二阶导数红外光谱快速鉴别轮胎橡胶颗粒

针对传统取样分析技术会破坏物证和综合考察样本作为混合物在多维度上的差异性,提出一种基于二阶导数红外光谱结合模式识别对轮胎橡胶颗粒快速准确鉴别的方法。采集并分析不同品牌共计96个轮胎橡胶颗粒的红外谱图及其二阶导数谱图,同时预处理采用自动基线校正、峰面积归一化和Savitzky-Golay平滑,建立判别分析模型,从而实现其品牌间的准确区分和认定。红外二阶导数谱图呈现出许多原始谱图中被掩盖谱峰的斜率变化特征,将样本谱图间的差异更为明显的表示了出来,结合原始谱图和其二阶导数谱图,得出实验样本主要由丁苯橡胶、顺丁橡胶和异戊橡胶3种类型。原始谱图判别预测模型分类准确率为95.83%,二阶导数判别预测模型分类正确率为100%,其区分能力更强,二阶导数结合判别分析可有效开展对轮胎橡胶颗粒的区分鉴别,其构建的模型分类效果更好。以品牌为单位,进一步对丁苯橡胶等3种类型的样本展开模式识别工作,得出其判别预测模型均实现了样本品牌间100%的区分和归类,实验结果理想。利用二阶导数红外光谱结合模式识别可实现对轮胎橡胶样本的准确识别与分类,方法具有一定的普适性和借鉴意义,可为其他物证的鉴别与分析提供一定的参考。     

紫外/可见光谱技术无损检测苹果的挤压损伤

目的 通过紫外/可见光谱技术结合模式识别算法,建立挤压损伤苹果的Fisher识别模型、K最近邻（KNN）识别模型和偏最小二乘判别分析（PLS-DA）识别模型。方法 以挤压损伤苹果和无损苹果为研究对象,采用光谱仪采集2种苹果的光谱反射率,综合比较不同光谱预处理方法（二阶微分（SD）、标准正态变换（SNV）和多元散射校正（MSC））对各模型识别效果的影响,并利用主成分分析方法（PCA）对预处理后的光谱数据进行降维,并提取能反映损伤苹果的特征光谱。结果 采用主成分分析法选择了累计贡献率超过99%的前7个主成分（P1—P7）作为特征光谱数据,有效地实现了光谱数据的降维;二阶微分对光谱反射率预处理的效果最好;3种判别模型均能满足实际要求,且SD+Fisher和SD+PLS-DA识别模型对校正集和预测集样本的总正确识别率均高达100%。结论 研究结果有助于实现挤压损伤苹果的快速识别。     

基于判别分析与ANN的药品铝塑包装泡罩XRF分析

目的针对案件现场常见的药品铝塑包装泡罩,为达到对其分类识别的目的,提出系列检验分析、数据处理方法。方法采用X射线荧光光谱法对45个药品铝塑包装泡罩样本所含元素进行检验并讨论分析。对检验结果进行无监督的系统聚类,利用离差平方和法计算欧氏距离进而将未知样本分为5类。结果将分类结果作为变量进行判别分析,选取累积方差百分比为97.8%的2个判别函数,其类内平方和与总平方和之比为0.015和0.394,具有较强的解释能力。绘制的样本判别分类图将5类样本类之间相互区分开来,样本总体判别正确率为95.6%。提取样本在判别函数上的判别得分构建了人工神经网络,最终分类正确率为97.8%。结论利用X射线荧光光谱法对药品铝塑包装泡罩进行检验,将元素种类及含量作为变量进行了分类,并构建了45个药品铝塑包装泡罩样本的人工神经网络分类模型,可借助该模型进一步实现对于案件现场未知类别的药品铝塑包装泡罩样本的分类识别。     

灯盏花素注射液指纹图谱的建立及质量相关性研究

目的：应用高效液相色谱法建立灯盏花素注射液指纹图谱。方法：Hanbon C18（5μm,250nm×4.6nm）,柱温25℃,检测波长335nm,流速为1ml.min-1,流动相：甲醇（A）-0.4%磷酸缓冲液（B）梯度洗脱。结果：确定了不同批次灯盏花素指纹图谱的特征指纹图谱及相似度。结论：本方法稳定可靠,重复性好,可...     

