|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Deep forest显示文摘Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting machines,we conjecture that the success of deep neural networks owes much to three characteristics, i.e.layer-by-layer processing, in-model feature transformation and sufficient model complexity. On one hand,our conjecture may offer inspiration for theoretical understanding of deep learning; on the other hand, to verify the conjecture, we propose an approach that generates deep forest holding these characteristics. This is a decision-tree ensemble approach, with fewer hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting. This study opens the door to deep learning based on non-differentiable modules without gradient-based adjustment, and exhibits the possibility of constructing deep models without backpropagation. | Zhi-Hua Zhou Ji Feng | 2019 | National Science Review2019，6，1： | 52 |
| 2 | Nonlinear singular vectors and nonlinear singular values显示文摘A novel concept of nonlinear singular vector and nonlinear singular value is introduced, which is a natural generalization of the classical linear singular vector and linear singular value to the nonlinear category. The optimization problem related to the determination of nonlinear singular vectors and singular values is formulated. The general idea of this approach is demonstrated by a simple two-dimensional quasigeostrophic model in the atmospheric and oceanic sciences. The advantage and its applications of the new method to the predictability, ensemble forecast and finite-time nonlinear instability are discussed. This paper makes a necessary preparation for further theoretical and numerical investigations. | 穆穆 | 2000 | Science China Earth Sciences2000，43，4： | 37 |
| 3 | CMIP6 Evaluation and Projection of Temperature and Precipitation over China显示文摘This article evaluates the performance of 20 Coupled Model Intercomparison Project phase 6(CMIP6)models in simulating temperature and precipitation over China through comparisons with gridded observation data for the period of 1995–2014,with a focus on spatial patterns and interannual variability.The evaluations show that the CMIP6 models perform well in reproducing the climatological spatial distribution of temperature and precipitation,with better performance for temperature than for precipitation.Their interannual variability can also be reasonably captured by most models,however,poor performance is noted regarding the interannual variability of winter precipitation.Based on the comprehensive performance for the above two factors,the“highest-ranked”models are selected as an ensemble(BMME).The BMME outperforms the ensemble of all models(AMME)in simulating annual and winter temperature and precipitation,particularly for those subregions with complex terrain but it shows little improvement for summer temperature and precipitation.The AMME and BMME projections indicate annual increases for both temperature and precipitation across China by the end of the 21st century,with larger increases under the scenario of the Shared Socioeconomic Pathway 5/Representative Concentration Pathway 8.5(SSP585)than under scenario of the Shared Socioeconomic Pathway 2/Representative Concentration Pathway 4.5(SSP245).The greatest increases of annual temperature are projected for higher latitudes and higher elevations and the largest percentage-based increases in annual precipitation are projected to occur in northern and western China,especially under SSP585.However,the BMME,which generally performs better in these regions,projects lower changes in annual temperature and larger variations in annual precipitation when compared to the AMME projections. | Xiaoling YANG Botao ZHOU Ying XU Zhenyu HAN | 2021 | Advances in Atmospheric Sciences2021，38，5： | 21 |
