主成分—人工神经网络在近红外光谱定量分析中的应用

近红外光谱的主成分由非线性迭代偏最小二乘法（ＮＩＰＡＬＳ）求出,主成分作标准化处理后,作为Ｂ－Ｐ神经网络的输入结点进行非线性迭代。该法的优点是,充分利用了全光谱的数据,得到消除噪声后的最佳主成分,能建立非线性模型,Ｂ－Ｐ神经网络迭代时间显著缩短,用该法对大麦中的淀粉含量进行了定量分析研究。结果为：校准和预测的相关系数分别为０．９８１和０．９５３,校准和预测的相对标准偏差分别为１．７０％和２．４８％     

主成分回归残差神经网络校正算法用于近红外光谱快速测定汽油辛烷值

根据汽油辛值预测体系本身的非线性特点,提出主成分回归残差神经网络校正算法（principal component regression residual artificial neural network,PCRRANN)用于近红外测定汽油辛烷值的预测模型校正,该方法给合了主成分回归算法（PC）,与经典的线性校正算法（PLS（Partial Least Square),PCR, 以及非线性PLS（NPLS,Non-linear PLS)等相比,预测明显的改善,文中还讨论了PCR主成分数及训练参数对预则模可能的影响。     

主成分-人工神经网络在近红外光谱定量分析中的应用

近红外光谱的主成分由非线性迭代偏最小二乘法（ＮＩＰＡＬＳ）求出。主成分作标准化处理后,作为Ｂ－Ｐ神经网络的输入结点进行非线性迭代。该法的优点是,充分利用了全光谱的数据,得到消除噪声后的最佳主成分,能建立非线性模型,Ｂ－Ｐ神经网络迭代时间显著缩短。用该法对大麦中的淀粉含量进行了定量分析研究。结果为：校准和预测的相关系数分别为０．９８１和０．９５３,校准和预测的相对标准偏差分别为１．７０％和２．４８％。     

基于近红外光谱技术与优化光谱预处理的陈皮产地鉴别研究

采集不同产地陈皮内侧和外侧的近红外光谱,采用不同光谱预处理方法进行预处理,筛选得到最佳光谱预处理方法,结合主成分分析法建立了陈皮产地的鉴别模型.实验发现,陈皮原始光谱中存在明显的基线漂移与背景干扰.使用单一光谱预处理可在一定程度上消除干扰的影响.经标准正态变量变换、多元散射校正、一阶导数、二阶导数与连续小波变换预处理后...     

红外光谱结合主成分分析鉴别道地山药

用红外指纹图谱和主成分分析法，对来自8省的74个山药样本的道地与非道地性进行了聚类分析，以主成分2和3作二维线性投影图，均具有较好的聚类和鉴别作用。利用已建模型预测了11个样本的道地性，正确率达90.9%。结果表明：所建模型合理，具有明显的分类和鉴别作用，具有一定的可行性和可靠性，为山药道地性鉴别提供了一种新的方法。     

基于近红外光谱分析技术的食品包装塑料的定性分析

该文基于近红外漫反射光谱分析技术对食品包装材料聚乙烯、聚丙烯进行定性判别试验研究,选取不同波段范围、采用不同光谱预处理方法,使用主成分分析法(Principal component analysis,PCA)结合SIMCA、贝叶斯判别、K-近邻3种模式识别方法建立定性预测模型,并根据正确识别率比较了各模型预测性能。结果表明:使用SIMCA方法、贝叶斯判别、K-近邻3种方法建立的定性校正模型均在1 050～1 550 nm波长范围内效果较好;采用矢量归一化、标准正态变量变换、中心化、滑动均值滤波、多项式平滑滤波、一阶微分6种光谱预处理方法和上述3种模式识别方法对塑料样品近红外光谱进行了数据处理,其中在1 050～1 550 nm范围内,主成分因子数为3,采用原始光谱建立的K-近邻定性校正模型较优,对样品校正集和预测集的正确识别率均为100%。可为食品包装材料聚乙烯、聚丙烯的快速鉴别研究提供参考。     

