A5107250713- Time Series Analysis and Forecasting
- Advanced Computational Techniques and Applications
- Advanced Malware Detection Techniques
- Multimodal Machine Learning Applications
- Chaos control and synchronization
- Domain Adaptation and Few-Shot Learning
- Advanced Algorithms and Applications
- Peptidase Inhibition and Analysis
- Advanced Neural Network Applications
- Web Application Security Vulnerabilities
- Security and Verification in Computing
- Microbial Natural Products and Biosynthesis
- RNA and protein synthesis mechanisms
Wuhan University
2023-2025
Zhongnan Hospital of Wuhan University
2025
Nanjing University of Information Science and Technology
2020
China University of Mining and Technology
2011
Henan Polytechnic University
2011
The cyclic structure of non-ribosomal peptides (NRPs) is critical for enhancing their stability and bioactivity, which highlights the importance exploring NRP cyclization enzymes natural product discovery. Thioesterases (TEs) are crucial that catalyze formation various lactams, including macrolactams, β-lactams, γ-lactams; however, potential to produce other lactam types remains largely unexplored. In this study, we identified spinactin A (1) novel derivatives, B–E (2–5), from...
Modern software is bloated, especially for libraries. The unnecessary code not only brings severe vulnerabilities, but also assists attackers to construct exploits. To mitigate the damage of bloated libraries, researchers have proposed several debloating techniques remove or restrict invocation unused in a library. However, existing approaches either statically keep all expected inputs, which leave each concrete input, rely on runtime context dynamically determine necessary code, could be...
Based the principle of minimizing average prediction error, in this paper genetic algorithm is adopted to determine parameters phase-space reconstruction multivariate time series. First, methods and series are introduced. Then theory select given that chromosome coding multi-parameters cascade binary string, fitness error function optimal combination obtained through operation. Finally, Matlab2009b simulation environment, applied confirm embedding dimensions time-delays Rossler coupling...
Aimed at solving the interdependences among reconstruction variables and their parameters, this paper adopted genetic algorithm to determine parameters in phase-space of multivariate time series simultaneously. First, process method are introduced. Then theory select is given that chromosome coding binary code string multi-parameters cascade, fitness function average prediction error optimal combination obtained through operation. Finally, Matlab2009b environment, applied two examples....
Domain adaptation is critical to transfer the invaluable source domain knowledge target domain. In this paper, for a particular visual attention model, saying hard attention, we consider adapt learned unlabeled To tackle kind of adaptation, novel adversarial reward strategy proposed train policy agent. training framework, agent competes with discriminator which takes features generated from both agents as input and tries its best distinguish them, thus align local feature counterpart. We...