A5086757876- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Software System Performance and Reliability
- Advanced Optical Sensing Technologies
- Advanced Neural Network Applications
- Medical Imaging Techniques and Applications
- Cloud Computing and Resource Management
- Visual Attention and Saliency Detection
- Advanced Malware Detection Techniques
- Random lasers and scattering media
- Image Processing Techniques and Applications
- Optical Coherence Tomography Applications
- Optical Imaging and Spectroscopy Techniques
- Big Data and Digital Economy
- Advanced X-ray and CT Imaging
- Advanced Vision and Imaging
Zhejiang Sci-Tech University
2018-2024
Chongqing University
2016
Vehicle affect the safety of people's daily life, and it is difficult to detect discriminate surrounding conditions vehicle because a variety object types different sizes. The paper aims establish digital assistant driving detection system, enhance rapid this multi-scale objects, provide effective decision-making responses ease traffic accidents. proposes pre-warning method based on YOLOv5. Two mainly models YOLOv3 YOLOv5 are taken estimate accuracy efficiency mechanism. Experimental results...
Single photon imaging integrates advanced single detection technology with Laser Radar (LiDAR) technology, offering heightened sensitivity and precise time measurement. This approach finds extensive applications in biological imaging, remote sensing, non-visual field imaging. Nevertheless, current LiDAR systems encounter challenges such as low spatial resolution a limited of view their intensity range images due to constraints the detector hardware. To overcome these challenges, this study...
Anomaly detection has been an important topic in cloud platforms to guarantee the dependability and robustness of services cloud. Most research works were proposed tackle performance problems algorithms caused by volume data, dynamic environment, various types anomalies, so on. However, almost all them take only optimization into account, which leads a situation that some key features detector deployment scalability framework itself are omitted. Therefore, anomaly awareness based on...
The advent of cloud platform has promoted the complexity and scales industries increasingly. Any deliberate or non-deliberate faults may cause enormous impact on system performance server costs. Anomaly detection is a good way to identify anomalies improve dependability platform. However, some anomaly methods are labeled data dependency, them sensitive dynamic runtime environment To address problems, an adaptive incremental clustering algorithm for virtual machines under proposed. Compared...
Fourier single pixel imaging utilizes pre-programmed patterns for laser spatial distribution modulation to reconstruct intensity image of the target through reconstruction algorithms. The approach features non-locality and high anti-interference performance. However, Poor quality is induced when interest occluded in imaging. To address problem, a deep learning-based inpainting algorithm employed within partially obscured targets with quality. It applies distance-based segmentation method...
Virtual machine is an important part of cloud platform. Ensuring virtual running correctly great significance to ensure the availability service. Due platform has characteristics large number machines and dynamic change environment, it's hard accept cost collecting training data for anomaly detector detector. This paper focuses on insufficient set high training, does research how improve detection accuracy efficiency under condition that there not enough Concretely speaking, main contents...