| 4 | Assessment of bearing performance degradation via extension and EEMD combined approach显示文摘As a key component in rotating machinery, the operating reliability of bearing influences the performance and service life of the equipment directly. In order to describe bearing performance degradation(BPD) process effectively, an assessment approach combining extension and ensemble empirical mode decomposition(EEMD) was proposed. First, the extension was utilized to construct the matter-element of bearing operating state, and the energy moment of intrinsic mode functions(IMFs) was used as characteristic parameter of the matter-element. Then, to determine classical domains of characteristic parameters, the mathematical statistics method was adopted. Finally, the BPD was analyzed qualitatively and quantitatively according to the comprehensive correlation degree of bearing current operating state related to its healthy state. The analytic results of bearing test-rig show that the proposed method indicates the incipient fault approximately occurring in the 81 st hour, and the method also quantitatively presents the degree of BPD. By contrast, the BPD assessment based on time-domain features extraction method could not achieve the above two results effectively. | 刘玉梅 赵聪聪 熊明烨 赵颖慧 乔宁国 田广东 | 2017 | Journal of Central South University2017，24，5： | 16 |
| 5 | The China Multi-Model Ensemble Prediction System and Its Application to Flood-Season Prediction in 2018显示文摘Multi-model ensemble prediction is an effective approach for improving the prediction skill short-term climate prediction and evaluating related uncertainties. Based on a combination of localized operation outputs of Chinese climate models and imported forecast data of some international operational models, the National Climate Center of the China Meteorological Administration has established the China multi-model ensemble prediction system version 1.0 (CMMEv1.0) for monthly-seasonal prediction of primary climate variability modes and climate elements. We verified the real-time forecasts of CMMEv1.0 for the 2018 flood season (June-August) starting from March 2018 and evaluated the 1991-2016 hindcasts of CMMEv1.0. The results show that CMMEv1.0 has a significantly high prediction skill for global sea surface temperature (SST) anomalies, especially for the El Nino-Southern Oscillation (ENSO) in the tropical central-eastern Pacific. Additionally, its prediction skill for the North Atlantic SST triple (NAST) mode is high, but is relatively low for the Indian Ocean Dipole (IOD) mode. Moreover, CMMEv1.0 has high skills in predicting the western Pacific subtropical high (WPSH) and East Asian summer monsoon (EASM) in the June-July-August (JJA) season. The JJA air temperature in the CMMEv1.0 is predicted with a fairly high skill in most regions of China, while the JJA precipitation exhibits some skills only in northwestern and eastern China. For real-time forecasts in March-August 2018, CMMEv1.0 has accurately predicted the ENSO phase transition from cold to neutral in the tropical central-eastern Pacific and captures evolutions of the NAST and IOD indices in general. The system has also captured the main features of the summer WPSH and EASM indices in 2018, except that the predicted EASM is slightly weaker than the observed. Furthermore, CMMEv1.0 has also successfully predicted warmer air temperatures in northern China and captured the primary rainbelt over northern China, except that it predicted much more precipitation in the middle and lower reaches of the Yangtze River than observation. | Hong-Li REN Yujie WU Qing BAO Jiehua MA Changzheng LIU Jianghua WAN Qiaoping LI Xiaofei WU Ying LIU Ben TIAN Joshua-Xiouhua FU Jianqi SUN | 2019 | Journal of Meteorological Research2019，33，3： | 16 |
| 6 | 在医院实现信息化集成平台显示文摘深入分析了在不改变现有医院信息系统底层架构的基础上,实现集成平台的必要性。结合业务流程,详细阐述了如何运用Web Service,Ensemble技术以及XML相关工具,实现跨各个业务系统间的交互和整合。 | 龙凤舞 | 2010 | 中国现代医学杂志2010，20，6： | 15 |
| 7 | 短期负荷预测的Ensemble混沌预测方法显示文摘负荷记录中的噪声以及预测方法中矩阵数值计算的奇异性,使得一次预测得到的结果具有较大的误差。为了降低初值中噪声的不利影响,将数值天气预报中的Ensemble方法移植到短期负荷预测中。在混沌相空间重构预测中,在参考矢量上叠加一定强度的正态分布噪声,形成多个扰动后的参考矢量,分别预测后得到多个预测结果,再由这些预测结果合成概率化的预测结果。采用这种Ensemble技术,不仅可以提高预测准确率,还可以得到概率化的预测结果。 | 杨正瓴 王渭巍 曹东波 张军 陈曦 | 2007 | 电力系统自动化2007，31，23： | 14 |
| 8 | 基于Ensemble的医院信息系统集成平台的研究与探索显示文摘目的:在医院内部信息系统集成方面,传统点对点接口通信模式存在系统耦合度高,系统整体稳定性和安全性难以预测和控制等隐患。不同业务系统之间难以实现数据交换与资源共享。如何打造一个稳定、高效、安全、可管理的集成平台,以满足不断变化的应用需求是一个亟待解决的问题。方法:将Ensemble集成平台技术引入到医院信息化建设中进行研究是一项非常有意义的工作,在分析传统点对点接口通信模式不足的基础上,文章结合Ensemble集成平台技术,建立了以病人为中心的统一视图,实现了跨平台的数据交换与共享。结果:通过Ensemble集成平台技术建立了以患者就诊流程为核心的内部信息共享交互平台,实现了全院数据交换与共享,消除了'信息孤岛',实现了新业务应用的快速部署。结论:Ensemble集成平台技术为医院业务变革提供了灵活的、快速实施和部署的系统架构,实现了医疗信息的交换与共享,优化了服务流程,提高了医院运营效率,满足了医院信息化可持续发展。 | 曹茂诚 陈旭 何及夫 牛启润 | 2012 | 中国数字医学2012，7，10： | 14 |
