区间偏最小二乘结合差分进化算法应用于鱼粉近红外光谱波长筛选

蛋白质含量是评价鱼粉质量的重要指标,该文采用近红外(NIR)光谱分析技术结合特征筛选方法建立了鱼粉蛋白质含量的快速定量分析模型,并结合区间偏最小二乘(iPLS)和二进制变异策略的差分进化(DE)算法建立了区间偏最小二乘差分进化(iPLS-DE)的波长筛选优化模式,对鱼粉NIR光谱数据进行特征波长筛选。iPLS-DE通过调试iPLS中等分子区间的数量,优选出9个最优特征波段,再采用二进制变异策略的DE算法在最优特征波段内筛选离散特征波长组合,最后根据模型的评价指标确定iPLS-DE优选模型并与iPLS优选模型进行比较。结果表明,将鱼粉全谱等分为5个子区间时,iPLS-DE筛选出50个离散特征波长建立的优选模型对测试集样品的预测均方根误差和相对分析误差分别为1.033%和4.058,而iPLS优选模型对测试集样品的预测均方根误差和相对分析误差分别为1.131%和3.855。表明iPLS-DE方法能够有效地提高NIR光谱分析模型对鱼粉蛋白质定量检测的预测能力。     

偏最小二乘及双波长K系数光度法同时测定矿物中钛,铁

本文运用化学计量学中的偏最小二乘法及双波长Ｋ系数法实现了Ｔｉ、Ｆｅ的同时测定，方法用于铝钒土及钛铁矿中Ｔｉ、Ｆｅ同时测定，结果满意。     

Bagging偏最小二乘和Boosting偏最小二乘算法的金银花醇沉过程近红外光谱定量模型预测能力研究

建立金银花醇沉过程中稳健的近红外光谱( Near infrared spectroscopy,NIR)定量模型,为金银花醇沉过程的快速评价提供方法。研究基于金银花醇沉过程绿原酸的 NIR 数据,通过建立 Bagging 偏最小二乘(Bagging-PLS)模型、Boosting偏最小二乘(Boosting-PLS)模型与偏最小二乘(Partial Least Squares,PLS)模型,实现对模型性能比较;在此基础上,采用组合间隔偏最小二乘法( Synergy interval partial least squares,siPLS)和竞争自适应抽样( Competitive adaptive reweighted sampling,CARS )法分别对光谱进行变量筛选,建立模型,实现了对模型预测性能的考察。实验结果表明, Bagging-PLS和Boosting-PLS(潜变量因子数设为10)的预测性能均优于 PLS 模型。在此基础上,两批样品采用 siPLS 筛选变量,第一个批次金银花筛选波段820~1029.5 nm和1030~1239.5 nm,第二个批次金银花醇沉筛选波段为820~959.5 nm和960~1099.5 nm;采用CARS方法变量筛选,两批样品分别选择5折交叉验证和10折交叉验证,取交叉验证均方根误差( RMSECV)值最小的子集作为最终变量筛选的结果。经过变量筛选的两批金银花醇沉过程中的绿原酸含量Bagging-PLS和Boosting-PLS模型的预测均方根误差(RMSEP)值降低了0.02~0.04 g/L,预测相关系数提高了4%~5%。综上,Baggning-PLS和Boosting-PLS算法可作为金银花醇沉过程NIR定量模型的快速预测方法。     

基于移动窗口-迭代遗传算法的近红外光谱波长选择方法

光谱样本数据常会受到环境噪声和其它组分的干扰，应作波长选择，以提高分析精度。近红外光谱谱区宽，搜索空间过大，难以直接采用遗传算法进行波长选择。为此本研究提出先用移动窗口偏最小二乘法（MWPLS）从宽谱区中初选出信息区间，再采用改进的迭代遗传算法（IGA）从中选出最优的信息子区间。MWPLS用移动窗口沿全谱区扫描，对信息区间的定位效果好，而IGA将顾及光谱数据的连续相关特性，运行多轮GA，并以上轮选择结果平滑处理后作为先验知识支持下轮的种群初始化。由此选出的连续相邻的波长点作为自变量，进行PLS建模，既可显著地简化模型，又保留一定的数据冗余，模型的稳健性好、分析精度高。将其用于小麦水分的近红外分析，效果良好，预测性能明显优于其它方法。     

