自适应蚁群优化算法的近红外光谱特征波长选择方法

为提高近红外光谱预测模型的精度和适用性,同时简化模型,提出了自适应蚁群优化偏最小二乘法优选特征波长的方法,建立不同产地苹果可溶性固形物含量混合分析模型。收集山东、陕西和新疆的富士苹果,采集3800~14000 cm"1范围的近红外光谱,并对其重要品质指标可溶性固形物含量进行测定。利用蚁群算法启发式全局搜索的特点,结合蒙特卡罗轮盘赌随机选择机制,优选苹果可溶性固形物含量的近红外光谱特征波长,然后用偏最小二乘法建立分析模型。与全光谱偏最小二乘模型和遗传偏最小二乘模型相比,蚁群优化算法选择的波长数最少,模型预测能力最强,预测的相关系数R和预测均方根误差RMSEP分别为0.9708和0.5144。研究结果表明,自适应蚁群优化算法可以有效选择近红外光谱特征波长,提高模型的稳健性和适用性。     

近红外光谱法测定30%TBP/正十二烷中硝酸含量

核燃料后处理工艺控制分析中,有机相中硝酸含量是一项重要的控制参数。通过研究TBP/正十二烷介质中硝酸的近红外光谱,将有机相样品的傅立叶变换近红外光谱与偏最小二乘回归法相结合,建立了含铀后处理有机相样品中硝酸浓度的测量方法。建立的定量校正模型的最佳校正标准偏差(RMSEC)、预测标准偏差(RMSEP)以及相关系数(r)分别为0.011,0.014,0.999。方法检出限为0.05 mol/L,测量结果的相对标准偏差不大于4%(n=6)。采用近红外分析法与滴定法对模拟样品进行测量,对测量结果进行t检验,结果表明两种方法的测定结果无显著性差异。所建方法无需样品预处理,可直接测量,分析速度快,结果准确,具有一定的实用性。     

近红外光谱相似性评估结合局部回归方法无损检测苹果糖度

基于Bayesian相似性评估方法结合偏最小二乘局部回归,对苹果近红外数据库进行数据挖掘。通过相似性计算方法搜索出与预测样品相近的近红外光谱,形成校正子集后采用局部回归方法获得待测样品的相关信息。该方法所建立局部模型的平均检验标准偏差(SEV)约为0.57,分析30个预测样品的预测标准偏差(SEP)约为0.61;基于马氏距离的传统方法建立的偏最小二乘局部模型的平均SEV为0.59,分析30个待测样品的预测SEP为0.64;而采用整个数据库建立的全局偏最小二乘模型的SEV约为0.65,分析30个预测样品SEP约为0.70。基于Bayesian相似性评估的局部回归方法在苹果糖度的近红外无损定量分析中获得较好的应用结果,在实际应用中该方法比全局回归方法具有更强的适用性,为近红外光谱分析提供了新的分析工具。     

独立分量分析预处理法提高苹果糖度模型预测精度研究

为了提高苹果近红外光谱糖度预测模型精度,利用独立分量分析方法(ICA)对苹果近红外光谱进行了预处理,并且建立了糖度的偏最小二乘(PLS)预测模型。结果表明,独立分量分析不但能分离出噪声信号,而且所分离出来的光谱信号也比原始光谱信号光滑。在预处理后的最佳PLS糖度模型校正时的相关系数rc和标准偏差SEC分别为0.9549和0.3361,用于预测时的相关系数rp和标准偏差SEP分别为0.9071和0.4355。与普通的平均处理法的PLS模型相比,其精度有所提高,且模型更加简洁。     

小波变换结合多维偏最小二乘方法用于近红外光谱定量分析

将小波变换和多维偏最小二乘法相结合用于近红外光谱定量校正模型的建立.首先将原始光谱进行小波变换分解,得到系列小波细节系数,通过选取一组受外界因素少、信息强的小波系数组成三维光谱阵,然后再采用多维偏最小二乘法建立校正模型.实验结果表明,该方法所建近红外校正模型的预测能力更强,并更具稳健性.     