基于P&T-GC/MS指纹图谱评价丝束加香滤棒质量的稳定性

目的 形成丝束加香滤棒质量稳定性的评价体系。方法 实验采用吹扫捕集-气相色谱-质谱技术（Purge&Trap-Gas Chromatography-Mass Spectrometry,P&T-GC-MS）结合“中药色谱指纹图谱相似度评价系统”对丝束加香滤棒中特征香味成分进行分析,以建立P&T-GC-MS指纹图谱,并利用欧氏距离法计算其相似度,以及聚类分析法评价不同批次间样品的差异性。结果 相同浓度、不同批次丝束加香滤棒的相似度均高于0.920,表明批次间、批次内样品的质量稳定性较好;各特征香味成分峰面积、保留时间的RSD值均小于1.70%,表明该方法具有良好的精密度、稳定性和重现性;所建的丝束加香滤棒标准指纹图谱与聚类分析结果一致,可将不同浓度的丝束加香滤棒进行有效甄别。结论 该方法可为评价丝束加香滤棒的质量稳定性提供参考依据。     

基于高光谱成像技术的药用胶囊铬含量快速检测方法研究

研究了基于高光谱成像技术快速检测药用胶囊铬含量的方法。首先应用传统的原子吸收分光法对药用明胶空心硬胶囊分析结果作为对照组,再对1048个胶囊（含正常和含有重金属铬）样本的高光谱数据进行降维和定性分析,最后选择偏最小二乘判别分析方法对光谱数据进行处理。当用4个偏最小二乘算子（LV）作为偏最小二乘法模型中的输入特征,分类准确率可达100%,2种样本的交叉验证和样本预测相关系数分别为0.923和0.972;敏感度与特异度均为100%。     

基于差分拉曼光谱对烟盒物证检验

目的 为了探究一种基于光谱分析的检验方法,以达到快速准确地区分检验烟盒物证的目的.方法 采用便携式差分拉曼光谱仪,对39个不同的黄色烟盒样本进行测试,取得各样本的差分拉曼光谱数据.根据烟盒填料种类对样本进行初步分类,再结合化学计量学,通过IBM SPSS Statistics 26.0软件,在主成分分析法对数据进行降维的基础上,对测量结果进行系统聚类和K-Means聚类.结果 39种样本依据填料种类可以区分为3类,结合化学计量学可以更准确地区分为6类.结论 该方法无损检材、快捷准确,且图谱不受荧光干扰,结合化学计量学方法可以对烟盒样本进行分类检验,此方法为公安机关在犯罪现场检验此类物证提供了依据.     

基于线性判别分析的决策融合脑电意识动态分类

脑电信号的识别与分类是脑机接口技术的热点研究问题,单一分类器不能很好利用特征以及分类器的适应性,导致识别的准确率很难进一步提高,基于线性判别分析的分类决策级融合策略,可用于提高脑-机接口系统的分类准确率。首先,通过分离出两种分类器的假性试验特征,从这两种方法中选择更有可能正确决策提高分类准确性;其次为了测量每个决策的不确定性,使用与所对应分类器的最大和第二大相关系数提取特征向量。基于这一思想,提出了一种新的决策选择器,该方法通过整合两种基于线性判别分析的算法选择更有可能是准确的决策,从而达到提高脑电信号分类准确度。实验结果表明,该方法通过与精度相近的算法相结合在运动想象数据分类上获得了较好的分类准确率。     

基于多元分类模型的颜料红外光谱鉴别

颜料的检验与认定是司法鉴定中一项重要的工作。在传统的分析中,侦查人员往往通过人工逐一比对和分析,其耗时长,误差大,无法满足无损、快速、准确检验现场颜料样本的需求。该文提出一种检验方法,以期实现对物证无损、快速、准确的检验与鉴定。通过采集并分析不同品牌共计48个颜料样本的红外谱图,采用多元散射校正、Savitzky-Golay平滑和峰面积归一化开展预处理工作,建立基于K近邻算法等4种分类模型,从而实现不同颜料间的区分和归类。在区分水粉类颜料和毕加索丙烯画颜料时,相较于K近邻和Fisher判别模型,多层感知器分类模型准确率更高(总体分类准确率为100%),分类结果更好。在经过主成分分析提取特征变量后,分类模型对两类颜料的区分准确率均为100%。应用MLP结合PCA构建的分类模型对颜料样本的区分效果最佳。针对水粉类中的两类即普通水粉类和毕加索水粉类颜料样本,多层感知器分类模型对其的分类准确率为97.2%,针对普通水粉类样本的两个品牌(贝碧欧和晨光),多层感知器分类模型的分类准确率为100%,实验结果理想。利用中红外光谱结合多元分类模型可实现对颜料样本准确的鉴别与区分,其快速无损准确,降低检验鉴定成本,提高检验鉴定效率,可为其他物证的鉴别与分析提供一定的参考。     

