A nonlinear behavioral modeling technique, based on support vector regression (SVR), is presented in this letter. As an advanced machine-learning technique, the SVR method provides a more effective way to determine the optimal model when compared with the more traditional modeling approaches based on artificial neural network (ANN) techniques. The proposed technique can overcome the well-known overfitting issue often associated with ANNs. In this letter, the basic theory of the proposed SVR modeling method is provided, along with details on model implementation in the context of RF transistor devices. Both simulation and experimental test examples for a 10-W gallium nitride (GaN) transistor are provided, revealing that the new modeling methodology provides a more efficient and robust prediction throughout the Smith chart when compared with ANNs, with the latest results showing excellent model fidelity at both the fundamental and at the second harmonic.

Coronavirus disease 2019 (COVID-19) is one of the most destructive pandemic after millennium, forcing the world to tackle a health crisis. Automated lung infections classification using chest X-ray (CXR) images could strengthen diagnostic capability when handling COVID-19. However, classifying COVID-19 from pneumonia cases using CXR image is a difficult task because of shared spatial characteristics, high feature variation and contrast diversity between cases. Moreover, massive data collection is impractical for a newly emerged disease, which limited the performance of data thirsty deep learning models. To address these challenges, Multiscale Attention Guided deep network with Soft Distance regularization ( MAG-SD ) is proposed to automatically classify COVID-19 from pneumonia CXR images. In MAG-SD , MA-Net is used to produce prediction vector and attention from multiscale feature maps. To improve the robustness of trained model and relieve the shortage of training data, attention guided augmentations along with a soft distance regularization are posed, which aims at generating meaningful augmentations and reduce noise. Our multiscale attention model achieves better classification performance on our pneumonia CXR image dataset. Plentiful experiments are proposed for MAG-SD which demonstrates its unique advantage in pneumonia classification over cutting-edge models. The code is available at https://github.com/JasonLeeGHub/MAG-SD .

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.

This letter proposes two compact folded spoof surface plasmon polariton (SSPP) transmission lines (TL) with single-sided grooves (Type A) and double-sided grooves (Type B), and their cut-off frequencies are 17.55 GHz and 19.52 GHz, respectively. Due to large number of units, the proposed SSPP TLs have steep sideband and excellent upper band suppression (< −48 dB). The compact folding solution could reduce the lateral size to nearly 2/5 of the original one, and to a certain extent solve the layout difficulties associated with traditional SSPP TLs due to their slender structure. The cut-off frequency can be independently regulated by stub length and width. The proposed components are fabricated and tested. The experimental results are in good agreement with the simulated results, demonstrating the possibility of compact folded SSPP TLs and greatly improving the potential of SSPP use in miniaturized and highly integrated circuit systems.

This paper presents an improved ultrawideband open-short de-embedding methodology. In contrast to the conventional measurement-based open-short de-embedding method, the presented method is a measurement-calculation hybrid method. First, the open and short de-embedding structures are measured, and the corresponding scattering parameters are obtained. Based on this, lumped-parameter models of the open and short de-embedding structures are established. Then, the established models are modified to solve the over de-embedding problem. Finally, the modified de-embedding structure models are implemented in the scattering parameters of device test structures to achieve ultrawideband de-embedding. To verify the proposed de-embedding method, the method is applied to active devices. The results before and after de-embedding are compared under multiple bias conditions. Furthermore, the results after de-embedding based on the conventional open-short method and the proposed method are compared up to 220 GHz. These results show that using the proposed method can achieve accurate ultrawideband de-embedding up to the terahertz frequency band.

Artificial intelligence (AI) techniques are increasingly being used for the inverse design of microwave devices. However, several challenges, including intensive computation costs for training samples, high-dimensional data, nonuniformity, and low-quality samples in the design space, can negatively impact the final modeling performance. To alleviate these issues, a high-quality sampling inverse design scheme incorporating wavelet transform deep learning (HQS-WTDL) is proposed to achieve customized, automated microwave filter design. In the forward simulation-based sampling, particle swarm optimization (PSO) is used to tentatively select rule-defined samples. Multilabel synthetic minority over-sampling technique (MLSMOTE) is then applied to enlarge the training samples and improve their uniformity in the design space. An inverse modeling approach using neural networks to map the nonlinear relationship between a given set of S-parameters and required filter structural parameters is presented. Given that the dimension of the S-parameters is much higher than that of the structure parameters, the corresponding neural network used in this approach is deep and complex, with multiple layers and neurons. To reduce the number of input variables, the S-parameters are subjected to wavelet transformation, allowing for more efficient representation by the neural network. The proposed method is validated using a band-pass microstrip hairpin filter as an example. Results demonstrate that the proposed approach achieves better modeling effectiveness and inverse design efficiency than conventional methods. In addition, the proposed method allows for fast customization of device parameters, such as center frequencies and bandwidths with good prediction accuracy.