Li-Ye Xiao

Prof. Dr. Li-Ye Xiao


Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 April 2021 in IEEE Transactions on Antennas and Propagation
Verified
Journal Article
Closed access
LXLi-Ye Xiao
Li-Ye Xiao
WSWei Shao
Wei Shao
FJFu-Long Jin
Fu-Long Jin
BWBing-Zhong Wang
Bing-Zhong Wang
QLQing Huo Liu
Qing Huo Liu
To improve the convenience and efficiency of antenna design, in this article, a novel inverse artificial neural network (ANN) model is proposed in which antenna performance indexes are set as the input and corresponding geometrical variables are set as the output. To solve the multiobjective problem of antenna modeling, the first part of the ANN model involves three parallel and independent branches for S -parameter, gain, and radiation pattern, and the second part outputs a final predicted result. Once the training is completed, the proposed inverse model can provide antenna geometries directly without being repetitively called by an optimization algorithm. Compared with the inverse extreme learning machine and five state-of-art forward models, the proposed model uses a small number of training samples and directly obtains the satisfying values of geometrical variables without any optimization process.

1 March 2020 in Applied Energy
Verified
Journal Article
Closed access
ZWZhuochun Wu
Zhuochun Wu
XXXiangjie Xia
Xiangjie Xia
LXLi-Ye Xiao
Li-Ye Xiao
YLYilin Liu
Yilin Liu

9 August 2018 in IEEE Transactions on Microwave Theory and Techniques
Verified
Journal Article
Closed access
LXLi-Ye Xiao
Li-Ye Xiao
WSWei Shao
Wei Shao
Xiao DingXiao Ding
Xiao Ding
BWBing-Zhong Wang
Bing-Zhong Wang
A dynamic adjustment kernel extreme learning machine with transfer functions is proposed for parametric modeling of the electromagnetic behavior of microwave components. If satisfactory accuracy has not been obtained, the proposed model, which supports the functionalities of increased learning, reduced learning, and hybrid learning, can utilize the overlap between the old training data set and the new one to achieve the accurate trained results with faster retraining. The validity of the proposed model is confirmed with two examples of a microstrip-to-microstrip vertical transition and a quadruple-mode filter.

30 April 2020 in IEEE Transactions on Antennas and Propagation
Verified
Journal Article
Closed access
LXLi-Ye Xiao
Li-Ye Xiao
JLJiawen Li
Jiawen Li
FHFeng Han
Feng Han
WSWei Shao
Wei Shao
QLQing Huo Liu
Qing Huo Liu
A dual-module machine learning scheme is proposed to reconstruct inhomogeneous scatterers with high contrasts and large electrical dimensions. The first nonlinear mapping module (NMM) is an extreme learning machine (ELM) which is used to convert the measured scattered fields at the receiver arrays into preliminary images of the scatterers. The second image enhancing module (IEM) is a convolutional neural network (CNN) which is used to further refine the images from NMM to obtain high-accuracy pixel-based model parameter distribution in the inversion domain. Compared with the traditional approximate methods such as backpropagation, the NMM-IEM machine learning can produce the preliminary image with much higher accuracy but the unknown weight matrices of the ELM are only solved for once during training. Hence, the IEM connected to NMM has a simple architecture and can be trained at a rather low cost. The performance of the proposed dual-module NMMIEM scheme and the conventional variational Born iterative method is compared in terms of inversion of scatterers with different electrical sizes and contrasts. Meanwhile, the NMMIEM is also assessed for the inversion of scatterers with high contrasts and large electrical dimensions and experimental data. Finally, the NMM-IEM is compared with CNNs used in the previous works.

12 December 2023 in IEEE Transactions on Antennas and Propagation
Verified
Journal Article
Closed access
LXLi-Ye Xiao
Li-Ye Xiao
YCYu Cheng
Yu Cheng
YLYan-Fang Liu
Yan-Fang Liu
FJFu-Long Jin
Fu-Long Jin
QLQing Huo Liu
Qing Huo Liu
To efficiently and conveniently realize the topology design with many degrees of freedom (DoFs), this work proposes an inverse topological design method (ITDM) based on machine learning for frequency selective surface (FSS) structures from a novel perspective. In the proposed ITDM, the input is a set of desired | S 11 | curves, and the output is the predicted FSS structure presented as an image to directly reveal the distribution of binary pixels in the modeling domain. To obtain the training dataset, an efficient training dataset construction strategy is proposed based on several classical FSS structures. The advantage of this approach is that the training samples can be guaranteed with high-quality, thus the convergence of the model is faster. Two numerical examples of single-layer and double-layer FSS structures involving large numbers of binary variables (900 and 1800, respectively) are employed to validate the effectiveness of the proposed ITDM. Meanwhile, the fabricated topological structures are also measured to verify the performance of a designed FSS obtained from ITDM.

22 February 2019 in IEEE Transactions on Antennas and Propagation
Verified
Journal Article
Closed access
LXLi-Ye Xiao
Li-Ye Xiao
WSWei Shao
Wei Shao
Xiao DingXiao Ding
Xiao Ding
QLQing Huo Liu
Qing Huo Liu
WJWilliam T. Joines
William T. Joines