A5114594007- Advanced Image Fusion Techniques
- Meteorological Phenomena and Simulations
- Advanced Data Storage Technologies
- Atmospheric and Environmental Gas Dynamics
- Cloud Computing and Resource Management
- Distributed and Parallel Computing Systems
- Optical Systems and Laser Technology
- Climate variability and models
- Atmospheric Ozone and Climate
- Image and Signal Denoising Methods
- Organic Food and Agriculture
- Traditional Chinese Medicine Studies
- Medical Image Segmentation Techniques
- Ship Hydrodynamics and Maneuverability
- Automated Road and Building Extraction
- Maritime Navigation and Safety
- Calibration and Measurement Techniques
- Agriculture Sustainability and Environmental Impact
- Maritime Transport Emissions and Efficiency
- Economic and Environmental Valuation
- Traffic Prediction and Management Techniques
- Anomaly Detection Techniques and Applications
- Atmospheric aerosols and clouds
- Autonomous Vehicle Technology and Safety
- Image Processing Techniques and Applications
Shanghai Institute of Technical Physics
2020-2024
Chinese Academy of Sciences
2014-2024
Ritsumeikan University
2023
Changsha University of Science and Technology
2022
Heilongjiang University
2019
Academia Sinica
2015
Institute of Computing Technology
2014
Deep learning has attracted wide attention recently because of its excellent feature representation ability and end-to-end automatic method. Especially in clinical medical imaging diagnosis, the semi-supervised deep model is favored widely used it can make maximum use a limited number labeled data combine with large unlabeled to extract more information knowledge from it. However, scarcity image data, vast size, instability quality directly affect model's robustness, generalization,...
In our study, a retrieval method of temperature profiles is proposed which combines an improved one-dimensional variational algorithm (1D-Var) and artificial neural network (ANN), using FY-4A/GIIRS (Geosynchronous Interferometric Infrared Sounder) infrared hyperspectral data. First, according to the characteristics observation data conventional 1D-Var, we introduced channel blacklists discarded channels that have large negative impact on retrieval, then used information capacity for...
Satellite infrared hyperspectral instruments can obtain a wealth of atmospheric spectrum information. In order to high-precision temperature and humidity profiles, we used the traditional One-Dimensional Variational (1D-Var) retrieval algorithm, combined with information capacity-weight function coverage method select channel. addition, an Artificial Neural Network (ANN) algorithm was introduced correct satellite observation data error compare it conventional correction method. Finally,...
Introduction Alternative meats have the potential to shape a sustainable food system. This study examined young consumers’ perceptions of and preferences for plant-based cultured meats. Since comparative studies on consumer alternative in different key Asian markets remain insufficient, this was conducted Japan China, both whom promising meat Asia. Methods We discrete choice experiment co-occurrence networks among 2006 ( n = 887 1,119 China) consumers. adopted treatment-control design where...
FY-4A/GIIRS (Geosynchronous Interferometric Infrared Sounder) is the first infrared hyperspectral atmospheric vertical detector in geostationary orbit. Compared to other similar instruments, it has advantages of high temporal resolution and stationary relative ground. Based on characteristics GIIRS observation data, we proposed a humidity profile retrieval method. We fully utilized information provided by forecast used two-dimensional brightness temperature data with dimension time optical...
Hive is the most mature and prevalent data warehouse tool providing SQL-like interface in Hadoop ecosystem. It successfully used many Internet companies shows its value for big processing traditional industries. However, enterprise systems as Smart Grid applications usually require complicated business logics involve manipulation operations like updates deletes. cannot offer sufficient support these while preserving high query performance. using Distributed File System (HDFS) storage...
Hive is the most mature and prevalent data warehouse tool providing SQL-like interface in Hadoop ecosystem. It successfully used many Internet companies shows its value for big processing traditional industries. However, enterprise systems as Smart Grid applications usually require complicated business logics involve manipulation operations like updates deletes. cannot offer sufficient support these while preserving high query performance. using Distributed File System (HDFS) storage...
The non-subsampled contourlet transform (NSCT) is a good approach in capturing the detail of images, so that it has wide range applications image denoising. In order to improve denoising effect NSCT method medical ultrasound local intuitionistic fuzzy entropy (LIFE) theory employed this work suppress noise high-frequency coefficients NSCT. On combination with LIFE and directionality coefficients’ distribution NSCT, directional (DLIFE) been put forward calculate corresponding suppression...
In recent years, the rise of machine learning algorithms provides a good tool for processing hyperspectral data. A series have served classification images. Derived from these methods that regarding spectral segments each pixel as sequence. Recurrent Neural Network (RNN) showing better capability sequence data play an important role in classification. The standard unidirectional RNN, however, only focus on current input and memory state past, cannot connect to future memory. Alternatively,...
With the connected vehicle (CV) can interact with infrastructure and be used as a moving sensor to bring more real-time higher precision input for intersection signal control. However, such connectivity also brings network security risks.To protect of intersections, this paper designs realistic attack model based on forged trajectory injection simulate potential that smart attacker may launch, key track points queued vehicles were extracted, traffic wave velocity was distance index transform...