差分拉曼光谱结合化学计量学对白色购物纸袋的检验研究

目的 建立差分拉曼光谱用于无损识别白色购物纸袋的方法。方法 对收集到的60种不同品牌、不同规格的白色购物纸袋进行拉曼光谱测定,对样品的拉曼光谱图进行预处理,根据光谱图对样品进行初步分类,并结合化学计量方法对样品进行分组。应用Fisher判别分析方法对分类结果进行验证。最后应用RBF模型对未知样本进行分类判别。结果 结合样品中所含的碳酸钙、滑石粉、硫酸钡的不同,可初步将白色购物纸袋样品分为五大类,采用K-均值聚类方法继续细分,通过Fisher判别方法对样品分结果进行验证,判别准确率为100%。应用神经网络RBF模型对未知样本进行判别分析,准确率达到89.48%。结论 该方法简便易行,为白色购物纸袋的分类提供了科学的依据,也为公安基层工作的开展提供了便捷的办法。     

Identification and quantification of industrial grade glycerol adulteration in red wine with fourier transform infrared spectroscopy using chemometrics and artificial neural networks

Fourier transform infrared (FT-IR) single bounce micro-attenuated total reflectance (mATR) spectroscopy, combined with multivariate and artificial neural network (ANN) data analysis, was used to determine the adulteration of industrial grade glycerol in selected red wines. Red wine samples were artificially adulterated with industrial grade glycerol over the concentration range from 0.1 to 15% and calibration models were developed and validated. Single bounce infrared spectra of glycerol adulterated wine samples were recorded in the fingerprint mid-infrared region, 900-1500 cm(-1). Partial least squares (PLS) and PLS first derivatives were used for quantitative analysis (r2 = 0.945 to 0.998), while linear discriminant analysis (LDA) and canonical variate analysis (CVA) were used for classification and discrimination. The standard error of prediction (SEP) in the validation set was between 1.44 and 2.25%. Classification of glycerol adulterants in the different brands of red wine using CVA resulted in a classification accuracy in the range between 94 and 98%. Artificial neural network analysis based on the quick back propagation network (BPN) and the radial basis function network (RBFN) algorithms had classification success rates of 93% using BPN and 100% using RBFN. The genetic algorithm network was able to predict the concentrations of glycerol in wine up to an accuracy of r2 = 0.998.     

Chemometric study on the forensic discrimination of soil types using their infrared spectral characteristics

Soil has been utilized in criminal investigations for some time because of its prevalence and transferability. It is usually the physical characteristics that are studied; however, the research carried out here aims to make use of the chemical profile of soil samples. The research we are presenting in this work used sieved (2 mm) soil samples taken from the top soil layer (about 10 cm) that were then analyzed using mid-infrared spectroscopy. The spectra obtained were pretreated and then input into two chemometric classification tools: nonlinear iterative partial least squares followed by linear discriminant analysis (NIPALS-LDA) and partial least squares discriminant analysis (PLS-DA). The models produced show that it is possible to discriminate between soil samples from different land use types and both approaches are comparable in performance. NIPALS-LDA performs much better than PLS-DA in classifying samples to location.     

