应用Hilbert变换提取拉曼光谱相位信息进行血液识别分类方法的研究

将拉曼光谱技术和化学计量学方法相结合实现了对人血和动物血种属的区分,并提出了一种基于Hilbert变换的拉曼光谱相位提取方法,提高了人血与动物血区分的准确度。分别对血液光谱数据和它所对应的相位信息进行主成分分析(PCA),通过主成分得分图比较两者对人与动物血液的区分程度,并建立偏最小二乘判别分析(PLS-DA)模型,通过设置合适的分类阈值y,可以实现人与动物血液的有效区分。结果表明在选取第一、第二主成分分析时,利用光谱数据相位信息建立的PCA模型,识别率更高,人与动物血液明显区分开来。其所对应的PLS-DA模型最优主成分数为3,预测标准误差(RMSEP)和决定系数(R2)分别为0.044 3和0.993 2。而用血液原始光谱建立的PLS-DA模型最优主成分数为6,RMSEP和R2分别为0.053 7和0.990 1。说明利用拉曼光谱相位信息建立的PLS-DA模型可以拟合较少的主成分数来获得误差更小的预测结果。进一步观察PLS-DA模型拟合不同主成分数的预测标准误差曲线图,当选取同样多的拟合主成分数时,利用血液拉曼光谱相位信息建立的PLS-DA模型其所对应的预测标准误差均低于原始血液光谱数据。所以,通过提取血液拉曼光谱数据的相位信息,可以降低模型的复杂程度,提高识别准确度。     

基于空间可分辨光谱的番茄成熟度判别方法研究

对基于空间可分辨光谱的番茄成熟度分类判别方法进行了试验研究。首先根据番茄的内部颜色,将600个番茄分为6个不同成熟度 (green, breaker, turning, pink, light red and red) ,然后用自行开发的多通道高光谱成像探头采集番茄的空间可分辨(SR)光谱,建立基于空间可分辨光谱的番茄成熟度偏最小二乘判别(PLSDA) 模型和支持向量机判别(SVMDA)模型。结果显示,对于PLSDA模型,SR光谱15为最佳分类光谱,分类正确率达到81.3%;对于SVMDA模型,SR光谱10为最佳预测分类光谱,分类正确率为86.3%。对六个成熟度等级番茄的判别分类,SVMDA模型要明显优于PLSDA模型。此外,相对于较小的光源-检测器距离SR光谱,较大的光源-检测器距离SR光谱可以获得更好的判别效果,显示出空间可分辨光谱在果蔬品质检测方面的应用潜力。     

基于高光谱成像技术的鲜枣裂纹的识别研究

裂纹是衡量鲜枣品质的重要指标之一,果皮裂纹加速鲜枣的腐烂,导致鲜枣货架期的缩短,严重降低鲜枣的经济价值。采用高光谱成像技术在380～1 030 nm波段范围内对鲜枣裂纹的位置及大小信息特征进行快速识别。选用偏最小二乘回归(PLSR)、连续投影法(SPA)和全波段图像主成分分析(PCA),得到鲜枣裂纹相关的敏感波段。然后利用选取的鲜枣裂纹的敏感波段对建模集的132个样本建立最小二乘支持向量机(LS-SVM)判别模型,并对预测集的44个样本进行判别。对PLSR-LS-SVM,SPA-LS-SVM和PCA-LS-SVM判别模型采用ROC曲线进行评判,得出PLSR-LS-SVM模型对鲜枣裂纹定性判别的结果(area=1,std=0)最佳。选取PLSR回归系数挑选出的5条鲜枣裂纹敏感波段(467,544,639,673和682 nm)对应的单波段图像进行主成分分析,其中将主成分PC4的图像结合图像处理技术,最终识别出鲜枣裂纹的位置、大小信息。结果表明,采用高光谱成像技术结合光谱图像处理可以实现鲜枣裂纹定性判别和定量识别的研究,为进一步开发相关仪器的研究提供理论方法和依据。     

绿豆种子萌发进程的显微拉曼成像研究

种子萌发不同阶段内化合物的变化一直是代谢组学的研究热点。本实验基于拉曼高光谱成像研究了绿豆种子萌发过程中子叶、胚芽和胚根的变化,对绿豆萌发不同阶段的三种器官切片进行拉曼成像测试,采用多元曲线分辨交替最小二乘(MCR-ALS),得了每个主成分对应的相对浓度及其纯光谱。在对成像数据的处理中,提出主成分选择重构这一可以去除噪声的方法。结果表明,对萌发不同阶段的的绿豆子叶拉曼成像进行MCR-ALS得到的主成分可解释原光谱的比例均超过0.99,揭示了显微拉曼成像技术作为一种活体无损的检测方式对于绿豆萌发进程中代谢物研究的可行性。     

