A5100338872- Machine Learning and ELM
- Advanced Text Analysis Techniques
- Spectroscopy Techniques in Biomedical and Chemical Research
- Topic Modeling
- Water Quality Monitoring and Analysis
- Advanced Semiconductor Detectors and Materials
- Fault Detection and Control Systems
- Biomedical Text Mining and Ontologies
- Advanced X-ray and CT Imaging
- Natural Language Processing Techniques
- Radiation Detection and Scintillator Technologies
- Advanced Algorithms and Applications
University of Chinese Academy of Sciences
2019-2023
Xi'an Institute of Optics and Precision Mechanics
2022-2023
Spectral Imaging Laboratory (United States)
2023
Chinese Academy of Sciences
2022
National Science Library
2019-2021
Objectives. This study set out to develop and validate a risk prediction tool for the early detection of heart failure (HF) onset using real-world electronic health records (EHRs). Background. While existing HF assessment models have shown promise in clinical settings, they are often tailored specific medical conditions, limiting their generalizability. Moreover, most methods rely on hand-crafted features, making it difficult capture high-dimensional, sparse, temporal nature EHR data, thus...
Owing to the general disadvantages of traditional neural networks in gas concentration inversion, such as slow training speed, sensitive learning rate selection, unstable solutions, weak generalization ability, and an ability easily fall into local minimum points, extreme machine (ELM) was applied sulfur hexafluoride (SF6) inversion research. To solve problems high dimensionality, collinearity, noise spectral data input ELM network, a genetic algorithm used obtain fewer but critical data....
Abstract Purpose Automatic keyphrase extraction (AKE) is an important task for grasping the main points of text. In this paper, we aim to combine benefits sequence labeling formulation and pretrained language model propose automatic Chinese scientific research. Design/methodology/approach We regard AKE from text as a character-level avoid segmentation errors tokenizer initialize our with BERT, which was released by Google in 2018. collect data Science Citation Database construct large-scale...
Abstract Purpose Move recognition in scientific abstracts is an NLP task of classifying sentences the into different types language units. To improve performance move abstracts, a novel model proposed that outperforms BERT-based method. Design/methodology/approach Prevalent models based on BERT for sentence classification often classify without considering context sentences. In this paper, inspired by masked (MLM), we propose called integrates content and contextual information recognition....
A large-format, high-resolution Hg<sub>1–<i>x</i></sub>Cd<sub><i>x</i></sub>Te infrared focal plane array (IRFPA) image sensor can be used in aerospace remote sensing and high-precision satellite imaging. The next generation of meteorological satellites China will all adopt this type sensor. However, space high-energy protons cause displacement damage effects IRFPA detectors induce total ionizing dose (TID) the pixel unit...