血清胆红素的近红外光谱无创检测

血清胆红素的无创检测在疾病的预防、早期诊断与后期治疗等阶段都具有极其重要的作用.本研究提出了一种基于近红外光谱技术的无创血清胆红素新方法.通过采集舌尖的近红外反射光谱并运用偏最小二乘法对采集到的光谱数据进行建模,从而实现对血清胆红素的快速无创检测.将采集到的全部57例样本按照4∶1的比例分训练集和预测集,分别建立总胆红素(TBIL)、直接胆红素(DBIL)和间接胆红素(IBIL)的偏最小二乘回归模型.3个模型的相关系数分别为0.9922,0.9947和0.9486,预测均方根误差(RMSEP)分别为6.13,4.61和4.05 μmol/L.结果表明:舌尖近红外反射光谱结合偏最小二乘法可用于血清胆红素含量的无创检测,并且为其它血液成分的无创检测开辟了新路径.     

小波变换结合多维偏最小二乘方法用于近红外光谱定量分析

将小波变换和多维偏最小二乘法相结合用于近红外光谱定量校正模型的建立。首先将原始光谱进行小波变换分解，得到系列小波细节系数，通过选取一组受外界因素少、信息强的小波系数组成三维光谱阵，然后再采用多维偏最小二乘法建立校正模型。实验结果表明，该方法所建近红外校正模捌的预测能力更强，并更具稳健性。     

近红外光谱法分析格列齐特片

应用化学计量法处理光谱数据,用偏最小二乘法建立格列齐特片的近红外分析模型。通过光谱预处理和模型的逐步优化最终确定定量分析模型的相关系数为0.991,交叉验证均方差(RMSECV)为0.641,预测均方根误差(RMSEP)为0.980,主因子数为4。选取15个验证样品对模型进行检验,检测结果相对误差在-2.04%～3.52%之间。     

偏最小二乘-反向传播-近红外光谱法同时测定饲料中4种氨基酸

偏最小二乘与人工神经网络联用对70个饲料样品建立起天门冬氨酸(Asp)、谷氨酸(Glu)、丝氨酸(Ser)和组氨酸(His)4种氨基酸含量的预测校正模型,以样品平行扫描光谱验证校正模型预测的准确性和重现性。用偏最小二乘法将原始数据压缩为主成分,采用单隐层的反向传播网络建模。取前3个主成分的12个数据输入网络,以Kolmogorov定理为依据,经过实验确定中间层的神经元个数为25,初始训练迭代次数为1000。偏最小二乘-反向传播网络模型对样品4个组分含量的预测决定系数(R2)分别为:0.981、0.997、0.979、0.946;样品平行扫描光谱预测值的标准偏差分别为:0.020、0.029、0.017、0.023。本研究为近红外快速检测在组分含量较低的样品实现多组分同时测定提供了思路。     

基于粒子群算法的波长选择方法用于苹果酸度的近红外光谱分析

采用便携式近红外光谱分析仪,对苹果样品进行扫描获得光谱数据,运用偏最小二乘法结合基于粒子群算法的波长选择方法对苹果试验数据进行多元统计分析,建立数学模型,利用该模型对苹果酸度进行了预测。对于基于粒子群算法和全谱偏最小二乘方法,校正集样品的酸度预测值和实测值之间的相关系数分别为0.9880和0.9553,校正均方根误差分别为0.0197和0.0388;预测集样品的酸度预测值和实测值之间的相关系数分别为0.9833和0.9596,预测均方根误差分别为0.0193和0.0304。与全谱偏最小二乘法相比,基于粒子群算法的偏最小二乘法,不仅较大地减少波长变量而降低计算量,而且也较大地提高了模型性能而增强了模型预测的准确性。该方法可建立较好的定量分析模型,能广泛应用于现场或野外苹果酸度的快速分析。     

Near-infrared spectroscopic determination of human serum albumin, γ-globulin, and glucose in a control serum solution with searching combination moving window partial least squares

