A5040956935- Formal Methods in Verification
- Constraint Satisfaction and Optimization
- Advanced Software Engineering Methodologies
- Infrastructure Maintenance and Monitoring
- Software Engineering Research
- Model-Driven Software Engineering Techniques
- Advanced Computational Techniques and Applications
- Image Processing Techniques and Applications
- 3D Surveying and Cultural Heritage
- Optical measurement and interference techniques
- Asphalt Pavement Performance Evaluation
- Industrial Vision Systems and Defect Detection
- Image and Object Detection Techniques
- Evaluation Methods in Various Fields
- Rough Sets and Fuzzy Logic
- Species Distribution and Climate Change
- Advanced Decision-Making Techniques
- Coding theory and cryptography
- Cryptographic Implementations and Security
- Wildlife Ecology and Conservation
- Complexity and Algorithms in Graphs
- Domain Adaptation and Few-Shot Learning
- Ergonomics and Musculoskeletal Disorders
- Real-Time Systems Scheduling
- Digital Media and Visual Art
Beijing Aerospace Flight Control Center
2023
Beijing Forestry University
2020-2023
Changzhou University
2010-2022
Southeast University
2019-2022
Stanford University
2021
China Medical University
2021
Zhejiang University
2021
Jinzhou Medical University
2021
University of Waterloo
2013-2018
Shenyang Aerospace University
2003-2018
Traditional automatic pavement distress detection methods using convolutional neural networks (CNNs) require a great deal of time and resources for computing are poor in terms interpretability. Therefore, inspired by the successful application Transformer architecture natural language processing (NLP) tasks, novel method called LeViT was introduced asphalt image classification. consists layers, transformer stages where Multi-layer Perception (MLP) multi-head self-attention blocks alternate...
Modern conflict-driven clause-learning SAT solvers routinely solve large real-world instances with millions of clauses and variables in them. Their success crucially depends on effective branching heuristics. In this paper, we propose a new heuristic inspired by the exponential recency weighted average algorithm used to bandit problem. The heuristic, call CHB, learns online which branch leveraging feedback received from conflict analysis. We evaluated CHB 1200 Competition 2013 2014...
Clafer is a lightweight yet expressive language for structural modeling: feature modeling and configuration, class object modeling, metamodeling. Tools an integrated set of tools based on Clafer. In this paper, we describe some product-line variability scenarios from the viewpoints owner, engineer, product engineer.
Modern conflict-driven clause-learning (CDCL) Boolean SAT solvers provide efficient automatic analysis of real-world feature models (FM) systems ranging from cars to operating systems. It is well-known that solver-based FMs scale very well even though instances obtained such are large, and the corresponding problems known be NP-complete. To better understand why so effective, we systematically studied many syntactic semantic characteristics a representative set large FMs. We discovered key...