A5088791693- Advanced Neural Network Applications
- Image Processing Techniques and Applications
- AI in cancer detection
- Industrial Vision Systems and Defect Detection
- Network Security and Intrusion Detection
- Digital and Cyber Forensics
- Infrared Target Detection Methodologies
- Optical Systems and Laser Technology
- Optical measurement and interference techniques
- Integrated Circuits and Semiconductor Failure Analysis
- 3D Shape Modeling and Analysis
- Internet Traffic Analysis and Secure E-voting
- Advanced Algorithms and Applications
- Traffic Prediction and Management Techniques
- Remote Sensing and LiDAR Applications
- 3D Surveying and Cultural Heritage
- Video Surveillance and Tracking Methods
- Digital Imaging for Blood Diseases
- Anomaly Detection Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Cell Image Analysis Techniques
- Smart Parking Systems Research
- Advanced Optical Sensing Technologies
- Power Line Communications and Noise
- COVID-19 diagnosis using AI
Beijing Information Science & Technology University
2025
East China Jiaotong University
2022-2024
Zhejiang University of Science and Technology
2024
As autonomous driving technology advances swiftly, the precise identification of road signs has become essential for enabling driving. This paper introduces an enhanced YOLOv8 model sign recognition. enhances original C2f module by incorporating RepViT Block, resulting in C2f_RVB module. alteration not only hastens convergence rate but also markedly boosts detection precision. Furthermore, we introduce a highly efficient architectural framework utilizing lightweight ViTs, which augments...
As innovation proceeds to advance, 3D recreation has ended up a critical portion of the field computer vision. Among these, reproduction based on RGB-D information sources well known approach in later long time. Right now, more develop inactive calculations have progressively successful for reproducing stationary objects. Be that as it may, their adequacy lessens when parts scene are blocked. This paper briefly presents particular approaches address impediment issues and fundamental concepts...
With the rise of deep learning, U-Net network, based on a U-shaped architecture and skip connections, has found widespread application in various medical image segmentation tasks. However, receptive field standard convolution operation is limited, because it difficult to achieve global long-distance semantic information interaction. Inspired by advantages ConvNext Neighborhood Attention (NA), we propose CAT-Unet this study address aforementioned challenges. We effectively reduce number...
A visual mechanical signal detection and loading platform with super-resolution based on deep learning is designed to improve the accuracy of signals. The include three-dimensional (3D) biological force quantitative 3D magnetic distortion ultrahigh resolution. In platform, four sensors are used collect signals, improved fuzzy clustering fusion method fuse signals collected by resolution technology connects instrument microscope, collects images through high-speed scanning components...
To accurately detect and identify whether there are abnormalities in the information of expressway networking system, an security event reasoning traceability method based on deep learning is proposed to build a data protection system that includes life periodicity system. In this model intrusion detection message exchange format established. The uses risk convolution neural network infer during sharing reorganize standardize according standardization model, store it database form Extensible...
To ensure the reliability and safety of expressway networking systems, this paper designs a data flow risk monitoring system for systems based on deep learning. The is composed analysis, formulation strategy, real-time monitoring, disaster recovery. Data analysis basis operation each part system. Meanwhile, indexes such as network management, assets, resources are selected to build index convolution neural model constructed, input into extract features through pooling process. Based this,...