A5107771841- Advanced SAR Imaging Techniques
- Radar Systems and Signal Processing
- Power Systems and Technologies
- Color perception and design
- Advanced Algorithms and Applications
- Sensory Analysis and Statistical Methods
- Neural Networks and Applications
- Image Processing Techniques and Applications
- Microgrid Control and Optimization
- Distributed Sensor Networks and Detection Algorithms
- Human Pose and Action Recognition
- Multisensory perception and integration
- Machine Fault Diagnosis Techniques
- Sparse and Compressive Sensing Techniques
- Energy, Environment, and Transportation Policies
- Target Tracking and Data Fusion in Sensor Networks
- Optical Systems and Laser Technology
- Power Systems and Renewable Energy
- Food Supply Chain Traceability
- Face and Expression Recognition
- 3D Shape Modeling and Analysis
- Image and Object Detection Techniques
- Energy Load and Power Forecasting
Shanghai Electric (China)
2024
Beijing University of Technology
2015
Zhejiang Sci-Tech University
2011
For a conventional narrow-band radar system, the detectable information of target is limited, and it difficult for to accurately identify type. In particular, classification probability will further decrease when part echo data missed. By extracting features in time frequency domains from multi-wave gates sparse data, this paper presents algorithm three different types aircraft target, i.e., helicopter, propeller jet. Firstly, classical reconstruction utilized reconstruct spectrum with...
As a special feature of rotor target, rotational angular velocity can provide important information for target classification and recognition. In this paper, estimation method is proposed based on complex empirical mode decomposition (CEMD) three-dimensional orthogonal matching pursuit (3D-OMP)-based parametric sparse representation (PSR) technique. Firstly, the translational radial estimated from radar echo via Fourier transform, then compensation implemented according to velocity....
How to generate a personalized 3D virtual body model conveniently and quickly is playing an increasingly important role in computer animation, reality, entertainment, e-commerce many other areas. Some related researchers just simply adjust human characteristic parameters using existing model. In this article, order the quickly, approach based on Fuzzy Support Vector Machines (FSVM) suggested. This constructs classification of parameter. The one-versus-one (OVO) method binary tree used handle...
Starting from the angle of demand response, a regulation mechanism electricity price that changes with air quality index has been proposed, which aims to stimulate dynamism users, and make themselves adjust their consumption behavior. As result, lot energy can be saved pollution problems relieved. The is adjusted by change index, means adjustment factor larger when more severe, higher, promoting users save energy. When it comes determine electricity, multi-objective optimization model...
Based on deliberate analysis of the detection problem concerning target buried in blind Doppler zone AEW radar, a system is conceived founding multi-AEW radar data fusion. The fusion rule as well generalized likelihood ratio and false alarm threshold local sensors are derived. Simulation results demonstrate that advanced technique can improve probability quality track dramatically case necessary condition satisfied.
In order to further improve the generalization ability of active decision model, a new model based on big data and pattern recognition was constructed by taking agricultural making as an example. The characteristics land remote sensing are obtained from two aspects spectrum shape. features were input into support vector machine realize classification farmland. Based this, combined with description method, environment is completed. Taking grain production, ecological compatibility...
Aiming at the weak micro characteristics of traditional narrowband radar targets, an aerial target type recognition method based on Box-Cox transform and convolutional neural network is proposed. The does not need to compensate fuselage component, carries out nonlinear transformation directly echo data, which enhances component. Then, two-dimensional time-frequency images are generated by short-time Fourier transform, input for feature learning, helicopter, propeller aircraft, jet aircraft...