检索结果-南通市图书馆

A Comparison of Three Kinds of Multimodel Ensemble Forecast Techniques Based on the TIGGE Data

Acta meteorologica Sinica 2012年第1期26卷 41-51页

作者：智协飞祁海霞白永清林春泽 Key Laboratory of Meteorological Disaster of Ministry of Education Nanjing University of Information Science & Technology Wuhan Institute of Heavy Rain China Meteorological Administration

Based on the ensemble mean outputs of the ensemble forecasts from the ECMWF （European Centre for Medium-Range Weather Forecasts）, JMA （Japan Meteorological Agency）, NCEP （National Centers for Environmental Prediction）, and UKMO （United Kingdom Met Office） in THORPEX （The Observing System Research and Predictability Experiment） Interactive Grand Global Ensemble （TIGGE） datasets, for the Northern Hemisphere （10~ 87.5~N, 0~ 360~） from i June 2007 to 31 August 2007, this study carried out multimodel ensemble forecasts of surface temperature and 500-hPa geopotential height, temperature and winds up to 168 h by using the bias-removed ensemble mean （BREM）, the multiple linear regression based superensemble （LRSUP）, and the neural network based superensemble （NNSUP） techniques for the forecast period from 8 to 31 August 2007. A running training period is used for BREM and LRSUP ensemble forecast techniques. It is found that BREM and LRSUP, at each grid point, have different optimal lengths of the training period. In general, the optimal training period for BREM is less than 30 days in most areas, while for LRSUP it is about 45 days.

关键词： multimodel superensemble bias-removed ensemble mean multiple linear regression neuralnetwork running training period TIGGE

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

用Matlab中的Neural Network Toolbox仿真赤道东太平洋SST的预报模型

引用

海洋科学 2001年第2期25卷 38-42页

作者：张韧蒋国荣李妍解放军理工大学气象学院海洋气象教研室南京211101

基于NCEP/NCAR再分析资料和COADS海洋资料中的全球月平均海平面气压场、850hPa纬向风场及海表温度场 ,利用Matlab中的neuralnetworkToolbox仿真环境和BP模型改进算法比较准确地仿真和反演出了南方涛动指数、赤道纬向风指数和滞后的赤道... 详细信息

基于NCEP/NCAR再分析资料和COADS海洋资料中的全球月平均海平面气压场、850hPa纬向风场及海表温度场 ,利用Matlab中的neuralnetworkToolbox仿真环境和BP模型改进算法比较准确地仿真和反演出了南方涛动指数、赤道纬向风指数和滞后的赤道东太平洋海温之间的动力结构和预报模型。该模型具有很好的拟合精度和可行的预报效果 ,可在一定时效内预测赤道东太平洋月平均海温的变化趋势。由于所建系统是具有直接因果关系的预报模型 ,因此不仅可直接用于预测。

关键词： neuralnetwork 系统仿真反演赤道东太平洋SST模

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Health Research of Wheel-Set Based on Data Mining

Health Research of Wheel-Set Based on Data Mining

引用

作者：何蕾西南交通大学

学位级别：硕士

As one of the key parts of high-speed train,wheel-set directly contacts with rails,and it is easy to produce corresponding wear and damage.Therefore,it is the top priority for ensuring the safety of train operation that studying the corresponding health state of train.Only when we grasp the wheel-set condition and understand the development trend of wheel-set parameters,can we provide a scientific basis for policymakers to formulate corresponding treatment measures.Therefore,in this thesis,the following works are done for the health status of motor vehicle wheel-set.On the one hand,the wear rule of wheel profile is studied and the correlation analysis between the wheel geometry parameters is done while the wheel diameter is used as the output for numerical fitting analysis.The analysis of wheel profile wear rule shows that the variation trend of diameters at different wheel location with the same carriage are roughly the same.Wheel tread wear generally presents a linear growth trend.During 4.40-4.55 million kilometer,wheel tread wear is very serious.With the increase of the running distance,the change rate of the QR value gradually tends to be slow.The QR value changes faster at 4.27-4.55 million kilometer,and the vertical wear of the rim is more serious.On the other hand,based on the historical data of wheel geometric parameters,ARIMA model and BP neural network model are applied to the prediction and analysis respectively,and the prediction results of the two models are compared.The ARIMA model has the best prediction effect on the wheel diameter,and the correlation coefficient is up to 93.61%.Secondly,the prediction accuracy of the tread wear is higher and the correlation coefficient is 84.97%.The final remaining three parameters are not very ideal,because the correlation coefficient R values are less than 80%.Therefore,the prediction of both wheel diameter and tread wear based on ARIMA model is better.The BP neural network is better for wheel tread wear and flange thickness prediction when it is used for whee

关键词： wheel-set datamining ARIMA neuralnetwork healthassessment lifeprediction

来源：

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Predicting Cervical Lymph Node Metastasis in Tongue Cancer based on CT Radiomics and Neural Network

Predicting Cervical Lymph Node Metastasis in Tongue Cancer b...

引用

2019第一届全国口腔颌面-头颈肿瘤学术大会——聚合引领、协同发展

作者：伍文杰钟奕伟北京大学口腔医院

Purpose/Background:Squamous cell carcinoma is the most common malignancy in the oral and maxillofacial region. Patient’s treatment strategies such as whether to perform neck dissection were significantly determined by the status of cervical lymph nodes. Radiomics realize the high-throughput extraction of radiomics data from medical images. The commonly used evaluation tool was CT, which mainly depends on the size, shape and necrosis. The radiomics of images was proposed to characterize the heterogeneity of underlying biological processes such as metabolism, hypoxia, cellular proliferation, vascularization and necrosis. We hypothesize that certain radiomics features based on CT will have statistically significant correlations to the status of cervical lymph nodes. This study is a diagnostic study and the object is tongue carcinoma. The aim of this study was to evaluate the predictive value of contrast-enhanced computed tomography（CECT） texture features and develop a neural network model for cervical lymph node metastasis prediction in patients with tongue squamous cell carcinoma based on pretreatment CECT.

关键词： Radiomics CT Tonguecancer Cervicallymphnode neuralnetwork

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：