A5001615978- Recommender Systems and Techniques
- Advanced Bandit Algorithms Research
- Microtubule and mitosis dynamics
- Machine Learning and Algorithms
- Power Quality and Harmonics
- Advanced Graph Neural Networks
- Power System Reliability and Maintenance
- Protist diversity and phylogeny
- Photosynthetic Processes and Mechanisms
- Silicon Carbide Semiconductor Technologies
- Experimental Learning in Engineering
- Topic Modeling
- Generative Adversarial Networks and Image Synthesis
- Embedded Systems Design Techniques
- HVDC Systems and Fault Protection
- Electricity Theft Detection Techniques
- High-Voltage Power Transmission Systems
- Advanced Data Processing Techniques
Institute of Macromolecular Chemistry
2025
Wenzhou Medical University
2025
Kuaishou (China)
2024
China Southern Power Grid (China)
2015-2020
Intracellular transport is a fundamental process crucial for cellular function, driven by the coordinated action of motor proteins that move cargo along microtubule tracks. Traditional tracking methods primarily focus on trajectories, often overlooking rotational dynamics and their impact interactions with complex network. To address this limitation, we introduced digitally assisted single-particle (dSPT) method significantly advances angular resolution intracellular dynamics. By integrating...
With the increasing demands of power supply, electric quality especially voltage sag deserves more concerns. This paper presents an approach K-means clustering analysis algorithm to classify and recognize from measured historical data large-scale grid in Shenzhen, China. The distances among different incidents distribution diagram are calculated first. When some nearer, a cluster center which is called centroid can be set represent these incidents. Then amounts locations determined based on...
The Probability Ranking Principle (PRP) has been considered as the foundational standard in design of information retrieval (IR) systems. principle requires an IR module's returned list results to be ranked with respect underlying user interests, so maximize results' utility. Nevertheless, we point out that it is inappropriate indiscriminately apply PRP through every stage a contemporary system. Such systems contain multiple stages (e.g., retrieval, pre-ranking, ranking, and re-ranking...
Rich user behavior data has been proven to be of great value for recommendation systems. Modeling lifelong in the retrieval stage explore long-term preference and obtain comprehensive results is crucial. Existing modeling methods cannot applied because they extract target-relevant items through coupling between target item. Moreover, current fail precisely capture interests when length sequence increases further. That leads a gap ability models model data. In this paper, we propose concept...