A5074883998- Chaos-based Image/Signal Encryption
- Advanced Steganography and Watermarking Techniques
- Robotics and Sensor-Based Localization
- Chaos control and synchronization
- Neural Networks Stability and Synchronization
- 3D Surveying and Cultural Heritage
- Nonlinear Dynamics and Pattern Formation
- Advanced Computational Techniques and Applications
- Remote Sensing and LiDAR Applications
- Cryptographic Implementations and Security
- Video Surveillance and Tracking Methods
- Robotic Path Planning Algorithms
- Advanced Vision and Imaging
- Advanced Image and Video Retrieval Techniques
- Advanced Algorithms and Applications
- 3D Shape Modeling and Analysis
- Cellular Automata and Applications
- IoT and Edge/Fog Computing
- Advanced Data Compression Techniques
- Network Security and Intrusion Detection
- Advanced Neural Network Applications
- Advanced Computing and Algorithms
- Graph Theory and Algorithms
- UAV Applications and Optimization
- Neural Networks and Applications
Wuhan University
2021-2025
Peking University People's Hospital
2025
Peking University
2025
Institute of Geodesy and Geophysics
2024
Geomatics (Norway)
2024
Chongqing University of Technology
2024
Singapore University of Technology and Design
2024
Chongqing University of Education
2011-2023
Harbin Institute of Technology
2022-2023
Shanghai University of Engineering Science
2023
Abstract Malicious JavaScript code in webpages on the Internet is an emergent security issue because of its universality and potentially severe impact. Because obfuscation complexities, detecting it has a considerable cost. Over last few years, several machine learning‐based detection approaches have been proposed; most them use shallow discriminating models with features that are constructed artificial rules. However, advent big data era for information transmission, these existing methods...
Visual Simultaneous Localization and Mapping (VSLAM) is a prerequisite for robots to accomplish fully autonomous movement exploration in unknown environments. At present, many impressive VSLAM systems have emerged, but most of them rely on the static world assumption, which limits their application real dynamic scenarios. To improve robustness efficiency system environments, this paper proposes RGBD SLAM based combination geometric semantic information (DGS-SLAM). First, object detection...
Registration is a basic yet crucial task in point cloud processing. In correspondence-based registration, matching correspondences by feature techniques may lead to an extremely high outlier (false correspondence) ratio. Current removal methods still suffer from low efficiency, accuracy, and recall rate. We use intuitive method describe the 6-DOF (degree of freedom) curtailment process registration propose strategy based on reliability correspondence graph. The constructs corresponding graph...
Autonomous exploration is crucial and highly challenging for various intelligent operations of unmanned aerial vehicles. However, low-efficiency problems caused by low-quality trajectory or back-and-forth maneuvers (BFMs) still exist. To improve the efficiency in unknown environments, a fast autonomous planner proposed this article. We first design novel frontier sequence generation method to significantly reduce BFM during considering multilevel factors an asymmetric traveling salesman...
Point Cloud Registration (PCR) is a fundamental and significant issue in photogrammetry remote sensing, aiming to seek the optimal rigid transformation between sets of points. Achieving efficient precise PCR poses considerable challenge. We propose novel micro-structures graph-based global point cloud registration method. The overall method comprised two stages. 1) Coarse (CR): develop graph incorporating micro-structures, employing an hierarchical strategy remove outliers for obtaining...
The "Life's Essential 8" (LE8) is a comprehensive lifestyle assessment tool by the American Heart Association, designed to mitigate cardiovascular disease risk optimizing factors including diet, physical activity, and other health metrics. While individual components of LE8 have been linked reduced cancer risks, studies on score trajectories over time their relation are lacking. This study employed Kailuan cohort, involving 48,330 participants who underwent three examinations from 2006 2010...
Plane segmentation is a basic yet important process in light detection and ranging (LiDAR) point cloud processing. The traditional plane algorithm typically affected by the number of clouds noise data, which results slow efficiency poor effect. Hence, an efficient encoding voxel-based (EVBS) based on fast adjacent voxel search proposed this study. First, binary octree to construct as object code voxel, can compute features quickly accurately. Second, region growing cluster corresponding...
Virtualization technology represented through Virtual Machines (VMs) is recognized as a key infrastructure in cloud computing. This developing rapidly and data centers face challenges such Machine Placement (VMP) for energy efficiency. VMP defined the efficient allocation of VMs to Host (HMs) achieve various objectives reducing consumption, load balancing avoid Service Level Agreement Violations (SLAV). In this paper, addressed using Deep Reinforcement Learning (DRL) based strategy determine...
Change detection (CD) is important for Earth observation, emergency response and time-series understanding. Recently, data availability in various modalities has increased rapidly, multimodal change (MCD) gaining prominence. Given the scarcity of datasets labels MCD, unsupervised approaches are more practical MCD. However, previous methods typically either merely reduce gap between through transformation or feed original directly into discriminant network difference extraction. The former...
Taking depth into consideration has been proven to improve the performance of semantic segmentation through providing additional geometry information. Most existing works adopt a two-stream network, extracting features from color images and separately using two branches same structure, which suffer high memory computation costs. We find that acquired by simple downsampling can also play complementary part in task, sometimes even better than scheme with branches. In this paper, novel...
Face recognition technology is an application of information security, which a kind multi-disciplinary technology, such as comprehensive mathematics, pattern recognition, and biological characteristics. With the development applications, requirements for accuracy anti-counterfeiting face are also increasing. In this paper, K-mean algorithm used to analyze features. Firstly, biometric features extracted, then method cluster Lastly, SVM classify. The results show that can achieve high...
In the application of wireless sensor networks, poor computing power, limited storage space, and short duration have severely restricted development networks. Compressed sensing technology is an emerging signal front-end processing technology, which breaks original use restrictions, saves space energy consumption, has become a research hotspot in field electronic technology. Based on network, this paper combines big data P2P direct connection perception idea to expand compression algorithm...