偏最小二乘近红外光谱法测定瘦肉脂肪酸组成的研究

利用偏最小二乘将瘦肉的近红外光谱数据分别与其棕榈酸、棕榈油酸、硬脂酸、油酸、亚油酸含量建立校正模型,并用交互校验和外部检验来考查模型的可靠性.各脂肪酸模型的校正相关系数分别为0.9998、0.9844、0.9963、0.9754、0.9969,均方估计残差(RMSEC)分别为0.0231、0.0485、0.111、0.373、0.311,交互校验均方残差(RMSECV)分别为0.509、0.115、0.225、0.848、0.649.应用所建立的各脂肪酸近红外模型对瘦肉脂肪酸组成进行预测,并对各脂肪酸的预测值与气相色谱法测定值进行配对t-检验,结果表明两者差异均不显著(p>0.05).     

仪器噪声在近红外光谱偏最小二乘模型内的传播效应

在实际多元校正应用中有很多因素会影响偏最小二乘(PLS)模型的预测效果,作为光谱数据本源的仪器噪声是其中的重要影响因素。以往的研究工作多使用各种滤波器或平滑方法来降低仪器噪声的影响,然而对于仪器噪声如何影响偏最小二乘的建模过程和模型预测能力鲜有报道。该文阐述并论证了仪器噪声怎样通过第一个隐变量的计算被引入模型中,经过对偏最小二乘计算过程的理论推导,论述了噪声的引入对偏最小二乘权重向量、载荷向量计算具有累积效应,并随着后续隐变量的计算不断在模型中传递,从而对偏最小二乘模型产生影响。同时对偏最小二乘模型的预测误差进行理论分解,将其划分为无噪理想模型本身的误差和由噪声传播导致的误差。结果表明,仪器噪声不仅会降低偏最小二乘模型的预测性能,还会影响偏最小二乘模型的最优复杂度选择。     

基于移动窗口-迭代遗传算法的近红外光谱波长选择方法

光谱样本数据常会受到环境噪声和其它组分的干扰,应作波长选择,以提高分析精度.近红外光谱谱区宽,搜索空间过大,难以直接采用遗传算法进行波长选择.为此本研究提出先用移动窗口偏最小二乘法(MWPLS)从宽谱区中初选出信息区间,再采用改进的迭代遗传算法(IGA)从中选出最优的信息子区间.MWPLS用移动窗口沿全谱区扫描,对信息区间的定位效果好,而IGA将顾及光谱数据的连续相关特性,运行多轮GA,并以上轮选择结果平滑处理后作为先验知识支持下轮的种群初始化.由此选出的连续相邻的波长点作为自变量,进行PLS建模,既可显著地简化模型,又保留一定的数据冗余,模型的稳健性好,分析精度高.将其用于小麦水分的近红外分析,效果良好,预测性能明显优于其它方法.     

遗传算法用于偏最小二乘方法建模中的变量筛选

利用全局搜索方法－遗传算法（genetic algorithms,GA)对近红外光谱分析中的波长变量进行筛选,再用偏最小二乘方法（patrial least squares,PLS）建立分析校正模型。对两类样品的近红外光谱分析应用实例表明,这种选取变量进行校正的方法,不仅简化、优化了模型,而且增强了所建模型的预测能力,尤其适用于单纯PLS较以校正关联的体系。     

Analysis of elements in wine using near infrared spectroscopy and partial least squares regression

The use of visible (VIS) and near infrared spectroscopy (NIRS) to measure the concentration of elements in Australian wines was investigated. Both white (n=32) and red (n=94) wine samples representing a wide range of varieties and regions were analysed by inductively coupled plasma mass spectrometry (ICP-MS) for the concentrations of calcium (Ca), potassium (K), magnesium (Mg), phosphorus (P), sodium (Na), sulphur (S), iron (Fe), boron (B) and manganese (Mn). Samples were scanned in transmittance mode (1mm path length) in a monochromator instrument (400-2500nm). The spectra were pre-treated by second derivative and standard normal variate (SNV) prior to developing calibration models using partial least squares (PLS) regression method with cross-validation. The highest coefficients of determination in cross-validation (R(val)(2)) and the lowest errors of cross-validation (SECV) were obtained for Ca (0.90 and 9.80mgL(-1)), Fe (0.86 and 0.65mgL(-1)) and for K (0.89 and 147.6mgL(-1)). Intermediate R(val)(2) (<0.80) and SECV were obtained for the other minerals analysed. The results showed that some macro- and microelements present in wine might be measured by VIS-NIRS spectroscopy.     