| 9 | Full waveform inversion based on the ensemble Kalman filter method using uniform sampling without replacement显示文摘Full waveform inversion(FWI) has been increasingly more and more important in seismology to better understand the interior structure of the Earth. FWI, by taking advantage of both the traveltime and amplitude in the data, provides high-resolution model parameters of the earth which can produce images with high resolution. However, this inversion method conventionally suffers from non-uniqueness due to many local minima of the objective function and large computing costs. In this study, we propose a new FWI method in a semi-random framework by integrating the ensemble Kalman filter and uniform sampling without replacement. Numerical results demonstrate that the new method can achieve highresolution results and a wider convergence domain. Accordingly, the new method overcomes the disadvantage of conventional FWIs that depend strongly on the initial model. | Jian Wang Dinghui Yang Hao Jing Hao Wu | 2019 | Science Bulletin2019，64，5： | 13 |
| 10 | 新一代LIS系统集成与应用研究显示文摘随着医院数字化进程的发展,LIS已成为医院信息系统的一个重要的组成部分。传统的LIS因为其管理思想以及软件技术等方面的不足,已经无法满足医院业务需求。武汉市中心医院引进了新一代基于多层B/S架构模式的LIS,并与医院的CIS、HIS、体检系统通过Ensemble集成平台集成,与其他系统一同集成到医院门户中。实践证明,LIS性能稳定、安全性高,提高了工作效率,加速了医院建设数字化医院的进程。 | 杨国良 左秀然 | 2010 | 当代医学2010，16，34： | 12 |
| 11 | Ensemble Forecasts of Tropical Cyclone Track with Orthogonal Conditional Nonlinear Optimal Perturbations显示文摘This paper preliminarily investigates the application of the orthogonal conditional nonlinear optimal perturbations(CNOPs)–based ensemble forecast technique in MM5(Fifth-generation Pennsylvania State University–National Center for Atmospheric Research Mesoscale Model). The results show that the ensemble forecast members generated by the orthogonal CNOPs present large spreads but tend to be located on the two sides of real tropical cyclone(TC) tracks and have good agreements between ensemble spreads and ensemble-mean forecast errors for TC tracks. Subsequently, these members reflect more reasonable forecast uncertainties and enhance the orthogonal CNOPs–based ensemble-mean forecasts to obtain higher skill for TC tracks than the orthogonal SVs(singular vectors)–, BVs(bred vectors)– and RPs(random perturbations)–based ones. The results indicate that orthogonal CNOPs of smaller magnitudes should be adopted to construct the initial ensemble perturbations for short lead–time forecasts, but those of larger magnitudes should be used for longer lead–time forecasts due to the effects of nonlinearities. The performance of the orthogonal CNOPs–based ensemble-mean forecasts is case-dependent,which encourages evaluating statistically the forecast skill with more TC cases. Finally, the results show that the ensemble forecasts with only initial perturbations in this work do not increase the forecast skill of TC intensity, which may be related with both the coarse model horizontal resolution and the model error. | Zhenhua HUO Wansuo DUAN Feifan ZHOU | 2019 | Advances in Atmospheric Sciences2019，36，2： | 11 |
| 12 | A soil moisture assimilation scheme based on the ensemble Kalman filter using microwave brightness temperature显示文摘This study presents a soil moisture assimilation scheme, which could assimilate microwave brightness temperature directly, based on the ensemble Kalman filter and the shuffled complex evolution method (SCE-UA). It uses the soil water model of the land surface model CLM3.0 as the forecast operator, and a radiative transfer model (RTM) as the observation operator in the assimilation system. The assimilation scheme is implemented in two phases: the parameter calibration phase and the pure soil moisture assimilation phase. The vegetation optical thickness and surface roughness parameters in the RTM are calibrated by SCE-UA method and the optimal parameters are used as the final model parameters of the observation operator in the assimilation phase. The ideal experiments with synthetic data indicate that this scheme could significantly improve the simulation of soil moisture at the surface layer. Further- more, the estimation of soil moisture in the deeper layers could also be improved to a certain extent. The real assimilation experiments with AMSR-E brightness temperature at 10.65 GHz (vertical polariza- tion) show that the root mean square error (RMSE) of soil moisture in the top layer (0―10 cm) by as- similation is 0.03355 m3·m-3, which is reduced by 33.6% compared with that by simulation (0.05052 m3·m-3). The mean RMSE by assimilation for the deeper layers (10―50 cm) is also reduced by 20.9%. All these experiments demonstrate the reasonability of the assimilation scheme developed in this study. | BingHao Jia ZhengHui Xie XiangJun Tian ChunXiang Shi | 2009 | Science China Earth Sciences2009，52，11： | 10 |
