A5064208724- Chinese history and philosophy
- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- AI in cancer detection
- Image Retrieval and Classification Techniques
- Intermetallics and Advanced Alloy Properties
- High Temperature Alloys and Creep
- Aluminum Alloy Microstructure Properties
- Radiomics and Machine Learning in Medical Imaging
- Material Properties and Applications
- Land Use and Ecosystem Services
- Digital Imaging for Blood Diseases
- Translation Studies and Practices
- Solidification and crystal growth phenomena
- Metallurgical Processes and Thermodynamics
- Microstructure and mechanical properties
- Advanced Image and Video Retrieval Techniques
- Luminescence and Fluorescent Materials
- Infrared Target Detection Methodologies
- Medical Image Segmentation Techniques
- Methane Hydrates and Related Phenomena
- X-ray Diffraction in Crystallography
- Urban Green Space and Health
- Additive Manufacturing Materials and Processes
- Remote Sensing and Land Use
National University of Defense Technology
2019-2025
University of Oulu
2024-2025
Fuyang Normal University
2024
Inspire Institute
2024
Macau University of Science and Technology
2024
North China University of Science and Technology
2024
Chinese Academy of Sciences
1999-2023
Northeast Forestry University
2018-2023
Northeastern University
2015-2023
Institute of Electronics
2021-2023
Background and Purpose: Edaravone dexborneol, comprised of 2 active ingredients, edaravone (+)-borneol, has been developed as a novel neuroprotective agent with synergistic effects antioxidant anti-inflammatory in animal models. The present clinical trial aimed at testing the dexborneol versus on 90-day functional outcome patients acute ischemic stroke (AIS). Methods: A multicenter, randomized, double-blind, comparative, phase III was conducted 48 hospitals China between May 2015 December...
In recent years, researches are concentrating on the effectiveness of Transfer Learning (TL) and Ensemble (EL) techniques in cervical histopathology image analysis. However, there have been very few investigations that described stages differentiation histopathological images. Therefore, this article, we propose an Ensembled (ETL) framework to classify well, moderate poorly differentiated First all, developed Inception-V3, Xception, VGG-16, Resnet-50 based TL structures. Then, enhance...
Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine (ML), as it necessitates the Incremental (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this field has seen recent progress, remains an active exploration area. This paper aims to provide comprehensive and systematic review FSCIL. In our in-depth examination, we delve into various facets FSCIL, encompassing problem definition, discussion primary...
Emerging evidences have verified that long non-coding RNAs (lncRNAs) play important regulatory roles in the pathogenesis and progression of cancers. lncRNAs metastasis associated lung adenocarcinoma transcript 1 (MALAT1) been found to be up-regulated some human The main objective this study was investigate expression level biological function MALAT1 gastric cancer (GC).Quantificational real-time polymerase chain reaction (qRT-PCR) performed detect mRNA levels 78 paired carcinoma tissues...
AbstractA simple and effective phenology-based algorithm was developed to detect map rubber tree plantations in Xishuangbanna, a prefecture southwest China's Yunnan province. This highlighted the unique phenological characteristics of deciduous during dry season. Phenology natural evergreen forests delineated with Normalized Difference Vegetation Index (NDVI), Land Surface Water (LSWI) Burn Ratio (NBR) derived from Landsat Thematic Mapper (TM), Enhanced plus (ETM+) Operational Imager imagery...
Few-shot Class-incremental Pill Recognition (FSCIPR) aims to develop an automatic pill recognition system that requires only a few training data and can continuously adapt new classes, providing technical support for applications in hospitals, portable apps, assistance visually impaired individuals. This task faces three core challenges: overfitting, fine-grained classification problems, catastrophic forgetting. We propose the Well-Prepared Learning (WP-FSCIL) framework, which addresses...
The severest drought on record occurred in southwestern China from September 2009 until March 2010. In order to measure the impact imposed vegetation, we developed an evaluation indicator called Vegetation Index Anomaly (VIA) based MODIS/EVI. tempo-spatial pattern of this was analyzed. Given that may be modulated by many factors, responses different vegetation types (woodland, grassland and cropland), spatial meteorological were also Results show more than 50% suffered because event, but...
The main obstacle to image augmentation with Generative Adversarial Networks (GANs) is the need for a large amount of training data, but this difficult small datasets like Environmental Microorganisms (EMs). EM analysis plays vital role in environmental monitoring and protection, it often encountered due difficulty collection. To end, we propose an Enhanced Framework GANs (EF-GANs) that combines geometric transformation methods augmentation. First all, color has insignificant impact on its...