of imaging scatterers that are separable from the known obstacles is addressed. Using such a priori information, the obstacle is regarded as a known scatterer rather than part of the background and can be excluded from the retrieving process by reformulating the cost function. As a result, the proposed method transforms the pr...
Conference Paper
This paper investigates the influence of the regularization term on the performance of the continuous-parameter subspace based optimization method in reconstructing perfectly electric conductors (PEC), which provides a theoretical explanation to the choice of regularization term. The number of leading singular values of a current-to-field mapping o...
Article
Full-text available
In this paper, an improved version of the subspace-based optimization method (SOM) is proposed to reconstruct perfectly electric conductor (PEC) scatterers using electromagnetic scattering data. The background medium, together with scatterers of arbitrary number and arbitrary shapes, is effectively expressed as a vector that facilitates to build up...
Article
Full-text available
This paper investigates the optimization progress of the continuous-type subspace based optimization method (SOM) for reconstructing perfect electric conductors (PEC). The total electric field and the induced current inside the reconstructed scatterers are investigated during optimization process. It is found that the electric field will vanish ins...
Conference Paper
This paper investigates a regularization scheme in the recently proposed subspace-based optimization method for solving inverse scattering problems. The number of leading singular values of a current-to-field mapping operator is found to balance the accuracy and the stability of the solution. If the number of leading singular values is chosen as a...
Article
Full-text available
Reconstruction of perfectly electric conductors (PEC) with transverse magnetic (TM) illumination by a subspace-based optimization method (SOM) is presented. Apart from the information that the unknown object is PEC, no other prior information such as the number of the objects, the approximate locations or the centers is needed. The whole domain is...

Network

Cited By

Projects

Project (1)
Project
To develop an imaging system hybrid with inverse scattering method to solve the brain stroke monitoring issue