Uncorrelated linear discriminant analysis (ULDA): A powerful tool for exploration of metabolomics data

The theory together with an algorithm for uncorrelated linear discriminant analysis (ULDA) is introduced and applied to explore metabolomics data. ULDA is a supervised method for feature extraction (FE), discriminant analysis (DA) and biomarker screening based on the Fisher criterion function. While principal component analysis (PCA) searches for directions of maximum variance in the data, ULDA seeks linearly combined variables called uncorrelated discriminant vectors (UDVs). The UDVs maximize the separation among different classes in terms of the Fisher criterion. The performance of ULDA is evaluated and compared with PCA, partial least squares discriminant analysis (PLS-DA) and target projection discriminant analysis (TP-DA) for two datasets, one simulated and one real from a metabolomic study. ULDA showed better discriminatory ability than PCA, PLS-DA and TP-DA. The shortcomings of PCA, PLS-DA and TP-DA are attributed to interference from linear correlations in data. PLS-DA and TP-DA performed successfully for the simulated data, but PLS-DA was slightly inferior to ULDA for the real data. ULDA successfully extracted optimal features for discriminant analysis and revealed potential biomarkers. Furthermore, by means of cross-validation, the classification model obtained by ULDA showed better predictive ability than PCA, PLS-DA and TP-DA. In conclusion, ULDA is a powerful tool for revealing discriminatory information in metabolomics data.     

Fluorescence excitation-emission matrix (EEM) spectroscopy for rapid identification and quality evaluation of cell culture media components

The application of fluorescence excitation-emission matrix (EEM) spectroscopy to the quantitative analysis of complex, aqueous solutions of cell culture media components was investigated. These components, yeastolate, phytone, recombinant human insulin, eRDF basal medium, and four different chemically defined (CD) media, are used for the formulation of basal and feed media employed in the production of recombinant proteins using a Chinese Hamster Ovary (CHO) cell based process. The comprehensive analysis (either identification or quality assessment) of these materials using chromatographic methods is time consuming and expensive and is not suitable for high-throughput quality control. The use of EEM in conjunction with multiway chemometric methods provided a rapid, nondestructive analytical method suitable for the screening of large numbers of samples. Here we used multiway robust principal component analysis (MROBPCA) in conjunction with n-way partial least squares discriminant analysis (NPLS-DA) to develop a robust routine for both the identification and quality evaluation of these important cell culture materials. These methods are applicable to a wide range of complex mixtures because they do not rely on any predetermined compositional or property information, thus making them potentially very useful for sample handling, tracking, and quality assessment in biopharmaceutical industries.     

Plasma phospholipid metabolic profiling and biomarkers of type 2 diabetes mellitus based on high-performance liquid chromatography/electrospray mass spectrometry and multivariate statistical analysis

Liquid chromatography/mass spectrometry (LC/MS) followed by multivariate statistical analysis has been successfully applied to the plasma phospholipids metabolic profiling in type 2 diabetes mellitus (DM-2). Principal components analysis and partial least-squares discriminant analysis (PLS-DA) models were tested and compared in class separation between the DM2 and control. The application of an orthogonal signal correction filtered model highly improved the class distinction and predictive power of PLS-DA models. Additionally, unit variance scaling was also tested. With this methodology, it was possible not only to differentiate the DM2 from the control but also to discover and identify the potential biomarkers with LC/MS/MS. The proposed method shows that LC/MS combining with multivariate statistical analysis is a complement or an alternative to NMR for metabonomics applications.     

Detection of apple juice adulteration using near-infrared transflectance spectroscopy

Near-infrared transflectance spectroscopy was used to detect adulteration of apple juice samples. A total of 150 apple samples from 19 different varieties were collected in two consecutive years from orchards throughout the main cultivation areas in Ireland. Adulterant samples at 10, 20, 30, and 40% w/w were prepared using two types of adulterants: a high fructose corn syrup (HFCS) with 45% fructose and 55% glucose, and a sugars solution (SUGARS) made with 60% fructose, 25% glucose, and 15% sucrose (the average content of these sugars in apple juice). The results show that NIR analysis can be used to predict adulteration of apple juices by added sugars with a detection limit of 9.5% for samples adulterated with HFCS, 18.5% for samples adulterated with SUGARS, and 17% for the combined (HFCS + SUGARS) adulterants. Discriminant partial least squares (PLS) regression can detect authentic apple juice with an accuracy of 86-100% and adulterant apple juice with an accuracy of 91-100% depending on the adulterant type and level of adulteration considered. This method could provide a rapid screening technique for the detection of this type of apple juice adulteration, although further work is required to demonstrate model robustness.     

