期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
光谱多元分析校正集和验证集样本分布优选方法研究 被引量:52
1
作者 刘伟 赵众 +2 位作者 袁洪福 宋春风 李效玉 《光谱学与光谱分析》 SCIE EI CAS CSCD 北大核心 2014年第4期947-951,共5页
分析了校正集和验证集样品数随性质分布不均匀性对光谱多元分析校正的不良影响,揭示了实际光谱多元校正中"均值化"现象,即性质值小的样本预测值结果偏大,性质值大的则偏小,提出了一种优选样品新方法—Rank-KS。其综合考虑光... 分析了校正集和验证集样品数随性质分布不均匀性对光谱多元分析校正的不良影响,揭示了实际光谱多元校正中"均值化"现象,即性质值小的样本预测值结果偏大,性质值大的则偏小,提出了一种优选样品新方法—Rank-KS。其综合考虑光谱空间和性质空间对样本进行挑选,将性质空间平均分为若干小区间,在每个小区间内分别利用Kennard-Stone法和随机法进行校正集和验证集样本的挑选,这样得到的校正集和验证集可明显改善样本数随性质分布的均匀性。以红外光谱测定汽油中碳酸二甲酯(DMC)含量和近红外光谱测定二甲亚砜溶液二甲亚砜浓度为研究对象,分别采用Rank-KS、随机法、Kennard-Stone、浓度梯度法和SPXY等方法选择校正集和验证集样品,使用多元线性回归和偏最小二乘法建立模型,比较这些方法对光谱多元校正分析的影响,结果表明Rank-KS方法可改善校正集和验证集样品数随性质分布的均匀性;对于样本数分布中间局部样本多和两端局部少、或者局部没有样本的样本集,使用Rank-KS算法挑选校正集,无论使用MLR还是PLS1建立多元分析模型,均能明显改善其模型预测能力,使得到的模型的预测均方根最小。 展开更多
关键词 样本分集 PLS回归 Kennard-Stone理论 近红外光谱 红外光谱
下载PDF
Biofilm Determination of Listeria monocytogenes That Isolated from Different Sources
2
作者 Srwa Ali Muhammed 《Journal of Life Sciences》 2014年第10期805-810,共6页
The study was conducted for the detection of Listeria monocytogenes bacteria from different sources (CSF and blood) obtained from patients in Pediatric hospital and from food sources like (yogurt, raw vegetables an... The study was conducted for the detection of Listeria monocytogenes bacteria from different sources (CSF and blood) obtained from patients in Pediatric hospital and from food sources like (yogurt, raw vegetables and raw milk, sausage). Ten isolates were isolated from 150 specimens one of them from CSF and one isolate isolated from blood samples the others isolated from food specimens 6 isolates isolated from sausage and 2 from raw vegetables. Isolates were identified traditionally involved culture methods based on selective enrichment and plating followed by the characterization of Listeria spp. based on colony morphology, sugar fermentation and haemolytic properties, identification by Api listeria was done. Determine the isolates that produce biofilm by tissue culture plate method. The highest biofilm forming strains ofListeria monocytogenes isolates appear in No. (D10, El, E5 and E7) OD reading each of them is (0.13, 0.09, 0.11 and 0.19) respectively, the lowest or poor biofilm forming strains appear in No. (D11, D12, E2, E3, E4 and E6) that optical density (OD) reading are (0.04, 0.03, 0.05, 0.04, 0.05 and 0.03) respectively by comparing with control prepared in well (A12) that stained by crystal violate without putting any isolates and the OD reading is (0.003). Confirmation by PCR was done only for four isolates that produce biofilm (D10 and El) that obtained from CSF and blood sample and for (E5 and E7) that obtained from food samples. 展开更多
关键词 Listeria monocytogenes BIOFILM API PCR OD.
下载PDF
Corrected-loss estimation for Error-in-Variable partially linear model 被引量:3
3
作者 JIN Jiao TONG XingWei 《Science China Mathematics》 SCIE CSCD 2015年第5期1101-1114,共14页
We consider an Error-in-Variable partially linear model where the covariates of linear part are measured with error which follows a normal distribution with a known covariance matrix. We propose a corrected-loss estim... We consider an Error-in-Variable partially linear model where the covariates of linear part are measured with error which follows a normal distribution with a known covariance matrix. We propose a corrected-loss estimation of the covariate effect. The proposed estimator is asymptotically normal. Simulation studies are presented to show that the proposed method performs well with finite samples, and the proposed method is applied to a real data set. 展开更多
关键词 partially linear model Error-in-Variable robust analysis
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部