A5077375228- Domain Adaptation and Few-Shot Learning
- Energy Efficient Wireless Sensor Networks
- Indoor and Outdoor Localization Technologies
- Multimodal Machine Learning Applications
- Advanced Algorithms and Applications
- PAPR reduction in OFDM
- Underwater Vehicles and Communication Systems
- Advanced Wireless Communication Techniques
- Data Management and Algorithms
- Machine Learning in Materials Science
- Nonmelanoma Skin Cancer Studies
- Video Surveillance and Tracking Methods
- Human Pose and Action Recognition
- Geographic Information Systems Studies
- Algorithms and Data Compression
- IoT-based Smart Home Systems
- Wireless Communication Networks Research
- Computational Drug Discovery Methods
- Machine Learning and ELM
- AI in cancer detection
- Real-time simulation and control systems
- Advanced Research in Science and Engineering
- Simulation and Modeling Applications
- Advanced Sensor and Control Systems
- Computational Physics and Python Applications
Anhui Jianzhu University
2020-2024
The University of Texas at Austin
2024
Nanjing University of Information Science and Technology
2022
Hefei University of Technology
2018
Kunming University of Science and Technology
2015
Harbin Engineering University
2006-2007
Northeastern University
2005
Abstract The analysis of skin lesion images is challenging due to the high interclass similarity and intraclass variance. Therefore, improving ability automatically classify based on necessary help physicians lesions. We propose a network model Visual Geometry Group Network (VGG‐16) fusion residual structure for multiclass classification VGG‐16 network, we simplify improve by adding preprocessing layer (CBRM layer) fusing structure. also use hair removal algorithm perform six data...
With the long-term dependence of humans on ore-based energy, underground mines are utilized around world, and mining is often dangerous. Therefore, many have established networks that manage acquire information from sensor nodes deployed miners in other places. Since power supplies mobile batteries, green communication an effective approach reducing energy consumption a network extending its longevity. To reduce networks, all factors negatively influence lifetime should be considered. The...
Prediction of drug-target interactions (DTIs) plays a crucial role in various areas drug development, such as reuse and identification potential side effects drugs. In recent years, although great progress has been made DTIs prediction, the existing methods still have problem high sparsity datasets. this work, multi-modal autoencoder is used to fuse similarity networks many different drugs (targets), so extract low-dimensional feature vectors input them into knowledge graph embedding (KGE)...
Pedestrian re-identification aims to distinguish and recognize a particular pedestrian within set of images taken by various cameras. Previous research has demonstrated that simple, global local features may not yield optimal results for the model. In this study, an end-to-end recognition network is enhanced incorporating multi-granularity features. This comprises multiple deep modules, specifically, two feature branch modules modules. To augment model's extraction capability, we have...