In this paper, a new deep learning approach is proposed to solve the electromagnetic inverse scattering (EMIS) problems. The conventional methods for solving inverse problems face various challenges including strong ill-conditions, high contrast, expensive computation cost and unavoidable intrinsic nonlinearity. To overcome these issues, we propose a new two-step machine learning based approach. In the first step, a complex-valued deep convolutional neural network (DConvNet) is employed to retrieve initial contrasts (permittivities) of dielectric scatterers from measured scattering data. In the second step, the previously obtained contrasts are input into a complex-valued deep residual convolutional neural network (DRCNN) to refine the reconstruction of images. Consequently, the EMIS problem can be solved with much higher accuracy even for high-contrast objects. Numerical examples have demonstrated the capability of the newly proposed method with the improved accuracy. The proposed deep learning approach for EMIS problem serves a new path for realizing real-time quantitative microwave imaging for high-contrast objects.

A general and systematic approach is the first time proposed in this paper to design the neutralization line (NL) for isolation enhancement in multiple-input multiple-output (MIMO) antenna arrays. Each NL consists of a metal strip and a reactive component attached at its middle position. It is connected with every two antenna radiators to generate an additional coupling path against the original antenna coupling for isolation enhancement. A general network model that leads to a systematic design procedure is developed to meet the required isolation criteria. Three practical examples are presented and used to verify the proposed NL-based decoupling technique (DT). The measurement results align well with simulations. For all these examples, good impedance matching, isolation over 25 dB, total radiation efficiencies over 70%, and very low envelop correlation coefficients (ECCs) can be achieved simultaneously after adopting the proposed NL DT. Compared with previous decoupling works using parasitic elements, decoupling networks or NLs, the proposed method can achieve either a much wider decoupling bandwidth or a much smaller antenna separation distance while keeping a low design complexity along with systematic design procedure.

Graphene is an ideal 2D material system bridging electronic and photonic devices. It also breaks the fundamental speed and size limits by electronics and photonics, respectively. Graphene offers multiple functions of signal transmission, emission, modulation, and detection in a broad band, high speed, compact size, and low loss. Here, we have a brief view of graphene based functional devices at microwave, terahertz, and optical frequencies. Their fundamental physics and computational models were discussed as well.

This paper proposes a novel deep learning (DL) approach to resolve the electromagnetic inverse scattering (EMIS) problems. The conventional approaches of resolving EMIS problems encounter assorted difficulties, such as high contrast, high computational cost, inevitable intrinsic nonlinearity and strong ill-posedness. To surmount these difficulties, a novel DL approach is proposed based on a novel complex-valued deep fully convolutional neural network (DConvNet) structure. The proposed complex-valued deep learning model for solving EMIS problems composes of an encoder network and its corresponding decoder network, followed by a final pixel-wise regression layer. The complex-valued encoder network extracts feature fragments from received scattered field data, while the role of the complex-valued decoder network is mapping the feature fragments to retrieve the final contrasts (permittivities) of dielectric scatterers. Hence, the proposed deep learning model functions as an “heterogeneous” transformation process, where measured scattering field data is converted into the corresponding contrasts of scatterers. As a consequence, the EMIS problem could be resolved accurately even for extremely high-contrast targets. Numerical benchmarks have illustrated the feasibility and accuracy of our proposed approach. The proposed approach opens a novel path for the deep learning based real-time quantitative microwave imaging for high-contrast scatterers.

We present a comprehensive review on the geometric-phase based metasurfaces for orbital angular momentum (OAM) generation and detection. These metasurfaces manipulate the electromagnetic (EM) wave by introducing abrupt phase change, which is strongly dependent on the polarization state of incident EM wave and can be interpreted by geometric phase. Hence, the conventional bulk devices that based on the accumulated phase change along the optical path can be avoided.

In this paper, a novel absorbing boundary condition (ABC) computation method for Finite-Difference Time-Domain (FDTD) is proposed based on the machine learning approach. The hyperbolic tangent basis function (HTBF) neural network is introduced to replace traditional perfectly matched layer (PML) ABC during the FDTD solving process. The field data on the interface of conventional PML are employed to train HTBF based PML model. Compared to the conventional approach, the novel method greatly decreases the size of computation domain and the computation complexity of FDTD because the new model only involves the one-cell boundary layer. Numerical examples are provided to benchmark the performance of the proposed method. The results demonstrate that the newly proposed method could replace conventional PML and could be integrated into FDTD solving process with satisfactory accuracy and compatibility to FDTD. According to our knowledge, this proposed model combined ANN model is an unreported new approach based on machine learning based for FDTD.