Jiangtao Su

Jiangtao Su

Auto-generated profile, based on publicly available information

Jiangtao Su

Innovation Center for Electronic Design Automation, Hangzhou Dianzi University, Hangzhou, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
3 April 2019 in IEEE Transactions on Microwave Theory and Techniques
Verified
Journal Article
Closed access
JCJialin Cai
Jialin Cai
JKJustin B. King
Justin B. King
JSJiangtao Su
Jiangtao Su
CYChao Yu
Chao Yu
SCShichang Chen
Shichang Chen
JLJun Liu
Jun Liu
A new, frequency-domain, behavioral modeling methodology for gallium nitride (GaN) high-electron-mobility transistors (HEMTs), based on the Bayesian inference theory, is presented in this paper. Several different probability distribution (kernel) functions are examined for the Bayesian-based modeling architecture, with the optimal kernel function identified through experimental testing. These results are compared to an alternative approach based on the artificial neural networks (ANNs), with the data showing that the proposed approach demonstrates improved accuracy, while at the same time, alleviating the well-known ANN overfitting issue. Model verification is performed at the fundamental and harmonic frequencies using the identified optimal kernel, through comparisons with simulated data from a reference nonlinear circuit model, and with experimental data from separate 2- and 10-W GaN HEMT devices, over a wide range of load conditions. The models can predict accurately the optimal area of the fundamental output power on the Smith chart and the area of optimal power efficiency. Furthermore, the ability of the model to interpolate across input power levels and input frequencies is also tested, with excellent fidelity to the simulated and measured data obtained.

21 December 2022 in IEEE Transactions on Microwave Theory and Techniques
Verified
Journal Article
Closed access
KXKuiwen Xu
Kuiwen Xu
ZQZemin Qian
Zemin Qian
YZYu Zhong
Yu Zhong
JSJiangtao Su
Jiangtao Su
HGHaijun Gao
Haijun Gao
WLWenjun Li
Wenjun Li
Solving inverse scattering problems (ISPs) is challenging because of its intrinsic ill-posedness and the nonlinearity. When dealing with highly nonlinear ISPs, i.e., those scatterers with high contrast and/or electrically large size, the traditional iterative nonlinear inversion methods converge slowly and take lots of computation time, even maybe trapped into local wrong solution. To alleviate the above challenges, a learning-assisted (LA) inversion approach termed as the LA inversion method (LAIM) with advanced generative adversarial network (GAN) in virtue of a new recently established contraction integral equation for inversion (CIE-I) is proposed to achieve a good balance between the computational efficiency and the accuracy of solving highly nonlinear ISPs. The preliminary profiles composed of only small amount of low-frequency components can be got efficiently by the Fourier bases expansion of CIE-I inversion (FBE-CIE-I). The physically exacted information can be taken as the input of the neural network to recover super-resolution image with more high-frequency components. A weighted loss function composed of the adversarial loss, mean absolute percentage error (MAPE), and structural similarity (SSIM) is used under the pix2pix GAN framework. In addition, the self-attention module is used at the end of the generator network to capture the physical distance information between two pixels and enhance the inversion accuracy of the feature scatterers. To further improve the inversion efficiency, the data-driven method (DDM) is used to achieve real-time imaging by cascading U-net and pix2pix GAN, where U-net is used to replace FBE-CIE-I in the LAIM. Compared with other LA inversion, both the synthetic and experimental examples have validated the merits of the proposed LAIM and DDM.

5 February 2020 in IEEE Transactions on Microwave Theory and Techniques
Verified
Journal Article
Closed access
JCJialin Cai
Jialin Cai
JLJun Liu
Jun Liu
JSJiangtao Su
Jiangtao Su
LSLing-ling Sun
Ling-ling Sun
SCShichang Chen
Shichang Chen
JKJustin B. King
Justin B. King
A new, frequency-domain, behavioral modeling methodology for radio frequency (RF) power transistors, based on canonical section-wise piecewise linear (CSWPL) functions, is presented in this article. The basic theory of the proposed model for fundamental, harmonic, and dc responses is provided within. Compared with the existing nonlinear behavioral models, which require tables of coefficients to account for varying input powers, the model described in this article is able to predict transistor behavior over the entire Smith chart, at different levels of input power, from the linear region to strongly nonlinear region, with only a single set of model coefficients. Model verification is performed at fundamental, harmonic, and dc frequencies through comparisons with simulated data from a reference nonlinear circuit model and with experimental data from separate 10- and 2-W GaN HEMT devices, over a wide range of load conditions. The models can predict, accurately, the optimal area on the Smith chart for maximum fundamental output power. Furthermore, the ability of the model to interpolate across input power levels is also tested, with excellent fidelity to the simulated and measured data obtained. Compared with a 2-D polynomial-based model, the proposed method provides for a more accurate prediction, while using fewer model coefficients.

