Lijun Jiang

In this paper, we introduce an innovative deep learning (DL) methodology designed for real-time quantitative microwave imaging (MWI). Our approach is centered around the utilization of a deep convolutional asymmetric encoder-decoder structure (DCAEDS), which requires only a single-frequency far-field measurement of the electromagnetic (EM) scattered field as input and subsequently predicts the contrasts (permittivities) of the target materials. During the offline training process, we incorporate an EM forward solver specifically crafted to compute the EM scattered field generated by the predicted target contrasts (permittivities) produced by the DCAEDS. The DCAEDS is seamlessly integrated with this EM forward solver to optimize the loss function. This loss function comprises two fundamental components: (1) Data-induced loss, directly quantifying the dissimilarity between the predictions of our proposed DCAEDS and the actual labels for the target contrasts (permittivities); (2) Physics-induced loss, evaluating the distinctions between the measured EM scattered field and the computed EM scattered field derived from the predicted target contrasts (permittivities) generated by the DCAEDS. Our DL approach excels in delivering precise results, even for high-contrast targets, overcoming limitations associated with conventional methods, such as computational cost and ill-conditioning. Numerical benchmarks using dielectric targets underscore the practicality and effectiveness of our DL-based approach.

This paper presents a hybrid data-driven method, termed moving average-Hankel-dynamic mode decomposition (MAHankDMD), for joint direction of arrival (DOA) and frequency estimation in environments affected by both radio frequency interference (RFI) and Gaussian white noise. The proposed approach integrates two key components: (1) a moving average-DMD filter that effectively mitigates Gaussian white noise and separates RFI from the source signal, and (2) a Hankel-DMD method that accurately estimates the DOA of the filtered signal and associates it with the corresponding frequency. The moving average-DMD stage first enhances the signal-to-noise ratio and improves the robustness of the estimation process through noise and inference mitigation, while the subsequent Hankel-DMD stage enables reliable parameter extraction even for overlapping sginals or strong interference conditions. Numerical simulations demonstrate the robustness of MAHankDMD, showing its ability to precisely estimate both DOA and frequency under challenging conditions involving RFI and Gaussian white noise interference. The proposed algorithm thus provides an effective solution for channel parameter estimation in complex noisy environments.

This paper introduces a recursive parallel dynamic mode decomposition (RPDMD) scheme tailored for multidimensional harmonic retrieval (MHR), specifically applied to MIMO wireless channel sounding. The RPDMD algorithm is devised to address the complexities inherent in multidimensional scenarios, leveraging the dynamic mode decomposition (DMD) framework within a recursive parallel structure. Initially, the observed tensorial multidimensional harmonic data is transformed into a two-dimensional matrix format along the r-th dimension. Subsequently, DMD dissects this matrix data into eigenvalues and their associated modes. The real and imaginary components of the DMD eigenvalues yield damping factors and frequencies in the r-th dimension, respectively. Furthermore, recursive DMD is employed to scrutinize each mode independently for parameter retrieval across the remaining dimensions, enabling parallel analysis. Ultimately, this high-dimensional correlated decomposition scheme delivers paired damping factors and frequencies for all tones. Notably, the proposed approach can ascertain the number of tones in undamped sinusoidal signals, making it particularly suitable for MHR even without prior knowledge of the source count. Numerical experiments demonstrate the accuracy and robustness of the RPDMD scheme, with comparative analysis indicating that RPDMD outperforms similar methods, achieving optimal results with minimal mean square error in high signal-to-noise ratio scenarios. This work presents an effective data-driven solution for the MHR problem in MIMO wireless channel sounding.

This paper proposes a novel coupling-informed data-driven algorithm tailored for the concurrent estimation of frequency and angle within a uniform linear array (ULA), while addressing the complicating influence of mutual coupling. Leveraging the hybrid dynamic mode decomposition (DMD) methodology, termed as averaged DMD, we incorporate moving average techniques to achieve effective denoising. The averaged DMD further decomposes the received signal into eigenvalues and corresponding eigenvectors. The frequency information is derived from the eigenvalues and the corresponding eigenvectors represent the steering vectors of sources. Subsequently, mutual coupling is informed into the calibration of the steering vector for each source. Specifically, the calibration of corresponding eigenvectors leverage the inverse of the mutual coupling matrix, i.e., Toeplitz matrix, acquired through Schur decomposition. Then, the calibrated steering vectors facilitate the estimation of angles. The decomposition results of our proposed method reveal a significant one-to-one correspondence between eigenvectors and eigenvalues, enabling the automatic pairing of estimated frequencies and angles. Several numerical examples demonstrate the effectiveness and robust anti-noise properties of the proposed method, especially in scenarios where mutual coupling has a significant impact. Hence, our work contributes to the advancement of signal processing techniques in ULA applications, offering a promising avenue for enhanced performance in practical communication and radar systems.

This article presents a novel hybrid approach for electromagnetic near-field scanning, combining model-based, i.e., Gaussian processes regression, and data-driven, i.e., dynamic mode decomposition, techniques. We first leverage the Latin hypercube sampling technique to achieve spatially sparse measurements. Subsequently, dynamic mode decomposition is applied to analyze the resulting spatiotemporal data with sparse spatial sampling, enabling the extraction of both frequency information and sparse dynamic modes. Finally, the Gaussian processes regression, also known as the Kriging method, is adopted for the full-state reconstruction. The proposed hybrid approach is benchmarked by an example of the crossed dipole antennas. The obtained results demonstrate that with a sparse spatial sampling factor of 130, the proposed approach can achieve a complete reconstructed field distribution suitable for engineering applications, along with accurate extraction of frequency information. Consequently, our hybrid framework offers a promising avenue for augmenting the efficiency and accuracy of electromagnetic near-field scanning, with the potential for application in diverse electromagnetic measurement scenarios.

This paper proposes a novel deep learning (DL) framework for the electromagnetic inverse scattering (EMIS) problems. Solving EMIS problems is the challenging topic due to various difficulties, such as intrinsic nonlinearity, high computation cost, high contrast, etc. To overcome these challenges, a novel DL-inspired approach is presented in the context of Conditional Deep Convolutional Generative Adversarial Network (CDCGAN), termed as CDCGAN-EMIS. The proposed CDCGAN is based on a Generator with EM forward solver and the corresponding Discriminator, both constructed by complex-valued deep convolutional neural networks (DConvNets). During the offline training step, the generator learns a distribution between the measured scattered field data and the corresponding contrasts (permittivities) of dielectric scatterers, while the discriminator determines whether the presented samples are real or fake. Therefore, such CDCGAN-EMIS can generate contrasts of scatterers from measured scattered field data, by learning the distribution between the known contrasts of scatterers and their corresponding field and generating solutions. Based on the proposed CDCGAN-EMIS, EMIS problems can be accurately solved even for extremely high-contrast scatterers. Numerical examples indicate the accuracy and feasibility of our method. The proposed CDCGAN-EMIS opens a novel path for the DL-inspired real-time quantitative microwave imaging method for high-contrast scatterers.