| 13 | 健康体检系统设计与应用显示文摘采用国外先进的多维数据库Cache作为生产数据库、以Ensemble作为与第3方软件进行数据交互的统一平台,开发设计具有B/S 3层架构的健康体检系统。该系统包括基础数据维护、缴费、体检医生工作站等模块,极大提高体检效率和质量,减轻医生工作量。 | 高世龙 李海涛 杨洋 | 2012 | 医学信息学杂志2012，33，11： | 10 |
| 14 | 国家风险动态性的多尺度特征提取与识别:以OPEC国家为例显示文摘国家风险是经济活动主体在国际业务中所面临的来自其他国家的风险,深入研究其内在特征,对于理解和把握国家风险的动态演化规律有着重要意义。鉴于国家风险复杂易变的特点,本文提出了一种基于'分解重构'思想的多尺度特征提取与识别的研究框架,利用Ensemble EMD方法将原始国家风险值分解到短期、中期和长期三个时间尺度上,引入方差贡献率、相关系数和Shapley值刻画各尺度与原始国家风险序列间的波动特征、模态特征以及全局重要度。以12个OPEC石油输出国为样本,实证结果发现:利用各尺度的模态特征和波动特征可以很好地实现样本国国家风险的分类管理,且分类具有较好的一致性;由Shapley值获得不同尺度的全局重要度,对于全部样本国呈现出一致且稳定的内在固有特征,即短期、中期和长期三尺度对国家风险的'贡献度'约为1∶1∶3。这不仅能够为国家风险管理提供了更为丰富的动态特征信息,而且对于更为全面的国家风险特征识别、监测与预测提供了一种新的研究方法。 | 孙晓蕾 姚晓阳 杨玉英 吴登生 李建平 | 2015 | 中国管理科学2015，23，4： | 10 |
| 15 | 基于Ensemble的医院信息系统集成平台应用研究显示文摘目的:为医院各个系统与HIS的整合提供方便灵活的接入方式。方法:在现有信息通信标准(如DICOM HL7)的基础上定义一个技术框架,来实现对整个信息系统的数据整合。结果:集成平台在实现医院内部信息系统数据交换的基础上,更进一步地实现了医院工作流程的集成,从医院整体医疗事务处理的层次上,规范了医院各种信息源所产生的数据处理的步骤、方法和格式,使多个信息系统能顺畅地按一定顺序完成医疗、事务的处理,是实现数字化医院向高级层次发展的重要技术。结论:集成平台结合了IHE和HL7标准,为医院信息集成提供了一个高可用性和高扩展性的平台。 | 杨春梅 海玲 褚贵洋 刘文岐 詹永丰 王宏 | 2014 | 医疗卫生装备2014，35，1： | 9 |
| 16 | Progress in ENSO prediction and predictability study显示文摘ENSO is the strongest interannual signal in the global climate system with worldwide climatic, ecological and societal impacts. Over the past decades, the research about ENSO prediction and predictability has attracted broad attention. With the development of coupled models, the improvement in initialization schemes and the progress in theoretical studies, ENSO has become the most predictable climate mode at the time scales from months to seasons. This paper reviews in detail the progress in ENSO predictions and predictability studies achieved in recent years. An emphasis is placed on two fundamental issues: the improvement in practical prediction skills and progress in the theoretical study of the intrinsic predictability limit. The former includes progress in the couple models, data assimilations, ensemble predictions and so on, and the latter focuses on efforts in the study of the optimal error growth and in the estimate of the intrinsic predictability limit. | Youmin Tang Rong-Hua Zhang Ting Liu Wansuo Duan Dejian Yang Fei Zheng Hongli Ren Tao Lian Chuan Gao Dake Chen Mu Mu | 2018 | National Science Review2018，5，6： | 8 |
| 17 | Molecular feature and therapeutic perspectives of immune dysregulation, polyendocrinopathy, enteropathy, X-linked syndrome显示文摘Regulatory T(Treg) cells, a subtype of immunosuppressive CD4^+T cells, are vital for maintaining immune homeostasis in healthy people. Forkhead box protein P3(FOXP3), a member of the forkhead-wingedhelix family, is the pivotal transcriptional factor of Treg cells. The expression, post-translational modifications, and protein complex of FOXP3 present a great impact on the functional stability and immune plasticity of Treg cells in vivo. In particular, the mutation of FOXP3 can result in immune dysregulation,polyendocrinopathy, enteropathy, X-linked(IPEX) syndrome, which is a rare genetic disease mostly diagnosed in early childhood and can soon be fatal. IPEX syndrome is related to several manifestations,including dermatitis, enteropathy, type 1 diabetes, thyroiditis, and so on. Here, we summarize some recent findings on FOXP3 regulation and Treg cell function. We also review the current knowledge about the underlying mechanism of FOXP3 mutant-induced IPEX syndrome and some latest clinical prospects.At last, this review offers a novel insight into the role played by the FOXP3 complex in potential therapeutic applications in IPEX syndrome. | Qianru Huang Xu Liu Yujia Zhang Jingyao Huang Dan Li Bin Li | 2020 | Journal of Genetics and Genomics2020，47，1： | 8 |
