Tianguo Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Tianguo Yuan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jiyang Xie
School of Physics, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Xiaolin Yang
School of Physics, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Yang Li
School of Physics, University of Electronic Science and Technology of China, Chengdu, China
3 shared publications - Erda Wen
School of Physics, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications Xiaozhen Yang
School of Physics, University of Electronic Science and Technology of China, Chengdu, China
2 shared publications- Hongchun Yang
School of Physics, University of Electronic Science and Technology of China, Chengdu, China
1 shared publication
Latest Publications
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 25 (1) , 354-358
Tandem Generalized Variational Autoencoder Network for Multisolutions Inverse Design
Inspired by the variational autoencoder (VAE), we propose a novel multi-solutions strategy combined with a tandem neural network for inverse design and optimization problems. In the training, a latent vector $z$ is concatenated to perturb the $S_{11}$ as input to the decoder. Within this framework, a multi-band slotted dipole antenna is employed as an example to validate the feasibility of the proposed network. Experimental results demonstrate that the proposed method not only breaks the one-to-one limitation between inputs and outputs in neural networks to generate diverse solutions, but also significantly accelerates model convergence through the introduction of a tandem architecture, compared with conventional generative adversarial approaches. The network potentially provides an efficient framework for solving inverse problems involving multi-solutions and optimization.
- 28 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 25 (1) , 354-358
Tandem Generalized Variational Autoencoder Network for Multisolutions Inverse Design
Inspired by the variational autoencoder (VAE), we propose a novel multi-solutions strategy combined with a tandem neural network for inverse design and optimization problems. In the training, a latent vector $z$ is concatenated to perturb the $S_{11}$ as input to the decoder. Within this framework, a multi-band slotted dipole antenna is employed as an example to validate the feasibility of the proposed network. Experimental results demonstrate that the proposed method not only breaks the one-to-one limitation between inputs and outputs in neural networks to generate diverse solutions, but also significantly accelerates model convergence through the introduction of a tandem architecture, compared with conventional generative adversarial approaches. The network potentially provides an efficient framework for solving inverse problems involving multi-solutions and optimization.
- 17 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 24 (10) , 3345-3349
Time-Delay Error of Time-Domain Aperture Antennas
We innovatively propose the concept of time-delay error for time-domain aperture antennas, as a counterpart to phase error in frequency-domain aperture antennas, which reveals the physical limit of time-domain radiative field enhancement during spherical-to-planar wavefront transformation. By establishing a universal relationship between this limit and antenna dimensions, we provide a theoretical benchmark for evaluating the ultimate performance bounds of various time-domain field enhancement approaches under fixed-aperture constraints - a contribution of significant value to cutting-edge research in this field. Furthermore, through the co-design of multi-port and metamaterial lenses, we experimentally demonstrate the feasibility of approaching this physical limit, thereby paving the way for extending metamaterial lens applications to transient electromagnetic systems.
- 17 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 24 (10) , 3345-3349
Time-Delay Error of Time-Domain Aperture Antennas
We innovatively propose the concept of time-delay error for time-domain aperture antennas, as a counterpart to phase error in frequency-domain aperture antennas, which reveals the physical limit of time-domain radiative field enhancement during spherical-to-planar wavefront transformation. By establishing a universal relationship between this limit and antenna dimensions, we provide a theoretical benchmark for evaluating the ultimate performance bounds of various time-domain field enhancement approaches under fixed-aperture constraints - a contribution of significant value to cutting-edge research in this field. Furthermore, through the co-design of multi-port and metamaterial lenses, we experimentally demonstrate the feasibility of approaching this physical limit, thereby paving the way for extending metamaterial lens applications to transient electromagnetic systems.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 73 (10) , 8313-8318
Flex-Form Generative Neural Network for Multifrequency Modes Antennas
This communication introduces a Flex-form Generative Neural Network (FGNN) that is capable of inverse designing the dimensions of a multi-frequency modes antenna, which is implemented with a metallic monopole patch containing variable numbers of slots, based on a target reflection coefficient across 0.3-3 GHz. The FGNN integrates three models: the Forward Prediction Model (FPM) for predicting the antenna’s reflection coefficient S11 based on geometric parameters, i.e., patch and slot dimensions, the Auxiliary Classification Model (ACM) for determining slots count, and finally the Inverse Design Model (IDM) for generating geometric parameters from the desired reflection coefficient. The proposed method enables flexible adjustment of antenna structure by allowing parameters output of indefinite-length. Antenna supporting up to three bands are achieved in this demonstration, with minimal amount of dataset required. The network potentially provides an efficient framework for various electromagnetic structures design with flexible forms of geometry parameters or targets.
- 8 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 73 (10) , 8313-8318
Flex-Form Generative Neural Network for Multifrequency Modes Antennas
This communication introduces a Flex-form Generative Neural Network (FGNN) that is capable of inverse designing the dimensions of a multi-frequency modes antenna, which is implemented with a metallic monopole patch containing variable numbers of slots, based on a target reflection coefficient across 0.3-3 GHz. The FGNN integrates three models: the Forward Prediction Model (FPM) for predicting the antenna’s reflection coefficient S11 based on geometric parameters, i.e., patch and slot dimensions, the Auxiliary Classification Model (ACM) for determining slots count, and finally the Inverse Design Model (IDM) for generating geometric parameters from the desired reflection coefficient. The proposed method enables flexible adjustment of antenna structure by allowing parameters output of indefinite-length. Antenna supporting up to three bands are achieved in this demonstration, with minimal amount of dataset required. The network potentially provides an efficient framework for various electromagnetic structures design with flexible forms of geometry parameters or targets.
- 22 February 2025
- Published by Elsevier in AEU - International Journal of Electronics and Communications
- Vol. 193
A high-gain, polarization-universal metasurface lens antenna for millimeter-wave communication
- 22 February 2025
- Published by Elsevier in AEU - International Journal of Electronics and Communications
- Vol. 193
A high-gain, polarization-universal metasurface lens antenna for millimeter-wave communication