Near-infrared (NIR) spectra in the region of 5000-4000 cm⁻¹ with a chemometric method called searching combination moving window partial least squares (SCMWPLS) were employed to determine the concentrations of human serum albumin (HSA), γ-globulin, and glucose contained in the control serum IIB (CS IIB) solutions with various concentrations. SCMWPLS is proposed to search for the optimized combinations of informative regions, which are spectral intervals, considered containing useful information for building partial least squares (PLS) models. The informative regions can easily be found by moving window partial least squares regression (MWPLSR) method. PLS calibration models using the regions obtained by SCMWPLS were developed for HSA, γ-globulin, and glucose. These models showed good prediction with the smallest root mean square error of predictions (RMSEP), the relatively small number of PLS factors, and the highest correlation coefficients among the results achieved by using whole region and MWPLSR methods. The RMSEP values of HSA, γ-globulin, and glucose yielded by SCMWPLS were 0.0303, 0.0327, and 0.0195 g/dl, respectively. These results prove that SCMWPLS can be successfully applied to determine simultaneously the concentrations of HSA, γ-globulin, and glucose in complicated biological fluids such as CS IIB solutions by using NIR spectroscopy.     

Simultaneous determination of human serum albumin, gamma-globulin, and glucose in a phosphate buffer solution by near-infrared spectroscopy with moving window partial least-squares regression

Near-infrared (NIR) spectra in the 12,000-4,000 cm(-1) region were measured for phosphate buffer solutions containing human serum albumin (HSA), gamma-globulin, and glucose with various concentrations at 37 degrees C. Five levels of full factorial design were used to prepare a sample set consisting of 125 samples of three component mixtures. The concentration ranges of HSA, gamma-globulin and glucose were 0.00-6.00 g dl(-1), 0.00-4.00 g dl(-1) and 0.00-2.00 g dl(-1), respectively. The 125 sample data were split into two sets, the calibration set with 95 data and the prediction set with 30 data. The most informative spectral ranges of 4648-4323, 4647-4255 and 4912-4304 cm(-1) were selected by moving window partial least-squares regression (MWPLSR) for HSA, [gamma]-globulin, and glucose in the mixtures, respectively. For HSA, the correlation coefficient (R) of 0.9998 and the root mean square error of prediction (RMSEP) of 0.0289 g dl(-1) were obtained. For [gamma]-globulin, R of 0.9997 and RMSEP of 0.0252 g dl(-1) were obtained. The corresponding statistic values of glucose were 0.9997 and 0.0156 g dl(-1), respectively. These statistical values obtained by MWPLSR are highly significant and better than those calculated by using the regions reported in the literature. The results presented here show that MWPLSR can select the informative regions with a simple procedure and increase the power of NIR spectroscopy for simultaneous determination of the concentrations of HSA, [gamma]-globulin and glucose in the mixture systems.     

Comparison of performance of partial least squares regression,secured principal component regression,and modified secured principal component regression for determination of human serum albumin, γ-globulin and glucose in buffer solutions and in vivo blood glucose quantification by near-infrared spectroscopy

The performances of three multivariate analysis methods—partial least squares (PLS) regression, secured principal component regression (sPCR) and modified secured principal component regression (msPCR)—are compared and tested for the determination of human serum albumin (HSA), γ-globulin, and glucose in phosphate buffer solutions and blood glucose quantification by near-infrared (NIR) spectroscopy. Results from the application of PLS, sPCR and msPCR are presented, showing that the three methods can determine the concentrations of HSA, γ-globulin and glucose in phosphate buffer solutions almost equally well provided that the prediction samples contain the same spectral information as the calibration samples. On the other hand, when some potential spectral features appear in new measurements, sPCR and msPCR outperform PLS significantly. The reason for this is that such spectral features are not included during calibration, which leads to a degradation in PLS prediction performance, while sPCR and msPCR can improve their predictions for the concentrations of the analytes by removing the uncalibrated features from the original spectra. This point is demonstrated by successfully applying sPCR and msPCR to in vivo blood glucose measurements. This work therefore shows that sPCR and msPCR may provide possible alternatives to PLS in cases where some uncalibrated spectral features are present in measurements used for concentration prediction.     