主成分分析-近红外光谱法快速测定婴儿配方乳粉中必需脂肪酸

利用主成分分析法将婴儿乳粉的近红外光谱数据与必需脂肪酸含量建立校正模型,并采用交互验证和外部检验两种方式来考察模型的可靠性。得到模型校正相关系数(R2)0.8704,均方估计残差(RMSEC)和交互校验均方残差(RMSECV)分别为0.6275和0.8907,应用所建立的必需脂肪酸近红外模型对婴儿乳粉必需脂肪酸含量进行预测,并将预测值和化学测量值进行配对t检验,结果表明两者无显著差异。     

近红外光谱主成分-所有可能回归法定量分析烤烟、小麦样品中的组分含量

利用主成分-所有可能回归法,建立了烤烟、小麦样品不同组份的近红外光谱定量分析模型。结果表明,烤烟样品的总糖、还原糖以及小麦样品的蛋白质含量的预测模型均有好的定量分析结果,且其预测结果与PLS法预测结果相当。     

基于近红外光谱技术与化学计量学的绿茶无损鉴别方法研究

该文利用近红外光谱技术结合化学计量学方法开发了不同品种绿茶的无损鉴别方法。通过近红外光谱技术得到了8个品种绿茶样品的近红外光谱,比较了单一以及优化组合光谱预处理方法对光谱的影响,利用无监督的主成分分析(PCA)与有监督的线性判别分析方法(LDA)分别构建了茶叶品种鉴别模型。结果表明:对比单一预处理方法,优化组合预处理具有更优的鉴别准确性。标准正态变量变换预处理消除了茶叶样品大小不均造成的光谱散射影响,一阶导数预处理实现了变动背景的消除,减少了基线漂移的影响,突出了图谱中的有效信息,采用二者相结合的预处理方式并结合无监督的主成分分析法可实现较为准确的绿茶样品种类鉴别分析,准确率达75.0%。此外,采用有监督的线性判别分析方法处理原始光谱数据,可达到100%的鉴别准确率,但该方法需提供类别的先验知识。因此,采用近红外光谱技术和化学计量学相结合的手段可实现不同品种绿茶的快速无损鉴别。     

主成分分析法用于中草药中微量元素含量的研究

应用主成分分析法,结合SPSS统计软件,对7种中草药中微量元素的含量进行定量定性的综合评价。在综合评价中,由第一和第二主成分的累计方差贡献率达到74．76％。该研究为中草药的开发和利用提供了科学依据。     

主成分分析-支持向量回归建模方法及应用研究

将主成分分析(PCA)用于近红外光谱的特征提取,并与支持向量回归(SVR)相结合,实现了主成分分析-支持向量回归(PCA-SVR)用于近红外光谱定量分析的建模方法。与单纯的SVR方法相比,不仅提高了运算速度,而且提高了模型的预测准确度。将PCA-SVR方法用于烟草样品中总糖和总挥发碱含量的测定,所得结果的预测均方根误差分别为1.323和0.0477;回收率分别为91.8%~112.6%和88.9%~120.2%。     

应用近红外光谱分析技术快速分析饲料质量

以饲料质量分析为例,综述了近红外光谱分析技术及仪器的发展、回归校正技术及在快速分析饲料质量中的应用,引用文献２５篇     

近红外光谱法结合化学计量学方法用于茶油真伪鉴别分析

采用近红外光谱透反射模式结合化学计量学方法对纯茶油进行真伪鉴别.收集并扫描了163个样品(合格97个,不合格66个),对样本进行光谱数据预处理优化及有效波段筛选.在5750～6000 cm-1波段处,光谱经过平滑,一阶导数以及自归一化后,采用无监督学习算法即主成分分析法(Principal component anal...     

