A5057517041- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Infrastructure Maintenance and Monitoring
- Robot Manipulation and Learning
- Video Surveillance and Tracking Methods
- Imbalanced Data Classification Techniques
- Robotic Mechanisms and Dynamics
- Metamaterials and Metasurfaces Applications
- Infrared Target Detection Methodologies
- Photonic and Optical Devices
- Tunneling and Rock Mechanics
- Time Series Analysis and Forecasting
- Human Motion and Animation
- Software-Defined Networks and 5G
- Gait Recognition and Analysis
- Domain Adaptation and Few-Shot Learning
- Robotic Path Planning Algorithms
- Face recognition and analysis
- Neural Networks and Reservoir Computing
- Network Traffic and Congestion Control
- Image and Object Detection Techniques
- Advanced Optical Network Technologies
- Visual Attention and Saliency Detection
Nanjing Tech University
2025
Shanghai University
2022-2024
State Ethnic Affairs Commission
2023
Minzu University of China
2023
Midea Group (China)
2021
Beijing Jiaotong University
2019
Huazhong University of Science and Technology
2016
The detection of anomalies in multivariate time-series data is becoming increasingly important the automated and continuous monitoring complex systems devices due to rapid increase volume dimension. To address this challenge, we present a anomaly model based on dual-channel feature extraction module. module focuses spatial time features using short-time Fourier transform (STFT) graph attention network, respectively. two are then fused significantly improve model’s performance. In addition,...
SUMMARY Collision-free motion planning of a virtual arm is an intractable task in high-interference environments. In this paper, approach for collision-free based on the forward and backward reaching inverse kinematics (FABRIK) algorithm proposed. First, random rotation strategy local optimum-seeking technology are introduced to improve FABRIK order avoid obstacles. The improvement used design final grasping posture according target position. Then, bidirectional rapidly exploring tree...
Inverse kinematics (IK) has been extensively applied in the areas of robotics, computer animation, ergonomics, and gaming. Typically, IK determines joint configurations a robot model achieves desired end-effector position robotics. Since forward backward teaching inverse (FABRIK) is iterative method that finds updated positions by locating point on line instead using angle rotations or matrices, it advantages fast convergence, low computational cost, visualizing realistic poses. However,...
Nonlinear Hall effect (NLHE) offers a novel means of uncovering symmetry and topological properties in quantum materials, holding promise for exotic (opto)electronic applications such as microwave rectification THz detection. The BCD-independent NLHE could exhibit robust response even at room temperature, which is highly desirable practical applications. However, materials with bulk inversion symmetry, the coexistence surface conducting channels often leads to suppressed complex...
As one of the main border gateway protocol (BGP) security schemes at present, research on machine learning-based BGP anomaly detection technology faces severe data imbalance due to lack data. To solve this problem, paper proposes an unbalanced generation method based undersampling and DoppelGANger, called US-DPGAN. Firstly, random is performed majority-class samples reduce imbalanced ratio dataset bias impact generated by DoppelGANger. Then, we use trained DoppelGANger model generate that...
With the ever-growing network traffic and vast amount of abnormal being created, anomaly detection methods have attracted close attention in cybersecurity domain. Generative adversarial networks (GANs) been applied to detection, but obtaining high-precision consistently stable results is still challenging for current methods. In paper, we propose an improved GAN-based method called GANDPS traffic. The GAN introduces encoder based on original GAN, a specialized layer integrated into process...