Jie Lan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jie Lan has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Hang Qu
School of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou 121001, China
1 shared publication - Huawei Yi
School of Electronics and Information Engineering, Liaoning University of Technology, Jinzhou 121001, China
1 shared publication - Lei Liu
College of Interdisciplinary Sciences Liaoning University of Technology Jinzhou China
1 shared publication - Shaocheng Tong
Navigation College Dalian Maritime University Dalian China
1 shared publication - Tao Wang
Liaoning University of Technology
1 shared publication - Yan-Jun Liu
Liaoning University of Technology
1 shared publication
Latest Publications
- Open Access
DVDR-SRGAN: Differential Value Dense Residual Super-Resolution Generative Adversarial Network
In the field of single-image super-resolution reconstruction, GAN can obtain the image texture more in line with the human eye. However, during the reconstruction process, it is easy to generate artifacts, false textures, and large deviations in details between the reconstructed image and the Ground Truth. In order to further improve the visual quality, we study the feature correlation between adjacent layers and propose a differential value dense residual network to solve this problem. We first use the deconvolution layer to enlarge the features, then extract the features through the convolution layer, and finally make a difference between the features before being magnified and the features after being extracted so that the difference can better reflect the areas that need attention. In the process of extracting the differential value, using the dense residual connection method for each layer can make the magnified features more complete, so the differential value obtained is more accurate. Next, the joint loss function is introduced to fuse high-frequency information and low-frequency information, which improves the visual effect of the reconstructed image to a certain extent. The experimental results on Set5, Set14, BSD100, and Urban datasets show that our proposed DVDR-SRGAN model is improved in terms of PSNR, SSIM, and LPIPS compared with the Bicubic, SRGAN, ESRGAN, Beby-GAN, and SPSR models.
Open AccessDVDR-SRGAN: Differential Value Dense Residual Super-Resolution Generative Adversarial Network
In the field of single-image super-resolution reconstruction, GAN can obtain the image texture more in line with the human eye. However, during the reconstruction process, it is easy to generate artifacts, false textures, and large deviations in details between the reconstructed image and the Ground Truth. In order to further improve the visual quality, we study the feature correlation between adjacent layers and propose a differential value dense residual network to solve this problem. We first use the deconvolution layer to enlarge the features, then extract the features through the convolution layer, and finally make a difference between the features before being magnified and the features after being extracted so that the difference can better reflect the areas that need attention. In the process of extracting the differential value, using the dense residual connection method for each layer can make the magnified features more complete, so the differential value obtained is more accurate. Next, the joint loss function is introduced to fuse high-frequency information and low-frequency information, which improves the visual effect of the reconstructed image to a certain extent. The experimental results on Set5, Set14, BSD100, and Urban datasets show that our proposed DVDR-SRGAN model is improved in terms of PSNR, SSIM, and LPIPS compared with the Bicubic, SRGAN, ESRGAN, Beby-GAN, and SPSR models.
- 13 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 29 (7) , 1841-1852
Adaptive Output Feedback Tracking Control for a Class of Nonlinear Time-Varying State Constrained Systems With Fuzzy Dead-Zone Input
This paper proposes an adaptive fuzzy controller for a class of uncertain strict-feedback non-matching nonlinear single input single output (SISO) systems with fuzzy dead zone and full time-varying state constraints. The states considered here are immeasurable and full states of the systems are constrained in a bounded set with time-varying regions. Following the adaptive backstepping design framework, the tangent barrier Lyapunov functions (TBLFs) are introduced to the integrated design to address the problems in such systems. Fuzzy logic systems (FLSs) are used to identify the unknown smooth functions and unknown parameters. An input-driven observer is designed to estimate the immeasurable states. To distinguish the conventional deterministic dead zone models, the output of dead zone is uncertainty. The form of indeterminate dead zone as a combination of a liner and a disturbance-like term is extended by the fuzzy algorithms. Even though output of dead zone is fuzzy and adopting the integrated design, the proposed fuzzy controller can ensure that all the signals in the closed-loop systems are semi-global uniformly ultimately bounded (SUUB) and guarantee the tracking performance. Finally, simulation results are shown to verify the effectiveness and reliability of the proposed approach.
- 13 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 29 (7) , 1841-1852
Adaptive Output Feedback Tracking Control for a Class of Nonlinear Time-Varying State Constrained Systems With Fuzzy Dead-Zone Input
This paper proposes an adaptive fuzzy controller for a class of uncertain strict-feedback non-matching nonlinear single input single output (SISO) systems with fuzzy dead zone and full time-varying state constraints. The states considered here are immeasurable and full states of the systems are constrained in a bounded set with time-varying regions. Following the adaptive backstepping design framework, the tangent barrier Lyapunov functions (TBLFs) are introduced to the integrated design to address the problems in such systems. Fuzzy logic systems (FLSs) are used to identify the unknown smooth functions and unknown parameters. An input-driven observer is designed to estimate the immeasurable states. To distinguish the conventional deterministic dead zone models, the output of dead zone is uncertainty. The form of indeterminate dead zone as a combination of a liner and a disturbance-like term is extended by the fuzzy algorithms. Even though output of dead zone is fuzzy and adopting the integrated design, the proposed fuzzy controller can ensure that all the signals in the closed-loop systems are semi-global uniformly ultimately bounded (SUUB) and guarantee the tracking performance. Finally, simulation results are shown to verify the effectiveness and reliability of the proposed approach.
- 18 January 2019
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 17 (2) , 536-544
Design of type-2 Fuzzy Logic Systems Based on Improved Ant Colony Optimization
- 18 January 2019
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 17 (2) , 536-544
Design of type-2 Fuzzy Logic Systems Based on Improved Ant Colony Optimization