正常、缺素和黄龙病柑桔叶片高光谱成像快速诊断

应用高光谱成像技术,结合峰值比判别法和偏最小二乘判别法,探讨快速无损诊断正常、缺素和黄龙病柑桔叶片的可行性。在374.28~1 016.89nm可见近红外光谱范围内,采集了正常、缺素和黄龙病柑桔叶片的高光谱数据。以主叶脉为轴线,两侧各选一个长约60像素、宽约30像素的椭圆形感兴趣区域。提取两个感兴趣区域的平均反射率光谱,经相关分析,筛选出502.79和374.28nm一对特征波长,建立了正常叶片的峰值比判别模型,模型误判率为1.7%,但该模型无法区分缺素和黄龙病叶片。采用二阶导数结合平滑光谱预处理方法,处理反射率光谱,建立了缺素和黄龙病叶片偏最小二乘判别模型。采用留一法交互验证确定最佳主成分因子数为17,建模相关系数为0.96,建模标准差为0.13,模型对两类叶片分类正确率都达到了100%。在此基础上,提出了峰值比判别模型和偏最小二乘判别模型相结合的不同类别叶片二步快速诊断法。采用未参与建模的正常、缺素和黄龙病叶片各10片,评价模型的分类能力,模型分类正确率达到了96.7%。实验结果表明:应用高光谱成像技术,结合由峰值比判别模型和偏最小二乘判别模型构成的二步判别法,快速识别正常、缺素和黄龙病柑桔叶片是可行的。     

形状平滑约束在多元曲线分辨交替最小二乘(MCR-ALS)解析高光谱成像中的应用

高光谱成像在多学科研究中提供了丰富的数据信息,由于数据量庞大,研究人员使用化学计量学方法对这些数据的信息进行提取。多元曲线分辨交替最小二乘(MCR-ALS)方法能够分辨混合体系的高光谱数据中的纯组分对应的光谱和浓度信息,得到了广泛的使用。为了进一步提高MCR-ALS对高光谱的解析能力,本文使用了形状平滑约束(SSC)分别分析了模拟数据和实验数据,结果表明,通过形状平滑约束,能够进一步提高MCR-ALS对高光谱数据解析的准确度,而且使MCR减少了扭曲模糊,在二线性分辨中获得了唯一解。     

基于高光谱成像技术应用光谱及纹理特征识别柑橘黄龙病

讨论了基于高光谱成像技术光谱及纹理特征在识别早期柑橘黄龙病中的应用。使用一套近地高光谱成像系统采集了176枚柑橘叶片的高光谱图像作为实验样品,其中健康叶片60枚,黄龙病叶片60枚,缺锌叶片56枚。手工选取每幅叶片高光谱图像的病斑位置作为样品感兴趣区域(regions of interest, ROI),计算其平均光谱反射率,并以此作为样品的反射光谱,光谱范围为396～1 010 nm。样品光谱分别经过主成分分析(PCA)及连续投影算法(SPA)进行数据降维,再结合最小二乘支持向量机(LS-SVM)分类器建立分类模型。相比原始光谱,由PCA选取的前四个主成分及SPA选取的一组最佳波长组合(630.4,679.4,749.4和899.9 nm)建立的模型拥有更好的分类识别能力,其对三类柑橘叶片平均预测准确率分别为89.7%和87.4%。同时,从被选四个波长的每幅灰度图像中提取6个灰度直方图的纹理特征以及9个灰度共生矩阵的纹理特征再次构建分类模型。经SPA优选的10个纹理特征值进一步提高了分类效果,对三类柑橘叶片的识别正确率达到了100%,93.3%和92.9%。实验结果表明,同时包含光谱信息及空间纹理信息的高光谱图像在柑橘黄龙病的识别中显示了很大的潜力。     