应用遗传算法和PLS的近红外光谱预测玉米中淀粉含量的研究

以普通玉米籽粒为试验材料,在应用遗传算法结合偏最小二乘回归法对近红外光谱数据进行特征波长选择的基础上,应用偏最小二乘回归法建立了特征波长测定玉米籽粒中淀粉含量的校正模型．试验结果表明,基于11个特征波长所建立的校正模型,其校正误差（RMSEC）、交叉检验误差（RMSECV）和预测误差（RMSEP）分别为0.30％、0.35％和0.27％,校正数据集和独立的检验数据集的预测值与实际测定值之间的相关系数分别达到0.9279和0.9390,与全光谱数据所建立的预测模型相比,在预测精度上均有所改善,表明应用遗传算法和PLS进行光谱特征选择,能获得更简单和更好的模型,为玉米籽粒中淀粉含量的近红外测定和红外光谱数据的处理提供了新的方法与途径．     

The use of FT-NIR for API content assay in organic solvent media: a single calibration for multiple downstream processing streams

The use of near infrared spectroscopy (NIRS) in downstream solvent based processing steps of an active pharmaceutical ingredient (API) is reported. A single quantitative method was developed for API content assessment in the organic phase of a liquid–liquid extraction process and in multiple process streams of subsequent concentration and depuration steps. A new methodology based in spectra combinations and variable selection by genetic algorithm was used with an effective improvement in calibration model prediction ability. Root mean standard error of prediction (RMSEP) of 0.05 in the range of 0.20–3.00% (w/w) was achieved. With this method, it is possible to balance the calibration data set with spectra of desired concentrations, whenever acquisition of new spectra is no longer possible or improvements in model's accuracy for a specific selected range are necessary. The inclusion of artificial spectra prior to genetic algorithms use improved RMSEP by 10%. This method gave a relative RMSEP improvement of 46% compared with a standard PLS of full spectral length.     

Classification and determination of total protein in milk powder using near infrared reflectance spectrometry and the successive projections algorithm for variable selection

This paper proposes a methodology for the classification and determination of total protein in milk powder using near infrared reflectance spectrometry (NIRS) and variable selection. Two brands of milk powder were acquired from three Brazilian cities (Natal-RN, Salvador-BA and Rio de Janeiro-RJ). The protein content of 38 samples was determined by the Kjeldahl method and NIRS analysis. Principal component regression (PCR) and partial least squares (PLS) multivariate calibrations were used to predict the total protein. Soft independent modeling of class analogy (SIMCA) was also used for full-spectrum classification, resulting in almost 100% classification accuracy, regardless of the significance level adopted for the F-test. Using this strategy, it was feasible to classify powder milk rapidly and nondestructively without the need for various analytical determinations. Concerning the multivariate calibration models, the results show that PCR, PLS and MLR-SPA models are good for predicting total protein in powder milk; the respective root mean square errors of prediction (RMSEP) were 0.28 (PCR), 0.25 (PLS), 0.11 wt% (MLR-SPA) with an average sample protein content of 8.1 wt%. The results obtained in this investigation suggest that the proposed methodology is a promising alternative for the determination of total protein in milk powder.     

Determination of human serum albumin and γ-globulin in a control serum solution by near-infrared spectroscopy and partial least squares regression

Near infrared (NIR) spectra in the 1300– 1850 nm region were measured for control serum solutions containing both albumin and γ-globulin of various concentrations. Partial least squares two (PLS2) regression was applied to the NIR spectra to determine simultaneously the concentrations of both proteins. For albumin, the correlation coefficient (R) of 0.988, the standard error of calibration (SEC) of 1.61 g/L, the standard error of prediction (SEP) of 1.29 g/L, the relative standard deviation (RSD) of 0.026 and the ratio of standard deviation of reference data in prediction to SEP (RPD) of 12.2 were obtained. For γ-globulin, the corresponding values were 0.997, 1.36 g/L, 1.35 g/L, 0.0365 and 8.66, respectively. The regression coefficients (RCs) of PLS factors were compared between albumin and γ-globulin, and the observed differences in the RCs were discussed based upon the differences in the hydration between albumin and γ-globulin. In order to explore the effects of various metabolites such as glucose, and cholesterol on the chemometrics models, the RCs for albumin and γ-globulin in the control serum solutions were also compared with those for albumin and γ-globulin in phosphate buffer solutions previously studied. The results of our experiments show that NIR spectroscopy with the use of PLS2 regression has considerable promise in nondestructive determination of the concentrations of blood serum proteins.     

