A5102707439- VLSI and Analog Circuit Testing
- Radiation Effects in Electronics
- Infrastructure Maintenance and Monitoring
- Physical Unclonable Functions (PUFs) and Hardware Security
- Advanced Image Fusion Techniques
- Fault Detection and Control Systems
- Image Processing Techniques and Applications
- Remote Sensing in Agriculture
- Traditional Chinese Medicine Studies
- Asphalt Pavement Performance Evaluation
- Remote-Sensing Image Classification
- Concrete Corrosion and Durability
- Photonic and Optical Devices
- Industrial Vision Systems and Defect Detection
- Remote Sensing and Land Use
- Anomaly Detection Techniques and Applications
- Automated Road and Building Extraction
- Advanced Neural Network Applications
- Advancements in PLL and VCO Technologies
- Optical Network Technologies
Zaozhuang University
2023-2024
Institute of Microelectronics
2024
Chinese Academy of Sciences
2020-2024
Xuzhou University of Technology
2024
Hunan University of Science and Technology
2023
National Space Science Center
2018-2020
University of Chinese Academy of Sciences
2020
Deep learning has attracted wide attention recently because of its excellent feature representation ability and end-to-end automatic method. Especially in clinical medical imaging diagnosis, the semi-supervised deep model is favored widely used it can make maximum use a limited number labeled data combine with large unlabeled to extract more information knowledge from it. However, scarcity image data, vast size, instability quality directly affect model's robustness, generalization,...
The joint classification of hyperspectral imagery (HSI) and LiDAR data is an important task in the field remote sensing image interpretation. Traditional methods, such as support vector machine (SVM) random forest (RF), have difficulty capturing complex spectral–spatial–elevation correlation information. Recently, progress has been made HSI-LiDAR using Convolutional Neural Networks (CNNs) Transformers. However, due to large spatial extent images, vanilla Transformer CNNs struggle effectively...
Vibration sensors are prone to bias, drift, and other failures. To avoid misjudgments in state monitoring systems potential safety accidents caused by vibration sensor failures, it is significant diagnose the faults of sensors. Existing methods for fault diagnosis primarily based on Deep Learning, but Extreme Gradient Boosting stands out due its excellent interpretability, compared ensemble learning algorithms, boasts superior accuracy efficiency. Therefore, a method proposed seven common...
This study uses a pulsed laser to investigate the sensitivity of sequential logic circuit Single-Event-Upset (SEU) under different supply voltages, clock frequencies, and architectures. The experimented is D flip-flop chain manufactured in 65-nm bulk CMOS technology. results indicate that as voltage decreases, SEU sensibility increases, particular at low ranges, it increases significantly. Additionally, effect frequency on mainly related propagation Single-Event-Transients (SETs) are...
As is well known, the classification performance of large deep neural networks closely related to amount annotated data. However, in practical applications, quantity data minimal for many computer vision tasks, which poses a considerable challenge convolutional that aim achieve ideal performance. This paper proposes new, fully supervised low-sample image model alleviate problem limited marked sample real life. Specifically, this presents new intrinsic consistency loss, can more effectively...
Single-event-upset (SEU) sensitivity of sequencing logic circuits (D flip-flops) fabricated in 65-nm bulk CMOS process is investigated as a function operating pattern, clock frequency, supply voltage and circuit structure by using pulsed laser.