基于高光谱成像技术应用光谱及纹理特征识别柑橘黄龙病（英文）

讨论了基于高光谱成像技术光谱及纹理特征在识别早期柑橘黄龙病中的应用。使用一套近地高光谱成像系统采集了176枚柑橘叶片的高光谱图像作为实验样品,其中健康叶片60枚,黄龙病叶片60枚,缺锌叶片56枚。手工选取每幅叶片高光谱图像的病斑位置作为样品感兴趣区域(regions of interest,ROI),计算其平均光谱反射率,并以此作为样品的反射光谱,光谱范围为396~1 010nm。样品光谱分别经过主成分分析(PXA)及连续投影算法(SPA)进行数据降维,再结合最小二乘支持向量机(LS-SVM)分类器建立分类模型。相比原始光谱,由PCA选取的前四个主成分及SPA选取的一组最佳波长组合(630.4,679.4,749.4和899.9 nm)建立的模型拥有更好的分类识别能力,其对三类柑橘叶片平均预测准确率分别为89.7%和87.4%。同时,从被选四个波长的每幅灰度图像中提取6个灰度直方图的纹理特征以及9个灰度共生矩阵的纹理特征再次构建分类模型。经SPA优选的10个纹理特征值进一步提高了分类效果,对三类柑橘叶片的识别正确率达到了100%,93.3%和92.9%。实验结果表明,同时包含光谱信息及空间纹理信息的高光谱图像在柑橘黄龙病的识别中显示了很大的潜力。     

MCR-BANDS用于高光谱成像分辨中旋转模糊度的评估

自建模曲线分辨用来将双线性光谱数据矩阵分解成具有明确物理或化学意义的曲线,一方面反映了复杂体系中各个主成分对应的纯光谱,同时也能够解析得到其对应的相对浓度。这一方法在高光谱解析中充分发挥了其优势,成为了高光谱分析中的重要方法之一。然而,双线性结构数据多元分辨模型在约束不充分的条件下往往不能获得唯一解,这一问题是由顺序模糊、尺度模糊和旋转模糊引起,其中旋转模糊最难消除。在高光谱成像中,如果不能明确浓度分布情况,将导致在成像领域难以确认目标的准确位置或形貌。为了充分了解旋转模糊带来的影响,评估非唯一解情况下可行解的范围,并进一步为实际应用中需要解析获得的每个主成分的纯光谱或波谱信号,以及其对应的浓度信息提供客观的评估依据,在以往的研究中,研究人员分别使用网格法、蒙特卡洛法进行抽样,以计算曲线分辨结果中可行解的范围,也有科研人员使用了几何多边形内部和外围面积的形式表示结果,但是这些结果往往面临运算时间过长,或者无法实现高维可视化而不适用于大于四个主成分的数据等问题,而且通常这些方法很难将曲线分辨过程中施加的除非负约束之外的其他约束方法加以利用,导致可行解范围计算不准确。为了解决以上问题,采用MCR-BANDS对MCR-ALS（多元曲线分辨-交替最小二乘）分辨获得的结果进行了旋转模糊程度的评估,并将其应用到遥感高光谱成像的解析中。首先以美国地质勘探局矿物光谱库中的纯光谱为基础的模拟数据集对MCR-ALS和MCR-BANDS的结果进行了评测,在模拟数据中能够方便地控制噪声的影响,控制选取主成分之间的纯光谱差异、仿照真实环境中浓度渐变特征等因素,考查了特定条件下MCR结果中旋转模糊的水平。随后为了证实所用方法的可行性,进一步采用MCR-ALS分析了机载可见/红外成像光谱仪（AVIRIS）获得的遥感高光谱图像数据,并首次采用MCR-BANDS对MCR-ALS的分辨结果的旋转模糊进行了分析,实现了对遥感高光谱数据成像浓度分布的受到旋转模糊影响的可视化表示。可以发现真实解和MCR-ALS获得的可行解均在MCR-BANDS计算得到的可行解范围之内。结果表明,MCR-BANDS方法基于最大和最小的信号贡献对旋转模糊的范围进行计算,能够适用于不同主成分的体系中,并且完美对接MCR-ALS中使用到的诸如非负、单峰、封闭和选择性约束等。MCR-BANDS的分析结果可以为MCR-ALS的解析结果提供相应的旋转模糊水平估计,有利于对MCR-ALS结果的解释;在充分约束条件下,能够有效减少甚至消除旋转模糊对MCR-ALS分辨结果的影响,为精确确定遥感高光谱中解析得到的目标物位置提供了客观的范围。     