| 18 | Selective Ensemble Extreme Learning Machine Modeling of Effluent Quality in Wastewater Treatment Plants显示文摘Real-time and reliable measurements of the effluent quality are essential to improve operating efficiency and reduce energy consumption for the wastewater treatment process.Due to the low accuracy and unstable performance of the traditional effluent quality measurements,we propose a selective ensemble extreme learning machine modeling method to enhance the effluent quality predictions.Extreme learning machine algorithm is inserted into a selective ensemble frame as the component model since it runs much faster and provides better generalization performance than other popular learning algorithms.Ensemble extreme learning machine models overcome variations in different trials of simulations for single model.Selective ensemble based on genetic algorithm is used to further exclude some bad components from all the available ensembles in order to reduce the computation complexity and improve the generalization performance.The proposed method is verified with the data from an industrial wastewater treatment plant,located in Shenyang,China.Experimental results show that the proposed method has relatively stronger generalization and higher accuracy than partial least square,neural network partial least square,single extreme learning machine and ensemble extreme learning machine model. | Li-Jie Zhao 1,2 Tian-You Chai 2 De-Cheng Yuan 1 1 College of Information Engineering,Shenyang University of Chemical Technology,Shenyang 110042,China 2 State Key Laboratory of Synthetical Automation for Process Industries,Northeastern University,Shenyang 110189,China | 2012 | International Journal of Automation and computing2012，9，6： | 8 |
| 19 | Application and improvement of an adaptive ensemble Kalman filter for soil moisture data assimilation显示文摘Accurate assignment of model and observation errors is crucial for the successful application of land surface data assimilation algorithms. Poorly-specified model and observation errors can significantly degrade assimilation results. In 2008, Reichle et al. developed an operational procedure to adaptively tune model and observation errors. In this paper, we modified and applied Reichle's procedure in the Noah land surface model to assimilate observed surface soil moisture data. Numerical simulations showed that: (1) the best estimate of model and observation errors appears when the empirical factor β equals 1.02; (2) the Reichle procedure can be deployed to adaptively tune errors if their true values change slowly; and (3) convergence of the Reichle procedure was improved using better initial errors achieved by iterative computations. | Shi XiaoKang Wen Jun Liu JianWen Tian Hui Wang Xin Li YaoDong | 2010 | Science China Earth Sciences2010，53，11： | 8 |
| 20 | The influence of tropical Indian Ocean warming on the Southern Hemispheric stratospheric polar vortex显示文摘During the past decades, concurrent with global warming, most of global oceans, particularly the tropical Indian Ocean, have become warmer. Meanwhile, the Southern Hemispheric stratospheric polar vortex (SPV) exhibits a deepening trend. Although previous modeling studies reveal that radiative cooling effect of ozone depletion plays a dominant role in causing the deepening of SPV, the simulated ozone-depletion-induced SPV deepening is stronger than the observed. This suggests that there must be other factors canceling a fraction of the influence of the ozone depletion. Whether the tropical Indian Ocean warming (IOW) is such a factor is unclear. This issue is addressed by conducting ensemble atmospheric general circulation model (AGCM) experiments. And one idealized IOW with the amplitude as the observed is prescribed to force four AGCMs. The results show that the IOW tends to warm the southern polar stratosphere, and thus weakens SPV in austral spring to summer. Hence, it offsets a fraction of the effect of the ozone depletion. This implies that global warming will favor ozone recovery, since a warmer southern polar stratosphere is un-beneficial for the formation of polar stratospheric clouds (PSCs), which is a key factor to ozone depletion chemical reactions. | LI ShuangLin Nansen-Zhu International Research Centre, Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China | 2009 | Science China Earth Sciences2009，52，3： | 7 |
您所在的机构暂未开通此部分的功能，请联系管理员