A5060099913- Magnetic confinement fusion research
- Anomaly Detection Techniques and Applications
- Alkaloids: synthesis and pharmacology
- Nuclear Engineering Thermal-Hydraulics
- Computational Physics and Python Applications
- Superconducting Materials and Applications
- Atmospheric aerosols and clouds
- Plant responses to water stress
- Precipitation Measurement and Analysis
- Network Security and Intrusion Detection
- Laser-Plasma Interactions and Diagnostics
- Plant responses to elevated CO2
- Mycobacterium research and diagnosis
- Cancer therapeutics and mechanisms
- Inflammation biomarkers and pathways
- Nuclear Materials and Properties
- Lightning and Electromagnetic Phenomena
- Topic Modeling
- Helicobacter pylori-related gastroenterology studies
- Plant Water Relations and Carbon Dynamics
- Circular RNAs in diseases
- MicroRNA in disease regulation
- Gut microbiota and health
- Sepsis Diagnosis and Treatment
Huazhong University of Science and Technology
2020-2024
Hainan Medical University
2022-2024
Abstract Tokamaks are the most promising way for nuclear fusion reactors. Disruption in tokamaks is a violent event that terminates confined plasma and causes unacceptable damage to device. Machine learning models have been widely used predict incoming disruptions. However, future reactors, with much higher stored energy, cannot provide enough unmitigated disruption data at high performance train predictor before damaging themselves. Here we apply deep parameter-based transfer method...
Abstract Machine learning research and applications in fusion plasma experiments are one of the main subjects on J-TEXT. Since 2013, various kinds traditional machine learning, as well deep methods have been applied to experiments. Further real-time experimental environment proved feasibility effectiveness methods. For disruption prediction, we started by predicting disruptions limited classes with a short warning time that could not meet requirements mitigation system. After years study,...
China has been suffering from water shortage for a long time. Weather modification and rainfall enhancement via cloud seeding proved to be effective alleviate the problem. Current methods mostly rely on solid carbon dioxide chemicals such as silver iodide hygroscopic salts, which may have negative impacts environment are expensive operate. Lab experiments efficiency of ion-based compared with traditional methods. Moreover, it is also more environmentally friendly economical operate at large...
Acute lung injury (ALI) is a severe inflammatory disease, underscoring the urgent need for novel treatments. Nauclea officinalis Pierre ex Pitard (Danmu in Chinese, DM) effective treating respiratory diseases. However, there still no evidence of its protective effect against ALI.Metabolomics was applied to identify potential biomarkers and pathways ALI treated with DM. Further, network pharmacology introduced predict key targets DM ALI. Then, were further verified by immunohistochemistry...
Negative ion-based cloud seeding has been shown to be an effective means in the laboratory. China’s first negative outfield trial was conducted northwestern interior. This paper briefly introduces principle of precipitation enhancement, and location is described. The design ionization system meteorological monitoring network are presented. implementation plan explained. In addition, evaluation experimental effects detailed this paper. We designed various analytical methods investigate both...
Circular RNAs (circRNAs) have been shown to play important regulatory roles in many human diseases, yet their functions pulpitis remain be clarified. This study was designed investigate the function of circ_0138960 progression and its underlying mechanism.Cell viability proliferation were analyzed by 3-(4,5-Dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay 5-Ethynyl-2'-deoxyuridine (EdU) assay. Flow cytometry enzyme-linked immunosorbent (ELISA) conducted analyze cell...
Abstract The high acquisition cost and the significant demand for disruptive discharges data-driven disruption prediction models in future tokamaks pose an inherent contradiction research. In this paper, we demonstrated a novel approach to predict tokamak using only few based on domain adaptation (DA). aims by finding feature space that is universal all tokamaks. first step use existing understanding of physics extract physics-guided features from diagnostic signals each tokamak, called...
Predicting disruptions across different tokamaks is a great obstacle to overcome. Future can hardly tolerate at high performance discharge. Few disruption discharges compose an abundant training set, which makes it difficult for current data-driven methods obtain acceptable result. A machine learning method capable of transferring prediction model trained on one tokamak another required solve the problem. The key containing feature extractor that able extract common precursor traces in...
Predicting disruptions across different tokamaks is necessary for next generation device. Future large-scale can hardly tolerate at high performance discharge, which makes it difficult current data-driven methods to obtain an acceptable result. A machine learning method capable of transferring a disruption prediction model trained on one tokamak another required solve the problem. The key feature extractor able extract common precursor traces in diagnostic data, and be easily transferred...
The high acquisition cost and the significant demand for disruptive discharges data-driven disruption prediction models in future tokamaks pose an inherent contradiction research. In this paper, we demonstrated a novel approach to predict tokamak using only few discharges. first step is use existing understanding of physics extract physics-guided features from diagnostic signals each tokamak, called feature extraction (PGFE). second align data (target domain) large amount (source based on...
Disruption prediction has made rapid progress in recent years, especially machine learning (ML)-based methods. Understanding why a predictor makes certain can be as crucial the prediction's accuracy for future tokamak disruption predictors. The purpose of most predictors is or cross-machine capability. However, if model interpreted, it tell samples are classified precursors. This allows us to types incoming and gives insight into mechanism disruption. paper designs called Interpretable...