- Microwave Engineering and Waveguides
- Advanced Computational Techniques and Applications
- Radio Wave Propagation Studies
- Millimeter-Wave Propagation and Modeling
- Soil Moisture and Remote Sensing
- Advanced Adaptive Filtering Techniques
- Advanced Antenna and Metasurface Technologies
- Magnetic Properties and Applications
- Sensor Technology and Measurement Systems
- Antenna Design and Analysis
Tianjin University
2023-2025
Nankai University
2025
Recently, neuro-transfer function (neuro-TF) has become a recognized method for electromagnetic (EM) parametric modeling. The existing neuro-TF methods use the vector fitting technique to perform transfer (TF) parameter extraction, commonly encountering nonsmoothness and discontinuity issues extracted TF parameters with respect geometrical parameters. This letter proposes an advanced autoencoder extraction modeling of microwave components. In proposed technique, is introduced extract set as...
This letter proposes a novel neuro-coupling matrix (neuro-CM) technique for parametric modeling of microwave filters. It is the first time to combine coupling (CM) and neural networks calculating intermediate variables learn relationship between geometrical parameters electromagnetic (EM) response A center-out optimization method proposed extract CM as training data more effectively, which provides much continuous than vector fitting. Compared with existing neuro-transfer function (neuro-TF)...
Microwave inverse modeling using artificial neural network (ANN) can quickly and accurately obtain geometric or physical parameters according to the optimization target. However, there exists problem of multivalued solutions for ANN. Ordinary ANN can't solve this problem. This paper aims apply a fourth-order microwave filter