4 March 2025 in IEEE Transactions on Antennas and Propagation
Verified
Journal Article
Closed access
ZDZhengyue Dong
Zhengyue Dong
YHYuke He
Yuke He
KXKuiwen Xu
Kuiwen Xu
SHSHAOQING HU
SHAOQING HU
QLQinyi Lv
Qinyi Lv
WLWenjun Li
Wenjun Li
A novel two-step iterative optimization method could be used in microwave and mm-wave bands for optimal topology of 2-D sparse multiple input multiple output (MIMO) arrays and an improved back-projection algorithm (IBPA) for near-range scenarios have been proposed to achieve high-resolution three-dimensional (3D) imaging. According to point spread functions (PSF), the array topology results from the proposed design method has superior performance on sidelobe level both in the interference region (IR) and non-interference region (NIR), and the obtained peak sidelobe levels (PSLs) are lower than the conventional topologies over 2 dB. The IBPA has weighting factors incorporated into its forward physical wave equations to improve accuracy of the model. The imaging capabilities of the proposed array and IBPA have been experimentally verified. The proposed array could further mitigate the artifact distribution in target image than conventional arrays which is consistent to theoretical analysis. The proposed IBPA could provide higher resolution and lower PSLs without increasing the computational complexity.

1 January 2025 in IEEE Transactions on Microwave Theory and Techniques
Verified
Journal Article
Closed access
RWRuijin Wang
Ruijin Wang
JSJiangtao Su
Jiangtao Su
WXWeiyu Xie
Weiyu Xie
MXMengmeng Xu
Mengmeng Xu
ZLZhongjie Lin
Zhongjie Lin
LSLing-ling Sun
Ling-ling Sun
In this work, a novel approach that combines artificial neural networks (ANNs) and polynomial modeling to efficiently model the behavior of nonlinear RF devices is introduced. Utilizing the strengths of ANNs in knowledge retention and transfer, the proposed approach effectively incorporates new operational states such as different dc biases, frequencies, dies, and devices into existing models. This adaptive capability, in addition to the dynamic sampling techniques that only capture crucial dynamic characteristics across various operational states, significantly enhances the behavioral model’s extrapolation ability across various operational states and decreases the amount of measurement data needed. This approach is verified with a 0.25- $\mu$ m real gallium nitride (GaN) high electron mobility transistor (HEMT) device measured at different dies, sizes, dc biases, and frequencies. The results show that by utilizing only 30% of the conventional measurement data, the established polynomial equation-based model achieved a normalized mean squared error (NMSE) below $-$ 30 dB. The proposed model technique also has the advantage of easily being implemented in computer-aided design (CAD) software and allows for the fast design of RF circuits in industry applications while ensuring high accuracy and adaptability.

12 January 2026 in IEEE Transactions on Microwave Theory and Techniques
Verified
Journal Article
Closed access
JWJiahao Wang
Jiahao Wang
JSJiangtao Su
Jiangtao Su
HLHaode Li
Haode Li
YTYuxiu Tong
Yuxiu Tong
TFTangyu Fu
Tangyu Fu
ZYZhiping Yu
Zhiping Yu
This article presents an enhanced 2-D dynamic-kernel convolutional neural network (2-D DK-CNN) framework for nonlinear radio frequency (RF) device frequency domain behavioral modeling. The model features a unique 2-D convolutional structure that jointly processes behavior model coefficients, enabling the network to directly capture harmonic interactions under strong nonlinear conditions. This structure also provides a unified feature space that supports robust extrapolation across frequencies, bias conditions, and device sizes. As a result, it addresses a key limitation of conventional behavioral models, which rely on extensive and costly measurements while offering limited extrapolation capability. To support this framework, several algorithmic strategies are introduced, including adaptive loss control for stable convergence, coefficient conditioning for explicit operating-condition encoding, multitask learning (MTL) for simultaneous harmonic response extraction, and normalization schemes tailored to hierarchical convolutional layers. The proposed model is validated on gallium nitride (GaN) high electron mobility transistor (HEMT) devices across diverse operating conditions. The results demonstrate its accuracy, robustness, and scalability. This technique promises to be a powerful and practically integrable tool for computer-aided design (CAD)-based nonlinear RF device modeling and design.