|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Snapshot boosting: a fast ensemble framework for deep neural networks显示文摘Boosting has been proven to be effective in improving the generalization of machine learning models in many fields. It is capable of getting high-diversity base learners and getting an accurate ensemble model by combining a sufficient number of weak learners. However, it is rarely used in deep learning due to the high training budget of the neural network. Another method named snapshot ensemble can significantly reduce the training budget, but it is hard to balance the tradeoff between training costs and diversity. Inspired by the ideas of snapshot ensemble and boosting, we propose a method named snapshot boosting. A series of operations are performed to get many base models with high diversity and accuracy, such as the use of the validation set, the boosting-based training framework, and the effective ensemble strategy. Last, we evaluate our method on the computer vision(CV) and the natural language processing(NLP) tasks, and the results show that snapshot boosting can get a more balanced trade-off between training expenses and ensemble accuracy than other well-known ensemble methods. | Wentao ZHANG Jiawei JIANG Yingxia SHAO Bin CUI | 2020 | Science China(Information Sciences)2020，63，1： | 4 |
| 2 | Management Algorithm for Prevention of Mother-to-child Transmission of Hepatitis B Virus(2022)显示文摘The World Health Organization(WHO)has set the goal of eliminating hepatitis as a threat to public health by 2030.Blocking mother-to-child transmission(MTCT)of hepatitis B virus(HBV)is not only the key to eliminating viral hepatitis,but also a hot issue in the field of hepatitis B prevention and treatment.To standardize the clinical management of preventing MTCT of HBV and achieve zero HBV infection among infants,the Chinese Foundation for Hepatitis Prevention and Control organized experts to compile a management algorithm for prevention of MTCT of HBV based on the latest research progress and guidelines,including 10 steps of pregnancy management and postpartum follow-up,among which screening,antiviral treatment,and infant immunization are its core components. | Zhihua Liu Zhongdan Chen Fuqiang Cui Yang Ding Yunfei Gao Guorong Han Jidong Jia Jie Li Zengde Li Yingxia Liu Qing Mao Ailing Wang Wei Wang Lai Wei Jianhong Xia Qing Xie Xizhong Yang Xueru Yin Hua Zhang Liaoyun Zhang Wenhong Zhang Hui Zhuang Xiaoguang Dou Jinlin Hou | 2022 | Journal of Clinical and Translational Hepatology2022，10，5： | 2 |
| 3 | Meiotic Chromosome Behavior in a Human Male t(8;15)Carrier显示文摘Reciprocal translocation is one of the most common structural chromosomal rearrangements in human beings;it is widely recognized to be associated with male infertility.This association is mainly based on the abnormal chromosome behavior of the translocated chromosomes and sex chromosomes during meiosis prophase I in reciprocal translocation carriers.However,the underlying mechanisms are not completely known.Here we report a reciprocal translocation carrier of t(8;15),who is oligozoospermic due to apoptosis of primary spermatocytes and to premature germ cell desquamation from seminiferous tubules.Further analysis showed abnormal synapsis and recombination frequency in this patient,indicating a connection between chromosome behavior and apoptosis of primary spermatocytes.We also compared these observations with recently reported findings on spermatogenesis defects in reciprocal translocation carriers,and discuss the possible mechanisms underlying bom common and unique phenotypes of reciprocal translocations involving different chromosomes with the aim of further understanding the regulation of human spermatogenesis. | Hanwei Jiang Liu Wang Yingxia Cui Zhipeng Xu Tonghang Guo Dongkai Cheng Peng Xu Wen Yu Qinghua Shi | 2014 | Journal of Genetics and Genomics2014，41，3： | 2 |
| 4 | A Novel Algorithm of Buffer Construction Based on Run-Length Encoding显示文摘 | Wang Jiecheng Cui Can Pu Yingxia | 2010 | The Cartographic Journal2010，47，3： | 1 |
