A5102729710- Advanced Control and Stabilization in Aerospace Systems
- Image and Video Stabilization
- Image Enhancement Techniques
- Cancer-related molecular mechanisms research
- Multimodal Machine Learning Applications
- Neuroscience and Neural Engineering
- Advanced Computational Techniques and Applications
- Embedded Systems and FPGA Design
- Advanced Measurement and Detection Methods
- Optical Systems and Laser Technology
- Domain Adaptation and Few-Shot Learning
- Video Surveillance and Tracking Methods
- Web Data Mining and Analysis
- Advanced Memory and Neural Computing
- Fire Detection and Safety Systems
- EEG and Brain-Computer Interfaces
Xi'an Jiaotong University
2024
National University of Defense Technology
2023-2024
Dalian University of Technology
2020
In steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI), improving the recognition performance for new subjects without calibration data is key challenge practical application. Unsupervised transfer learning an effective way to overcome it. However, existing studies focus solely on what transfer, rather than how effectively resulting in unsatisfactory effectiveness or even negative transfer. this study, innovative unsupervised cross-subject method SSVEP-BCI was...
The complex influence of various disturbances on an inertially stabilized platform (ISP) restricts the further improvement its servo performance. This article investigates mapping relationship between internal and external performance by establishing a high-precision dynamics model device with simulation experiment. For disturbances, nonlinear friction backlash is established based BP neural network, transmission error reconstructed principle main order invariance. road disturbance torque,...
Compared with zero-shot learning (ZSL), the generalized (GZSL) is more challenging since its test samples are taken from both seen and unseen classes. Most previous mapping-based methods perform well on ZSL, while their performance degrades GZSL. To solve this problem, inspired by ensemble learning, paper proposes a model cooperative coupled generative networks (CCGN). Firstly, to alleviate hubness reverse visual feature space as embedding space, mapping achieved center generation network....
Although researchers have made great progress in image dehazing recently, there are still challenges balancing the suitable universality and accuracy. In this paper, we propose dark channel prior cycle dehaze network (DCP-Cycle-Dehaze) to single dehazing. This is based on CycleGAN, which adds DCP loss knowledge improved perceptual achieve function. DCP-Cycle-Dehaze mainly enhance capacity of model by enhancing sensitivity for haze features during training. It further improves performance...
In order to improve the state monitoring and adaptive control capability of inertial stabilization platforms (ISPs) with unknown loads, it is necessary estimate dynamic parameters comprehensively online. However, most current online estimation methods regard system as a linear dual-inertia model which neglects backlash nonlinear friction torque. It reduces accuracy leads incomplete low estimated parameters. The purpose this research achieve comprehensive accurate multiple ISPs lay foundation...