A5050793881- stochastic dynamics and bifurcation
- Chaos control and synchronization
- Industrial Vision Systems and Defect Detection
- Vehicle License Plate Recognition
- Neural Networks and Applications
- Image Processing Techniques and Applications
- VLSI and Analog Circuit Testing
- Engineering and Test Systems
- Multimodal Machine Learning Applications
- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Smart Agriculture and AI
- Chaos-based Image/Signal Encryption
- Remote Sensing and Land Use
- Image and Object Detection Techniques
- Advanced Memory and Neural Computing
- AI in cancer detection
- Advanced Image Fusion Techniques
- Nonlinear Dynamics and Pattern Formation
- Anomaly Detection Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Advanced Neural Network Applications
- Advanced Steganography and Watermarking Techniques
- Domain Adaptation and Few-Shot Learning
- Video Surveillance and Tracking Methods
Jilin University
2020-2024
Northwest Normal University
2022-2023
Ministry of Education of the People's Republic of China
2021
Shanghai Jiao Tong University
2013
Dalian University of Technology
2005
Abstract In this paper, a novel four-dimensional memristive chaotic system is constructed by incorporating memristor model into three-dimensional system. Through the analysis of Lyapunov exponent, bifurcation diagram, and Poincaré cross-section system, it has been observed that capable exhibiting stable state, as well complex dynamic behaviors, such attractor coexistence, transient chaos, offset boosting. To validate actual existence real circuit built based on Multisim simulation, numerical...
Automatic segmentation of polyps from colonoscopy images plays a critical role in early screening and treatment colorectal cancer.Although deep learning methods have made significant progress, precise polyp faces two challenges: (1) the imbalance color appearances limited training dataset hinders generalization model, (2) diverse scales, locations shapes with blurred boundary.To address issues, Dataset-Level Color Augmentation (DLCA) Convolutional Multi-scale Attention Module (CMAM) are...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
The remarkable progress in cross-modal retrieval relies on accurately-annotated multimedia datasets. In practice, most existing datasets used for training models are automatically collected from the Internet to reduce data collection costs. However, it inevitably contains mismatched pairs, i.e. , noisy correspondences, thus degrading model performance. Recent advances utilize predicted similarity distribution of individual samples noise validation and correction, which easily faces two...
The great development in micromanipulation technology has exigent request to develop image processing for microscopic images. Considering the characteristics of color images imriging system and information ima;ges, two wavelet transformation based methods HSI space vector edge detection were proposed. Then, interested area is interpolated using cubic spline :and accurate subpixel edges are obtained on zero point first-order derivatives. applied with simulated noise real experiment results...
In the initial phase of production improvement for new technology, a fault chip may contain multiple defects. Owing to interaction between defects, state‐of‐the‐art defect diagnosis procedure based on simulation single‐modelled faults generate large number candidate faults. Early methods test scores removed correct when narrowing set faults, which caused drop in diagnostic accuracy. This Letter proposes method combined with make better use information reduce and improve The approach computes...
Abstract Diagnosis is an essential step to improve the yield in semiconductor manufacturing industry. It performed on a failing chip determine location of defects. However, defect diagnosis procedure may obtain too much candidate faults which lead difficulties next physical failure analysis. Recently, methods based test score reduce fault set are proved be effective. The previous method free information computes for each implies identification ability. This letter proposes novel recognition...