应用近红外高光谱成像技术预测甘蔗可溶性固形物含量

为了探究应用近红外高光谱成像技术对甘蔗内部可溶性固形物（SSC）预测的可行性,试验样本选择三种不同品种中的240个甘蔗节作为研究对象。通过高光谱成像系统获取甘蔗节的近红外光谱信息和图像信息,并分别探讨了光谱信息和图像纹理信息对甘蔗可溶性固形物预测的可行性。采用最小二乘回归（PLSR）,最小二乘支持向量机（LS-SVM）及主成分回归（PCR）建模方法构建甘蔗可溶性固形物的预测模型。比较了连续投影算法（SPA）、无信息变量消除算法（UVE）及区间偏最小二乘（iPLS）特征提取方法对预测结果的影响。实验结果表明：基于甘蔗的光谱信息能实现可溶性固形物的预测,其中偏最小二乘回归模型的建模集和预测集的相关系数分别为0.879和0.843,均方根误差分别为0.644和0.742。通过UVE算法提取105个有效波长所建立的PLSR模型的建模集及预测集相关系数分别为0.860和0.813,均方根误差分别为0.693和0.810。     

Comparison of chemometric methods in the analysis of pharmaceuticals with hyperspectral Raman imaging

Chemical imaging method of vibrational spectroscopy, which provides both spectral and spatial information, creates a three‐dimensional (3D) dataset with a huge amount of data. When the components of the sample are unknown or their reference spectra are not available, the classical least squares (CLS) method cannot be applied to create visualized distribution maps. Raman image datasets can be evaluated even in such cases using multivariate (chemometric) methods for extracting the needed hidden information. The capability of chemometrics‐assisted Raman mapping is evaluated through the analysis of pharmaceutical tablets (considered as unknown) with the aim of estimating the pure component spectra based on the collected Raman image. Six chemometric methods, namely, principal component analysis (PCA), maximum autocorrelation factors (MAF), sample–sample 2D correlation spectroscopy (SS2D), self‐modeling mixture analysis (SMMA), multivariate curve resolution–alternating least squares (MCR‐ALS), and positive matrix factorization (PMF), were compared. SMMA was found to be the best choice to determine the number of components. MCR‐ALS and PMF provided the pure component spectra with the highest quality. MCR‐ALS was found to be superior to PMF in the estimation of Raman scores (which correspond to the concentrations) and yielded almost the same results as CLS (using the real reference spectra). Thus, the combination of Raman mapping and chemometrics could be successfully used to characterize unknown pharmaceuticals, identify their ingredients, and obtain information about their structures. This may be useful in the struggles against illegal and counterfeit products and also in the field of pharmaceutical industry when contaminants are to be identified. Copyright © 2011 John Wiley & Sons, Ltd.     

近红外光谱指纹分析在羊肉产地溯源中的应用

为寻求低廉、快速有效地签别羊肉产地来源的方法,对来自内蒙古自治区锡林郭勒盟、呼伦贝尔市和阿拉善盟三个牧区,及重庆市和山东省菏泽市两个农区共99份羊肉样品进行近红外光谱扣描,利用主成分分析结合线性判别分析(PCA+LDA),以及偏最小二乘判别分析法(PLS-DA)对光谱数据进行了分析,建立了羊肉产地来源的定性判别模型.结...     

Comparison of multivariate linear regression methods in micro‐Raman spectrometric quantitative characterization

Chemical imaging was used in this study as a powerful analytical tool to characterize pharmaceuticals in solid form. The majority of analyses are evaluated with bilinear modelling using only the pure component spectra or just the chemical images themselves to estimate the concentrations in each pixel, which are far from true quantitative determination. Our aim was to create more accurate concentration images using regression methods. For the first time in chemical imaging, variable selections with interval partial least squares (PLS) and with genetic algorithms (PLS‐GA) were applied to increase the efficiency of the models. These were compared to numerous bilinear modelling and multivariate linear regression methods such as univariate regression, classical least squares (CLS), multivariate curve resolution–alternating least squares (MCR‐ALS), principal component regression (PCR) and partial least squares (PLS). Two component spray‐dried pharmaceuticals were used as a model. The paper is shown that, in contrast to the usual way of using either external validation or cross‐validation, both should be performed simultaneously in order to get a clear picture of the prediction errors and to be able to select the appropriate models. Using PLS with variable selection, the root mean square errors were reduced to 3% per pixel by keeping only those peaks that are truly necessary for the estimation of concentrations. It is also shown that interval PLS can point out the best peak for univariate regression, and can thereby be of great help even when regulations allow only univariate models for product quality testing. Variable selection, besides yielding more accurate overall concentrations across a Raman map, also reduces the deviation among pixel concentrations within the images, thereby increasing the sensitivity of homogeneity studies. Copyright © 2015 John Wiley & Sons, Ltd.     