Near-infrared spectroscopy quantitative determination of Pefloxacin mesylate concentration in pharmaceuticals by using partial least squares and principal component regression multivariate calibration

Pefloxacin mesylate, a broad-spectrum antibacterial fluoroquinolone, has been widely used in clinical practice. Therefore, it is very important to detect the concentration of Pefloxacin mesylate. In this research, the near-infrared spectroscopy (NIRS) has been applied to quantitatively analyze on 108 injection samples, which was divided into a calibration set containing 89 samples and a prediction set containing 19 samples randomly. In order to get a satisfying result, partial least square (PLS) regression and principal components regression (PCR) have been utilized to establish quantitative models. Also, the process of establishing the models, parameters of the models, and prediction results were discussed in detail. In the PLS regression, the values of the coefficient of determination (R²) and root mean square error of cross-validation (RMSECV) of PLS regression are 0.9263 and 0.00119, respectively. For comparison, though applying PCR method to get the values of R² and RMSECV we obtained are 0.9685 and 0.00108, respectively. And the values of the standard error of prediction set (SEP) of PLS and PCR models are 0.001480 and 0.001140. The result of the prediction set suggests that these two quantitative analysis models have excellent generalization ability and prediction precision. However, for this PFLX injection samples, the PCR quantitative analysis model achieved more accurate results than the PLS model. The experimental results showed that NIRS together with PCR method provide rapid and accurate quantitative analysis of PFLX injection samples. Moreover, this study supplied technical support for the further analysis of other injection samples in pharmaceuticals.     

Improving Prediction of Peroxide Value of Edible Oils Using Regularized Regression Models

We present four unique prediction techniques, combined with multiple data pre-processing methods, utilizing a wide range of both oil types and oil peroxide values (PV) as well as incorporating natural aging for peroxide creation. Samples were PV assayed using a standard starch titration method, AOCS Method Cd 8-53, and used as a verified reference method for PV determination. Near-infrared (NIR) spectra were collected from each sample in two unique optical pathlengths (OPLs), 2 and 24 mm, then fused into a third distinct set. All three sets were used in partial least squares (PLS) regression, ridge regression, LASSO regression, and elastic net regression model calculation. While no individual regression model was established as the best, global models for each regression type and pre-processing method show good agreement between all regression types when performed in their optimal scenarios. Furthermore, small spectral window size boxcar averaging shows prediction accuracy improvements for edible oil PVs. Best-performing models for each regression type are: PLS regression, 25 point boxcar window fused OPL spectral information RMSEP = 2.50; ridge regression, 5 point boxcar window, 24 mm OPL, RMSEP = 2.20; LASSO raw spectral information, 24 mm OPL, RMSEP = 1.80; and elastic net, 10 point boxcar window, 24 mm OPL, RMSEP = 1.91. The results show promising advancements in the development of a full global model for PV determination of edible oils.     

Feasibility study on qualitative and quantitative analysis in tea by near infrared spectroscopy with multivariate calibration

This study attempted the feasibility to use near infrared (NIR) spectroscopy as a rapid analysis method to qualitative and quantitative assessment of the tea quality. NIR spectroscopy with soft independent modeling of class analogy (SIMCA) method was proposed to identify rapidly tea varieties in this paper. In the experiment, four tea varieties from Longjing, Biluochun, Qihong and Tieguanyin were studied. The better results were achieved following as: the identification rate equals to 90% only for Longjing in training set; 80% only for Biluochun in test set; while, the remaining equal to 100%. A partial least squares (PLS) algorithm is used to predict the content of caffeine and total polyphenols in tea. The models are calibrated by cross-validation and the best number of PLS factors was achieved according to the lowest root mean square error of cross-validation (RMSECV). The correlation coefficients and the root mean square error of prediction (RMSEP) in the test set were used as the evaluation parameters for the models as follows: R = 0.9688, RMSEP = 0.0836% for the caffeine; R = 0.9299, RMSEP = 1.1138% for total polyphenols. The overall results demonstrate that NIR spectroscopy with multivariate calibration could be successfully applied as a rapid method not only to identify the tea varieties but also to determine simultaneously some chemical compositions contents in tea.