Study on Light Aging of Silk Fabric by Fourier Transform Infrared Spectroscopy and Principal Component Analysis

To investigate environmental effect on cultural materials, Fourier transform infrared technique (FTIR/ATR) was applied to analyze the silk aging process. Changes in chemical and conformational structures of silk fabric undergoing ultraviolet induced degradation were investigated. The IR spectra provided strong bands of photosensitive amide I, II, and III. For overlapping amide III region, both of the original and second-derivative IR spectra revealed that UV irradiation induced the structural transformation from β-sheet domain to β-turn conformation, which was supported by the increase of β-turn marker band at 1015 cm^?1 associated with polyglycine. Additionally the reduced bands associated with (GlyAla)_n segment at 1000 and 976 cm^?1, and the decreased band at 1070 cm^?1 related to β-sheet structure also illustrated the conformational transition. Furthermore, we applied a chemometric method of principal component analysis for the evaluation of silk degradation based on variations in amide I spectral region. The score plot using the first two principal components effectively summarized the general trend of silk-aging and revealed the quick degradation appeared in the initial stages (12 h and 24 h) and the 108-hr stage. This work provides a potential novel application of the infrared spectroscopy in noninvasive qualitative and quantitative investigation of silk degradation.     

Rapid Authentication of Olive Oil by Raman Spectroscopy Using Principal Component Analysis

A method of principal component analysis was employed to authenticate genuine olive oil based on Raman spectroscopy, which can reliably distinguish olive oil from other types of oils and can also accurately identify the level of adulteration in a set of olive oil samples contaminated with 5% or more of other types of oils, such as soybean oil, rapeseed oil, sunflower seed oil, and corn oil. The method is very easy, effective, time-saving, and requires minimal sample preparation. Therefore, the method is a promising technique for the rapid authentication application of olive oil.

[Supplementary materials are available for this article. Go to the publisher's online edition of Analytical Letters for the following free supplemental resource(s): Additional text and table]     

Characterization of Automobile Plastics by Principal Component Analysis and Near-Infrared Spectroscopy

Based on near-infrared diffuse reflection spectroscopy, multivariate calibration models for discarded automobile plastic were constructed using principal component analysis and clustering analysis to rapidly characterize four widely employed materials: polypropylene, polyethylene, acrylonitrile butadiene styrene, and polymethylmethacrylate with an accuracy rate of 97%. The method was shown to rapidly discriminate waste automobile plastic.     

Tea Classification by Near Infrared Spectroscopy with Projection Discriminant Analysis and Gene Expression Programming

Traditional gene expression programming for classification is designed for binary decisions. Herein, projection discriminant analysis for direct multiclass categorization using gene expression programming is described. Gene expression programming was first employed to examine new synthetic variables that were built as nonlinear combinations of the original features. The data were projected on planes spanned by these new synthetic variables and the nearest centroid was employed to classify new samples. A new objective function was formulated to determine optimum synthetic variables. Direct multiclass categorization using a gene expression programming algorithm was used to classify six tea varieties analyzed by near infrared spectroscopy. Compared with traditional gene expression programming, principal component analysis, and linear discriminant analysis, direct multiclass categorization with gene expression programming algorithm was more efficient. Visual inspection of high dimensional data by this approach also facilitated classification and comprehension of data.     

近红外光谱用于低温水结构的分析

采用近红外光谱分析并结合拉曼光谱和分子动力学模拟研究了二甲基亚砜(DMSO)-水混合物中水在低温时的结构,对DMSO降低水冰点的机理进行了讨论.通过对不同DMSO含量混合物的近红外和拉曼光谱分析,发现了DMSO与水相互作用的光谱信息,表明DMSO与水在混合物中主要以摩尔比1∶2和2∶1的氢键结构(DW2和D2W)的形式存在,结构形式主要取决于DMSO和水在混合物中的比例.通过对水和30%(摩尔分数)DMSO-水混合物的温控近红外光谱分析,发现DW2结构抑制四面体水结构的形成是混合物冰点降低的主要原因.采用分子动力学模拟对DMSO-水混合物体系进行的模拟进一步证明了结论的可靠性.