Determination of mechanical properties of historical paper based on NIR spectroscopy and chemometrics – a new instrument

Due to sampling restrictions in the analysis of cultural heritage materials, non-destructive approaches are intensively sought for. While NIR spectrometry has rarely been used for this purpose due to the complexity of the spectra, chemometric methods can be used to extract the necessary information. For the purpose of determination of mechanical properties of historical paper, partial least squares approach was used and it is shown that tensile strength, and tensile strength after folding, can be estimated based on NIR spectra. As the mechanical properties of paper-based objects define their accessibility, a new dispersive portable instrument was built, which will enable us to rapidly survey the condition of library and archival collections. PACS  82.80.Gk; 28.52.Fa; 28.52.Lf     

Determination of the Al content in aluminum‐modified SiO2 stationary phases using X‐ray scattering spectroscopy

This paper describes the determination of aluminum in the presence of silica using a method based on X‐ray scattering spectrometry coupled with chemometric tools (principal component analysis and partial least squares) that treat samples according to their Al concentrations. Samples were prepared by mixing Al and Si oxides. X‐ray spectra of all samples, including pure oxides of aluminum and silicon, were submitted to the chemometric tools. Principal component analysis results show that it is possible to classify three subgroups of Al (low, medium and high Al content), whereas partial least squares 1 was used to construct calibration and cross‐validation models for Al in the presence of Si. The method is simple, fast, does not require sample dissolution prior to analysis, is of low cost and can be applied as a routine procedure. The method was used to quantify Al in some chromatographic stationary phases covered with a layer of Al₂O₃. Good correlations with low errors were obtained. Copyright © 2013 John Wiley & Sons, Ltd.     

Analysis of colonic autofluorescence spectra using multivariate curve resolution alternating least squares

Autofluorescence （AF） spectra of colonic normal and adenocarcinoma tissues are measured under excitation of 337 nm and analyzed by multivariate curve resolution alternating least squares （MCR-ALS） method using non-negativity constraint. Collagen, nicotinamide adenine dinucleotide hydrate （NADH） and elastin are identified as the main contributing biomedical components. Fisher＇s discrminant anlysis （FDA） on the concentration profiles of the principle components （PCs） shows acceptable sensitivity, specificty and accuracy for discrminanting the adenocarcinoma tissues from the normal tissues. MCR-ALS is a powerful tool for characterzing the spectra profiles of the main biochemical components in neoplasm transformation.     

基于三维荧光光谱技术对掺假蜂蜜无损鉴别研究

提出了一种应用三维荧光谱技术结合化学计量学方法快速无损鉴别蜂蜜中大米糖浆掺假的新方法。利用特征参量法和主成分分析法对三维荧光光谱信息量进行压缩提取,并结合线性判别分析法(LDA)和误差反向传播神经网络法(BP-ANN)对蜂蜜掺假进行分析。结果显示,在掺假蜂蜜判别试验中,采用4个主成分时,模型对预测集样本的识别率最佳,LDA模型识别率为94.44%,BP-ANN模型识别率为100%,说明非线性的BP-ANN模型更适合蜂蜜掺假识别。研究表明,三维荧光光谱结合BP-ANN判别模型可以快速、 无损、 准确地鉴别蜂蜜中大米糖浆掺假。     

Multivariate data analysis for Raman spectroscopic imaging

This article reviews the analytic techniques for Raman spectroscopic imaging with emphasis on chemometrics. Key information included in Raman spectra is often distributed broadly throughout the dataset. It is possible to condense the information into a very compact matrix representation by a chemometric technique of factor analysis such as principal component analysis (PCA) or self‐modeling curve resolution (SMCR). PCA yields two matrices called scores and loadings which complementarily represent the entire features broadly distributed in the dataset. This concept can be further extended to other forms of data transformation schemes, including bilinear data decomposition based on SMCR analysis. SMCR offers a firmer model which is chemically or physically interpretable. The information derived from these techniques readily brings useful insight into building a mechanistic model for understanding complex phenomena studied by Raman spectroscopy. Illustrative examples are given for applications of both PCA and SMCR to Raman imaging of pharmaceutical tablets. Copyright © 2009 John Wiley & Sons, Ltd.