Jiayi Zhao

Dr. Jiayi Zhao

Aerospace Information Research Institute, Beijing, China
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
1 March 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JZJiayi Zhao
Jiayi Zhao
YMYong Ma
Yong Ma
FCFu Chen
Fu Chen
ESErping Shang
Erping Shang
WYWutao Yao
Wutao Yao
JYJin Yang
Jin Yang
High-resolution (HR) remote sensing images have important applications in many scenarios, and improving the resolution of remote sensing images via algorithms is one of the key research fields. However, current super-resolution (SR) algorithms, which are trained on synthetic datasets, tend to have poor performance in real-world low-resolution (LR) images. Moreover, due to the inherent complexity of real-world remote sensing images, current models are prone to color distortion, blurred edges, and unrealistic artifacts. To address these issues, real-SR datasets using the Gao Fen (GF) satellite images at different spatial resolutions have been established to simulate real degradation situations; moreover, a second-order attention generator adversarial attention network (SA-GAN) model based on real-world remote sensing images is proposed to implement the SR task. In the generator network, a second-order channel attention mechanism and a region-level non-local module are used to fully utilize the a priori information in low-resolution (LR) images, as well as adopting region-aware loss to suppress artifact generation. Experiments on test data demonstrate that the model delivers good performance for quantitative metrics, and the visual quality outperforms that of previous approaches. The Frechet inception distance score (FID) and the learned perceptual image patch similarity (LPIPS) value using the proposed method are improved by 17.67% and 6.61%, respectively. Migration experiments in real scenarios also demonstrate the effectiveness and robustness of the method.

28 December 2016 in Industrial & Engineering Chemistry Research
Verified
Journal Article
Closed access
JZJiayi Zhao
Jiayi Zhao
YSYingying Sun
Yingying Sun
YMYongfeng Men
Yongfeng Men

29 October 2021
Verified
Conference Paper
Open access
JZJiayi Zhao
Jiayi Zhao
YLYang Liu
Yang Liu
In this paper, the absorption, distribution, metabolism, excretion, and toxicity of compounds are modeled, and the classification prediction models of Caco-2, CYP3A4, HERG, hob and Mn in ADMET properties are constructed respectively. Firstly, the main variables corresponding to the five indicators are obtained and the special data set is constructed. Then, two sets of integrated learning schemes, bagging integrated decision tree and boosting integrated GBDT, are used for modeling. At the same time, logical regression and naive Bayesian algorithm is used for classification prediction as the control group to construct the classification model. Finally, ACC, F1 and other indexes are used as model evaluation indexes to select the optimal model of each index. The results show that the characteristic distributions of Mn and HERG, Caco-2, CYP3A4 and HOB are similar.