A5102884121- Neural Networks Stability and Synchronization
- Remote Sensing and LiDAR Applications
- Data Stream Mining Techniques
- Adversarial Robustness in Machine Learning
- Remote Sensing and Land Use
- Smart Grid Security and Resilience
- Advanced Memory and Neural Computing
- Sensorless Control of Electric Motors
- Advanced Measurement and Detection Methods
- 3D Shape Modeling and Analysis
- Advanced Algorithms and Applications
- Electrical Contact Performance and Analysis
- 3D Surveying and Cultural Heritage
- Non-Destructive Testing Techniques
- Control Systems in Engineering
- Advanced Image Fusion Techniques
- Neural Networks and Applications
- Advanced Clustering Algorithms Research
- Railway Engineering and Dynamics
- Spectral Theory in Mathematical Physics
- Wind Turbine Control Systems
- Stability and Control of Uncertain Systems
- Network Security and Intrusion Detection
- Matrix Theory and Algorithms
- Distributed Control Multi-Agent Systems
Hunan University of Technology
2007-2023
Central South University
2017-2018
Next‐generation networks are data‐driven by design but face uncertainty due to various changing user group patterns and the hybrid nature of infrastructures running these systems. Meanwhile, amount data gathered in computer system is increasing. How classify process massive reduce transmission network a very worthy problem. Recent research uses deep learning propose solutions for related issues. However, faces problems like overfitting that may undermine effectiveness its applications...
Accurately identifying the rail surface state is crucial for enhancing train traction and braking capabilities, as well ensuring safe operation maintenance. Few-shot learning commonly utilized to recognize state, effectively resolving overfitting issue caused by limited sample data. However, when it comes actual situation of data, few-shot faces challenges such insufficient extraction feature information a tendency lose distinguishing degree information. To address aforementioned issues,...
In a wind turbine generator, it is difficult to achieve good control performance using the conventional PID variable pitch controller because of multi-variables and nonlinearities controller. Based on principles generating set, this study introduces mathematical model for generators proposes fuzzy method by combining methods effectively overcome deficiencies order enhance self-learning predictability system, an improved proposed based online support vector machine (SVM). Finally, simulation...
This paper focuses on the generalized<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"><mml:mrow><mml:msub><mml:mrow><mml:mi>H</mml:mi></mml:mrow><mml:mrow><mml:mn mathvariant="normal">2</mml:mn></mml:mrow></mml:msub></mml:mrow></mml:math>filtering of static neural networks with a time-varying delay. The aim this problem is to design full-order filter such that filtering error system globally asymptotically stable guaranteed<mml:math...
To solve the problems among traditional methods which are reliability and robustness of system, we propose a novel target recognition system based on multi-sensor fusion in this article. The presented uses sensors data infrared, visible light sound to recognize moving objects field environment. design consists set algorithms simulation system. Tested with data, it shows that has high rates low time delay compared is highly suitable for real-time implementation demonstrated through series experiments.
The speed control performance of permanent magnet synchronous motor (PMSM) drive system is degraded due to non-matching disturbances such as parameter perturbation and load torque mutation. This paper presents a nonlinear generalized predictive method based on equivalent-input-disturbance (GPC-based-EID) realize the fast response strong robustness controller PMSM system. Firstly, continuous time mechanical equation established. A theory rather than PI traditional vector designed. Then, with...
Cluster analysis is an important data mining issue, where objects under investigation are grouped into subsets of the original set objects. In recent several years, a few clustering algorithms have been developed for stream problem. However these lack extensibility or efficiency. this paper we propose new evolving streams system with fusion. We discuss fundamentally different philosophy which guided by application centered requirements. The highly suitable real-time implementation and...