Metabolic profiling of glucuronides in human urine by LC-MS/MS and partial least-squares discriminant analysis for classification and prediction of gender

Mass spectrometry (MS) is increasingly being used for metabolic profiling, but detection modes such as constant neutral loss or multiple reaction monitoring have not often been reported. These modes allow focusing on structurally related compounds, which could be advantageous for situations in which the trait under investigation is associated with a particular class of metabolites. In this study, we analyzed endogenous glucuronides excreted in human urine by monitoring characteristic transitions of putative steroid glucuronides by LC-MS/MS for discrimination of females from males. Two methods for data extraction were used: (i) a manual procedure based on visual inspection of the chromatograms and selection of 23 peaks and (ii) a software-supported method (MarkerView) set to extract 100 peaks. Data from 10 female and 10 male students were analyzed by principal component analysis (PCA) and partial least-squares discriminant analysis (PLS-DA) using software SIMCA. With PCA, only the manual peak selection resulted in clustering males and females. With PLS-DA, the manual method provided full separation on the basis of one single discriminant; the software-supported approach required a two-component model for complete separation. Loading plots were analyzed for their ability to reveal peaks with high discriminating power, that is, potential biomarkers. The PLS-DA models were validated with urine samples collected from five new females and five new males. Gender was correctly assigned for all. Our results indicate that inclusion of biological criteria for variable selection coupled to class-specific MS analysis and data extraction by appropriate software may constitute a valuable addition to the methods available for metabolomics.     

Large-scale human metabolomics studies: a strategy for data (pre-) processing and validation

A large metabolomics study was performed on 600 plasma samples taken at four time points before and after a single intake of a high fat test meal by obese and lean subjects. All samples were analyzed by a liquid chromatography-mass spectrometry (LC-MS) lipidomic method for metabolic profiling. A pragmatic approach combining several well-established statistical methods was developed for processing this large data set in order to detect small differences in metabolic profiles in combination with a large biological variation. Such metabolomics studies require a careful analytical and statistical protocol. The strategy included data preprocessing, data analysis, and validation of statistical models. After several data preprocessing steps, partial least-squares discriminant analysis (PLS-DA) was used for finding biomarkers. To validate the found biomarkers statistically, the PLS-DA models were validated by means of a permutation test, biomarker models, and noninformative models. Univariate plots of potential biomarkers were used to obtain insight in up- or downregulation. The strategy proposed proved to be applicable for dealing with large-scale human metabolomics studies.     

Pixel selection for near-infrared chemical imaging (NIR-CI) discrimination between fish and terrestrial animal species in animal protein by-product meals

This paper proposes a method based on near-infrared hyperspectral imaging for discriminating between terrestrial and fish species in animal protein by-products used in livestock feed. Four algorithms (Mahalanobis distance, Kennard-Stone, spatial interpolation, and binning) were compared in order to select an appropriate subset of pixels for further partial least squares discriminant analysis (PLS-DA). The method was applied to a set of 50 terrestrial and 40 fish meals analyzed in the 1000-1700 nm range. Models were then tested using an external validation set comprising 45 samples (25 fish and 20 terrestrial). The PLS-DA models obtained using the four subset-selection algorithms yielded a classification accuracy of 99.80%, 99.79%, 99.85%, and 99.61%, respectively. The results represent a first step for the analysis of mixtures of species and suggest that NIR-CI, providing valuable information on the origin of animal components in processed animal proteins, is a promising method that could be used as part of the EU feed control program aimed at eradicating and preventing bovine spongiform encephalopathy (BSE) and related diseases.     

Efficient Integration of Sufficient Dimension Reduction and Prediction in Discriminant Analysis

Sufficient dimension reduction (SDR) methods are popular model-free tools for preprocessing and data visualization in regression problems where the number of variables is large. Unfortunately, reduce-and-classify approaches in discriminant analysis usually cannot guarantee improvement in classification accuracy, mainly due to the different nature of the two stages. On the other hand, envelope methods construct targeted dimension reduction subspaces that achieve dimension reduction and improve parameter estimation efficiency at the same time. However, little is known about how to construct envelopes in discriminant analysis models. In this article, we introduce the notion of the envelope discriminant subspace (ENDS) as a natural inferential and estimative object in discriminant analysis that incorporates these considerations. We develop the ENDS estimators that simultaneously achieve sufficient dimension reduction and classification. Consistency and asymptotic normality of the ENDS estimators are established, where we carefully examine the asymptotic efficiency gain under the classical linear and quadratic discriminant analysis models. Simulations and real data examples show superb performance of the proposed method. Supplementary materials for this article are available online.