历史查询   



 为了更好的帮助您理解掌握查询词或其译词在地道英语中的实际用法，我们为您准备了出自英文原文的大量英语例句，供您参考。 
We also show that SBI is applicable to other underlying predictors, such as the McFarling Combined predictor.


In this paper we present the Bayesian Combined Predictor (BCP), a probabilistically motivated predictor for time series prediction.




 The Climatology and persistance (CLIPER) models for predicting typhoon motion were proposed from regression analysis of the future zonal and meridional displacements based on climatology, persistance and some combined predictors for the South China Sea (113123°E, 1025°N), and a set of equations to predict the zonal and meridional displacements of typhoon track were deriyed based on entire samples at24 h to 120 h intervals. Also, entire sample were stratified according to the prior 24 h heading subgroups,... The Climatology and persistance (CLIPER) models for predicting typhoon motion were proposed from regression analysis of the future zonal and meridional displacements based on climatology, persistance and some combined predictors for the South China Sea (113123°E, 1025°N), and a set of equations to predict the zonal and meridional displacements of typhoon track were deriyed based on entire samples at24 h to 120 h intervals. Also, entire sample were stratified according to the prior 24 h heading subgroups, and subgroup CLIPER forecast equations were derived based on subgroup sample. It is shown that both the dependent samples and the independent samples are predicted more accurately by the stratified equations than by the entire sample equations. The average forecast errors for either entire sample model or subgroup sample model are smaller than those by similar kinds of models in our country and overseas. Especially, it is worthy of note that typhoon meridional displacement strongly influences the zonal displacement at each forecast interval and that meridional displacement is always selected as a predictor in the zonal forecast equations. Thus, the CLIPER approach provides a simple and low cost technique to predict typhoon motion for coast marine and meteorological stations, especially for shipping vessels.  基于南海（113°─123°E，10°─25°N）台风的气候学、持续性和一些组合因子，根据与未来的经向、纬向位移的回归分析，发展了一种预报台风路径的气候与持续的（CLIPER）模式。并建立了一组从24小时到120小时的预报台风路径经、纬向位移的预报方程，同样，根据台风前24小时移向的分组，建立了分类样本预报方程，对非独立样本和独立样本试报表明，分类样本方程比全样本方程有更高的精度，无论对于全样本模式还是分类样本模式，平均预报误差均小于国内、外同类模式。特别值得指出的是，在每个预报时次中，台风的经向位移对其纬向位移有较强的影响，而且，在纬向位移预报方程中，经向位移总是作为前几个因子被入选，因此，CLIPER方法为沿岸海洋台站和气象台站以及远洋船舶预报台风路径提供了一种简便易行的技术。  By means of analysing the mechanism of blending materials,a general blending efficiency model was proposed.Applying this model to an example,a formula of blending efficiency was gained which is more accurate than those in papers[2～3].Finally,a highprecision optimal combining predictor formula for calculating blending efficiency is provided.  在分析混匀机理的基础上，提出了反映因素相关的原料混匀效率的三元二次修正公式，应用回归理论得出比较符合实际的混匀效率计算公式；同时，应用最优组合预测方法，求出一个精度较高的混匀效率计算公式。  The Climatology and peristance (CLIPER) models for predicting typhoon motion were proposed from regression analysis of the future zonal and meridional displacements based on climatology, persistance and some combined predictors for the South China Sea (113123°E, 1025°N) , and a set of equations to predict the zonal and meridional displacements of typhoon track were derived based on entire samples at24 h to 120 h intervals. Also, entire sample were stratified according to the prior 24 h heading subgroups,... The Climatology and peristance (CLIPER) models for predicting typhoon motion were proposed from regression analysis of the future zonal and meridional displacements based on climatology, persistance and some combined predictors for the South China Sea (113123°E, 1025°N) , and a set of equations to predict the zonal and meridional displacements of typhoon track were derived based on entire samples at24 h to 120 h intervals. Also, entire sample were stratified according to the prior 24 h heading subgroups, and subgroup CLIPER forecast equations were derived based on subgroupsample. It is shown that both the dependent samples and the independent samples are predicted more accurately by the stratified equations than by the entire sample equations. The average forecast errors for either entire sample model or subgroup sample model are smaller than those by similar kinds of models in our country and overseas. Especially, it is worthy of note that typhoon meridional displacement stronly influences the zonal displacement at each forecast interval and that meridional displacement is always selected as a predictor in the zonal forecast equations. Thus, the CLIPER approach provides a simple and low cost technique to predict trphoon motion for coast marine and meteorlogical stations, especially for shipping vessels.  基于南海(113°—123°E,10°—25°N)台风的气候学、持续性和一些组合因子,根据与未来的经向、纬向位移的回归分析,发展了一种预报台风路径的气候与持续的(CLIPER)模式。并建立了一组从24小时到120小时的预报台风路径经纬向位移的预报方程,同样,根据台风前24小时移向的分组,建立了分类样本预报方程,对非独立样本和独立样本试报表明,分类样本方程比全样本方程有更高的精度,无论对于全样本模式还是分类样本模式,平均预报误差均小于国内外同类模式,特别值得指出的是,在每个预报时次中。台风的经向位移对其纬向位移有较强的影响,而且,在纬向位移预报方程中,经向位移总是作为前几个位子被入选,因此,CLIPER方法为沿岸海洋台站和气象台站以及远洋船舶预报台风路径提供了一种简便易行的技术。   << 更多相关文摘 
相关查询  