Quantifying silica in filter-deposited mine dusts using infrared spectra and partial least squares regression

The feasibility of measuring airborne crystalline silica (α-quartz) in noncoal mine dusts using a direct-on-filter method of analysis is demonstrated. Respirable α-quartz was quantified by applying a partial least squares (PLS) regression to the infrared transmission spectra of mine-dust samples deposited on porous polymeric filters. This direct-on-filter method deviates from the current regulatory determination of respirable α-quartz by refraining from ashing the sampling filter and redepositing the analyte prior to quantification using either infrared spectrometry for coal mines or x-ray diffraction (XRD) from noncoal mines. Since XRD is not field portable, this study evaluated the efficacy of Fourier transform infrared spectrometry for silica determination in noncoal mine dusts. PLS regressions were performed using select regions of the spectra from nonashed samples with important wavenumbers selected using a novel modification to the Monte Carlo unimportant variable elimination procedure. Wavenumber selection helped to improve PLS prediction, reduce the number of required PLS factors, and identify additional silica bands distinct from those currently used in regulatory enforcement. PLS regression appeared robust against the influence of residual filter and extraneous mineral absorptions while outperforming ordinary least squares calibration. These results support the quantification of respirable silica in noncoal mines using field-portable infrared spectrometers.

Effect of temperature variation on the visible and near infrared spectra of wine and the consequences on the partial least square calibrations developed to measure chemical composition

Many studies have reported the use of near infrared (NIR) spectroscopy to characterize wines or to predict wine chemical composition. However, little is known about the effect of variation in temperature on the NIR spectrum of wine and the subsequent effect on the performance of calibrations used to measure chemical composition. Several parameters influence the spectra of organic molecules in the NIR region, with temperature being one of the most important factors affecting the vibration intensity and frequency of molecular bonds. Wine is a complex mixture of chemical components (e.g. water, sugars, organic acids, and ethanol), and a simple ethanol and water model solution cannot be used to study the possible effects of temperature variations in the NIR spectrum of wine. Ten red and 10 white wines were scanned in triplicate at six different temperatures (25 °C, 30 °C, 35 °C, 40 °C, 45 °C and 50 °C) in the visible (vis) and NIR regions (400-2500 nm) in a monochromator instrument in transmission mode (1 mm path length). Principal component analysis (PCA) and partial least squares (PLS) regression models were developed using full cross validation (leave-one-out). These models were used to interpret the spectra and to develop calibrations for alcohol, sugars (glucose + fructose) and pH at different temperatures. The results showed that differences in the spectra around 970 nm and 1400 nm, related to OH bonding were observed for both varieties. Additionally an effect of temperature on the vis region of red wine spectra was observed. The standard error of cross validation (SECV) achieved for the PLS calibration models tended to inverse as the temperature increased. The practical implication of this study it is recommended that the temperature of scanning for wine analysis using a 1 mm path length cuvette should be between 30 °C and 35 °C.     

Coal analysis by application of the partial least squares method to infrared spectra

Summary A method for the rapid characterization of brown coals based on the application of a powerful method of principal component analysis, the Partial Least Squares method (PLS), is described. A data catalogue of 44 brown coals from different deposits of East European and Asian countries was used, which lists analyses of several coal parameters. Infrared spectra of brown coals were recorded and different coal properties were predicted with the help of PLS. The results show that, with the PLS-method used, several coal properties can be predicted and it is possible to describe the classification of a coal for several technological processes. The developed method is useful because of the multiplicity of information obtained within a short time and because it is possible to replace lengthy classical methods.     

