YZYali Zong

Yali Zong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yali Zong has a total of 60 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Fast Physics-Driven Fourier-Spectral Solver for Highly Nonlinear Inverse Scattering Problems

    by Yutong Du, Zicheng Liu, Yi Huang, Bazargul Matkerim, Bo Qi, Yali Zong, Peixian Han

    Physics-driven neural solvers can reconstruct strongly nonlinear inverse scattering scenes without supervised training, but their per-instance optimization over pixel-wise unknowns is computationally expensive. This letter presents a fast physics-driven Fourier-spectral solver for two-dimensional transverse-magnetic inverse scattering. The induced current is parameterized in a truncated Fourier basis, so that the reconstruction is carried out in a compact spectral space rather than on dense spatial grids. To improve robustness in high-contrast regimes, a contraction integral equation is incorporated into the physics-consistency model. In addition, a contrast-compensated operator is introduced to alleviate boundary attenuation caused by spectral truncation, and a bridge-suppressing loss is designed to reduce false connections between adjacent scatterers. A lightweight fully connected network, initialized from a back-propagation-based estimate, optimizes the spectral coefficients for each measurement instance. Numerical examples and Fresnel experimental data show that the proposed method preserves the main target topology and quantitative contrast with sub-second reconstruction time. Compared with representative spatial-domain physics-driven solvers, it achieves nearly two orders of magnitude acceleration while maintaining competitive reconstruction quality, which is promising for fast microwave imaging applications.

  • Field Reconstruction for High-Frequency Electromagnetic Exposure Assessment Based on Deep Learning

    by Miao Cao, Zicheng Liu, Bazargul Matkerim, Tongning Wu, Changyou Li, Yali Zong, Bo Qi

    Fifth-generation (5G) communication systems, operating in higher frequency bands from 3 to 300 GHz, provide unprecedented bandwidth to enable ultra-high data rates and low-latency services. However, the use of millimeter-wave frequencies raises public health concerns regarding prolonged electromagnetic radiation (EMR) exposure. Above 6 GHz, the incident power density (IPD) is used instead of the specific absorption rate (SAR) for exposure assessment, owing to the shallow penetration depth of millimeter waves. This paper proposes a hybrid field reconstruction framework that integrates classical electromagnetic algorithms with deep learning to evaluate the IPD of wireless communication devices operating at 30 GHz, thereby determining compliance with established RF exposure limits. An initial estimate of the electric field on the evaluation plane is obtained using a classical reconstruction algorithm, followed by refinement through a neural network model that learns the mapping between the initial and accurate values. A multi-antenna dataset, generated via full-wave simulation, is used for training and testing. The impacts of training strategy, initial-value algorithm, reconstruction distance, and measurement sampling density on model performance are analyzed. Results show that the proposed method significantly improves reconstruction accuracy, achieving an average relative error of 4.57%for electric field reconstruction and 0.12 dB for peak spatial-average IPD estimation on the test dataset. Additionally, the effects of practical uncertainty factors, including probe misalignment, inter-probe coupling, and measurement noise, are quantitatively assessed.

  • Improved Physics-Driven Neural Network for Solving Inverse Scattering Problems

    by Yutong Du, Zicheng Liu, Bo Wu, Jingwei Kou, Hang Li, Changyou Li, Yali Zong, Bo Qi

    This paper presents an improved physics-driven neural network (IPDNN) framework for solving electromagnetic inverse scattering problems (ISPs). Unlike data-driven solvers that require large labeled datasets and often suffer from limited generalization, the proposed method performs instance-wise optimization under electromagnetic governing equations and measured scattered-field constraints. Three improvements over the original PDNN framework are introduced. First, a Gaussian-localized oscillation-suppressing window (GLOW) activation function is designed to stabilize convergence and enable a lightweight yet accurate network architecture. Second, a dynamic scatter subregion identification strategy is further developed to adaptively refine the computational domain, preventing missed detections and reducing computational cost. Third, transfer learning is incorporated to extend the solver’s applicability to practical scenarios, integrating the physical interpretability of iterative algorithms with the approximation capability of neural networks. Numerical and experimental results on representative Fresnel datasets show that the proposed IPDNN achieves up to a 57% reduction in reconstruction error while maintaining robust performance under noise levels up to 50%. Under the current implementation, the proposed FCN-based realization also requires substantially less training memory than the original PDNN. These results demonstrate that IPDNN provides a more accurate and practically extensible physics-driven framework for electromagnetic inverse scattering.

  • Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems

    by Yutong Du, Zicheng Liu, Bazargul Matkerim, Changyou Li, Yali Zong, Bo Qi, Jingwei Kou

    In recent years, deep learning-based methods have been introduced for solving inverse scattering problems (ISPs), but most of them heavily rely on large training datasets and suffer from limited generalization capability. In this paper, a new solving scheme is proposed where the solution is iteratively updated through a physics-driven neural network (PDNN), the hyperparameters of which are optimized by minimizing the loss function which incorporates the constraints from measured scattered fields and the prior information about scatterers. Unlike data-driven neural network solvers, PDNN does not require an offline training dataset. Its weights are iteratively updated based solely on the measured incident and scattered fields, similar in philosophy to conventional inverse algorithms but enhanced by neural-network flexibility. Thus, the generalization issue is eliminated. Moreover, to accelerate the imaging, a subregion enclosing the scatterers is automatically identified and used to restrict the computational domain. Numerical and experimental results demonstrate that the proposed scheme achieves high reconstruction accuracy and strong stability, even for complex and lossy scatterers.


  • Design of Multiband Patch Antennas Using Adaptive Topology Optimization Method

    by Xinyu Ma, Yali Zong, Peihua Zhang, Jian Chen, Zhiyi Ren, Zicheng Liu, Changyou Li

    The rapid development of modern communication systems drives an urgent need for multiband antenna solutions. Patch antennas are widely used in mobile communication systems due to their simple structure, low profile, and other inherent advantages. They are also compatible with most compact mobile devices. Traditional microstrip patch antenna designs often rely heavily on the designer’s experience. This reliance can introduce uncertainty in both performance and design cycle, which limits the effective design and deployment of antennas with complex or diverse requirements. To address this problem, an adaptive topology optimization method is proposed, in which the material distribution serves as the design variable. The optimization process adaptively determines material distribution within the design domain to achieve the target performance. Because this method does not rely on prior design experience, it can effectively enhance design performance and efficiency. The proposed method is applied to the design of a tri-band microstrip patch antenna that supports WiFi/2.4 GHz and 5G/sub-6 GHz communication. The performance across these bands is jointly optimized using an adaptive interpolation model and a loss function embedded in the objective function. Numerical results show that optimizing the topology of the radiating patch effectively improves the reflection coefficient at the target frequencies. The test data of the fabricated prototype show strong agreement with the numerical simulations. The results indicate that the proposed antenna design method provides key advantages, including intelligent tunability and flexible structural control. These features allow for convenient and rapid achievement of desired performance metrics. This approach also provides valuable insights for addressing the evolving requirements of patch antennas in various fields.


  • Quality-Factor-Inspired Deep Neural Network Solver for Solving Inverse Scattering Problems

    by Yutong Du, Zicheng Liu, Miao Cao, Zupeng Liang, Yali Zong, Changyou Li

    Deep neural networks (DNNs) have been applied to address electromagnetic inverse scattering problems (ISPs) and shown superior imaging performances, which can be affected by the training dataset, the network architecture, and the applied loss function. Here, the quality of data samples is concerned and valued by the defined quality factor. Based on the quality factor, the composition of the training dataset is optimized. The network architecture is integrated with the residual connections and channel attention mechanism to improve feature extraction. A loss function that incorporates data-fitting error, physical information constraints, and the desired feature of the solution is designed and analyzed to suppress the background artifacts and improve the reconstruction accuracy. Various numerical analyses are performed to demonstrate the superiority of the proposed quality-factor-inspired DNN (QuaDNN) solver, and the imaging performance is finally verified by experimental imaging tests.


  • Beam Compensation of Planar Arrays for Microwave Power Transmission with Pointing Errors

    by Kang Wang, Yali Zong

    The establishment of the space solar power station (SSPS) provides a way to solve the energy crisis fundamentally, some of the implementation schemes and instructive theory about SSPS are still in the process of research. Due to some uncertainties in the space of the transmitting antenna, the beam pointing of the transmitting antenna will be deviation, resulting in a decrease of wireless power transfer (WPT). In order to solve this problem, we propose a research scheme for beam compensation of the transmitting antenna using non-dominated sorting genetic algorithm-II (NSGA-II). In this process, the paper equivalents the three-objective programming problem as dual-objective programming, which greatly reduces the amount of calculation and improves the calculation speed. The results show that by optimizing the phase of the 8*8 array’s 64 elements, the beam direction adjustment from (1°, 1°) to (0°,0°) is achieved, and the antenna gain is improved by about 0. 5dB. This strategy allows the transmitted power of the antenna to be concentrated as much as possible in the receiving area of the receiving antenna.

  • Inverse Scattering Solver Based on Deep Neural Network With Total Variation Regularization

    by Jie Ma, Zicheng Liu, Yali Zong

    Deep neural network (DNN) techniques have been applied to solve nonlinear electromagnetic inverse scattering problems (ISP) and shown potentials in superior imaging performances over traditional methods. In DNN ISP solvers, data features are learned from imaging samples to accurately represent the contrast distribution through the optimization of hyper-parameters of neural network, while the loss function which often quantifies discrepancies between the predicted imaging result and the ground truth is targeted to be minimized in the training process. In this paper, to further make use of the (piece-wise) smoothness of the contrast distribution, the desired solution is regularized by additionally penalized its total variation (TV) in the loss function. Effects of the TV regularization on the DNN ISP solver are studied and summarized with various simulation settings and the improvement in imaging performance is verified based on experiment data.