- Advanced Steganography and Watermarking Techniques
- Chaos-based Image/Signal Encryption
- Video Surveillance and Tracking Methods
- Computational Geometry and Mesh Generation
- Advanced Aircraft Design and Technologies
- Vehicle License Plate Recognition
- Advanced Numerical Analysis Techniques
- Computer Graphics and Visualization Techniques
- Probabilistic and Robust Engineering Design
- Adhesion, Friction, and Surface Interactions
- Genomics and Rare Diseases
- 3D Shape Modeling and Analysis
- Biomedical Text Mining and Ontologies
- Tribology and Lubrication Engineering
- Advanced Multi-Objective Optimization Algorithms
- Topic Modeling
- Digital Media Forensic Detection
- Lubricants and Their Additives
Tsinghua University
2025
Nanjing University of Aeronautics and Astronautics
2002-2023
Abstract Rare diseases, affecting ~350 million people worldwide, pose significant challenges in clinical diagnosis due to the lack of experienced physicians and complexity differentiating between numerous rare diseases. To address these challenges, we introduce PhenoBrain, a fully automated artificial intelligence pipeline. PhenoBrain utilizes BERT-based natural language processing model extract phenotypes from texts EHRs employs five new diagnostic models for differential diagnoses The AI...
Currently,mainstream 3D steganographic algorithms embed data through geometric modifications. To enhance the anti-steganalysis ability of such algorithms,we propose an additive Gaussian noise model for mesh steganography. Our work starts with a theoretical analysis correlations vertex coordinate components. Based on this analysis,the whole embedding operation is decomposed into three independent tasks that target components,respectively. obtain vertex-changing probabilities,we construct...
Laser Surface Texturing (LST) is an advanced method of surface micro-texturing technology. The aim this paper to investigate the effect micro-patterned laser texturing surfaces on hydrodynamic lubrication. Numerical model 3D set up based Reynolds equation. By Full Multi-Grid (FMG) V Cycle Algorithm, matrix pattern and interfering are investigated several parameters. It shown that lubrication performance influenced by type parameter micro-pattern. Result indicates ability pressure built-up...
Generative Steganography (GS) is a novel technique that utilizes generative models to conceal messages without relying on cover images. Contemporary GS algorithms leverage the powerful capabilities of Diffusion Models (DMs) create high-fidelity stego However, these algorithms, while yielding relatively satisfactory generation outcomes and message extraction accuracy, significantly alter modifications initial Gaussian noise DMs, thereby compromising steganographic security. In this paper, we...
3D Gaussian Splatting (3DGS) has recently created impressive assets for various applications. However, the copyright of these is not well protected as existing watermarking methods are suited 3DGS considering security, capacity, and invisibility. Besides, often require hours or even days optimization, limiting application scenarios. In this paper, we propose GuardSplat, an innovative efficient framework that effectively protects assets. Specifically, 1) We first a CLIP-guided Message...
Purpose This paper aims to develop a new method of fuselage drag optimization that can obtain results faster than the conventional methods based on full computational fluid dynamics (CFD) calculations and be used improve efficiency preliminary design. Design/methodology/approach An efficient for helicopter shape surrogate-based is presented. Two numerical simulation are applied in different stages according their relative advantages. The fast panel calculate sample data save calculation time...