A practical approach for near infrared spectral quantitative analysis of complex samples using partial least squares modeling

The number of latent variables (LVs) or the factor number is a key parameter in PLS modeling to obtain a correct prediction. Although lots of work have been done on this issue, it is still a difficult task to determine a suitable LV number in practical uses. A method named independent factor diagnostics (IFD) is proposed for investigation of the contribution of each LV to the predicted results on the basis of discussion about the determination of LV number in PLS modeling for near infrared (NIR) spectra of complex samples. The NIR spectra of three data sets of complex samples, including a public data set and two tobacco lamina ones, are investigated. It is shown that several high order LVs constitute main contributions to the predicted results, albeit the contribution of the low order LVs should not be neglected in the PLS models. Therefore, in practical uses of PLS for analysis of complex samples, it may be better to use a slightly large LV number for NIR spectral analysis of complex samples. Supported by the National Natural Science Foundation of China (Grant Nos. 20775036 & 20835002)     

Determination of lecithin and soybean oil in dietary supplements using partial least squares-Fourier transform infrared spectroscopy

Lecithin and soybean oil in dietary supplements were determined by Fourier transform infrared spectrometry transmission measurements in dichloromethane in combination with a partial least squares (PLS) regression. Two different PLS models were developed, using 16 synthetic mixtures of analytes in dichloromethane, making measurements in the spectral range from 931.8 to 1252.3 cm⁻¹ for lecithin and from 911.4 to 1246.9 cm⁻¹ and 1695.3 to 1774.5 cm⁻¹ for soybean oil. Seven products from the Spanish market with lecithin concentrations between 21.1% and 99.1% and soybean oil concentrations between 0% and 37.2% were analyzed by the proposed method and the data was compared to a chromatographic reference procedure obtaining accurate results. For samples spiked with amounts between 50 and 250 mg of lecithin and soybean oil recovery percentages between 98.0% and 102.1% and between 93.6% and 102.0% with an average precision of 0.35% and 0.41% were achieved for lecithin and soybean oil, respectively. This method can be applied for the quality control of dietary supplements.     

Partial least square analysis of lysozyme near-infrared spectra

Proteins possess strong absorption features in the combination range (5000-4000 cm⁻¹) of the near infrared (NIR) spectrum. These features can be used for quantitative analysis. Partial least squares (PLS) regression was used to analyze NIR spectra of lysozyme with the leave-one-out, full cross-validation method. A strategy for spectral range optimization with cross-validation PLS calibration was presented. A five-factor PLS model based on the spectral range between 4720 and 4540 cm⁻¹ provided the best calibration model for lysozyme in aqueous solutions. For 47 samples ranging from 0.01 to 10 mg/mL, the root mean square error of prediction was 0.076 mg/mL. This result was compared with values reported in the literature for protein measurements by NIR absorption spectroscopy in human serum and animal cell culture supernatants.     

Determination of nimesulide in pharmaceutical and biological samples by a spectrophotometric method assisted with the partial least square method

A simple and sensitive spectrophotometric method for the determination of nimesulide in bulk, in pharmaceutical dosage form, and in biological fluids was developed. The method is based on the reduction of the nitro group of nimesulide by zinc and hydrochloric acid followed by diazotization, and coupling with orcinol in basic medium to form a stable chromophore, which absorbs at 465 nm. The method showed a good linearity in the range 0.4–4.0 μg mL^?1. Partial least square modeling as a powerful multivariate statistical tool is also applied, compiled, and compared for determination of nimesulide. The experimental matrix for the partial least square calibration method was designed with 24 samples. The cross-validation was used for selecting the number of factors. The root mean square error prediction (RMSEP) and the relative error of prediction (REP %) were 0.089 and 3.95, respectively. The developed method is free from the interference of common excipients used in pharmaceutical dosages. The method was also used for the determination of nimesulide in pharmaceutical dosages as well as in human serum and urine samples.     

多模型共识偏最小二乘法用于近红外光谱定量分析

将多模型共识偏最小二乘法用于近红外光谱定量分析。利用随机抽取的训练子集建立一系列偏最小二乘模型,选取其中性能较好的部分模型作为成员模型,用这些成员模型来预测未知样品。将该方法用于一组生物样本的近红外光谱与样品中人血清白蛋白、γ-球蛋白以及葡萄糖含量之间的建模研究,并与单模型偏最小二乘法了进行比较。结果 PLS对独立测试集中三种组分进行50次重复预测的平均RMSEP分别为0.1066,0.0853和0.1338,RMSEP的标准偏差分别为0.0174,0.0144和0.0416;而本方法重复预测的平均RMSEP分别为0.0715,0.0750和0.0781,RMSEP的标准偏差分别为0.0033,0.2729×10-4和0.0025。