| 5 | 5-HMF attenuates inflammation and demyelination in experimental autoimmune encephalomyelitis mice by inhibiting the MIF-CD74 interaction显示文摘The neuroprotective role of 5-hydroxymethyl-2-furfural(5-HMF)has been demonstrated in a variety of neurological diseases.The aim of this study is to investigate the effect of 5-HMF on multiple sclerosis(MS).IFN-γ-stimulated murine microglia(BV2 cells)are considered a cell model of MS.With 5-HMF treatment,microglial M1/2 polarization and cytokine levels are detected.The interaction of 5-HMF with migration inhibitory factor(MIF)is predicted using online databases.The experimental autoimmune encephalomyelitis(EAE)mouse model is established,followed by a 5-HMF injection.The results show that 5-HMF facilitates IFN-γ-stimulated microglial M2 polarization and attenuates the inflammatory response.According to the network pharmacology and molecular docking results,5-HMF has a binding site for MIF.Further results show that blocking MIF activity or silencing CD74 enhances microglial M2 polarization,reduces inflammatory activity,and prevents ERK1/2 phosphorylation.5-HMF inhibits the MIF-CD74 interaction by binding to MIF,thereby inhibiting microglial M1 polarization and enhancing the anti-inflammatory response.5-HMF ameliorates EAE,inflammation,and demyelination in vivo.In conclusion,our research indicates that 5-HMF promotes microglial M2 polarization by inhibiting the MIF-CD74 interaction,thereby attenuating inflammation and demyelination in EAE mice. | Dongsheng Guan Yingxia Li Yinglin Cui Huanghong Zhao Ning Dong Kun Wang Deqi Ren Tiantian Song Xiaojing Wang Shijie Jin Yinghe Gao Mengmeng Wang | 2023 | Acta Biochimica et Biophysica Sinica2023，55，8： | 0 |
| 6 | LECF:recommendation via learnable edge collaborative filtering显示文摘The core of recommendation models is estimating the probability that a user will like an item based on historical interactions.Existing collaborative filtering(CF)algorithms compute the likelihood by utilizing simple relationships between objects,e.g.,user-item,item-item,or user-user.They always rely on a single type of object-object relationship,ignoring other useful relationship information in data.In this paper,we model an interaction between user and item as an edge and propose a novel CF framework,called learnable edge collaborative filtering(LECF).LECF predicts the existence probability of an edge based on the connections among edges and is able to capture the complex relationship in data.Specifically,we first adopt the concept of line graph where each node represents an interaction edge;then calculate a weighted sum of similarity between the query edge and the observed edges(i.e.,historical interactions)that are selected from the neighborhood of query edge in the line graph for a recommendation.In addition,we design an efficient propagation algorithm to speed up the training and inference of LECF.Extensive experiments on four public datasets demonstrate LECF can achieve better performance than the state-of-the-art methods. | Shitao XIAO Yingxia SHAO Yawen LI Hongzhi YIN Yanyan SHEN Bin CUI | 2022 | Science China(Information Sciences)2022，65，1： | 0 |
| 7 | A new trapezoidal-mesh based data model for spatial operations显示文摘This paper presents a new spatial data model based on trapezoidal-mesh for implementing spatial operations within geographical information systems(GIS).Based only on the solid foundation of spatial operations,diversified application models can be established to bridge the gap between Digital Earth models and the real world with its real-world problems(‘connecting through location’).In this paper,the involved polygon features are decomposed into a series of trapezoidalmeshes.Then,geo-processing operations are employed on these meshes rather than the original polygon features,resulting in a relatively simple spatial computation.As a kind of model designed by integrating raster with vector,the model presented here has advantages over other models when carrying out spatial operations insofar as providing a solid foundation for achieving the grand goal of Digital Earth.The concept of this data model and the two extensive examples of its application in spatial operations are elaborated upon in this article.As a result,this article and the research that supports it,proves that the adoption of the trapezoidal-mesh model greatly improves the efficiency of spatial operations in GIS. | Jiechen Wang Can Cui Gang Chen Yingxia Pu Jinsong Ma | 2012 | International Journal of Digital Earth2012，5，2： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员