基于高光谱成像技术的配方烟丝组分判别

应用近红外（1 000～2 200 nm）高光谱成像技术开展了面对像素、面对样本的配方烟丝 4种组分（叶 丝、梗丝、薄片丝、膨胀丝） 的判别研究。以样本高光谱图像的所有像素点光谱数据进行面对像素的组分判 别;以样本所有像素点的平均光谱数据进行面对样本的组分判别。采用二阶导数法结合萨维茨基－戈莱平滑 （SG）滤波对光谱数据进行预处理。通过面对像素数据的主成分分析,证实了基于面对像素的高光谱数据进行 组分判别的可行性,以前5主成分建立的支持向量机模型很好地实现了叶丝与梗丝、叶丝与薄片丝的判别任 务。建立了面对样本的4组分的K近邻和支持向量机判别模型,通过连续投影算法和二阶导数法进行特征波 长选择,筛选出具有高判别准确率的波段,组分判别率达86. 97%。     

基于长春西汀酸的荧光偏振免疫方法测定磺胺二甲氧基嘧啶

合成了荧光标记物长春西汀酸和示踪物磺胺二甲氧基嘧啶-长春胺酸,并采用薄层色谱法对示踪物进行提纯.以磺胺二甲氧基嘧啶为分析对象,利用示踪物与磺胺二甲氧基嘧啶抗体的特异性反应,采用荧光偏振免疫分析方法(FPIA)研究了荧光标记物的荧光光谱特性.此荧光标记物在357 nm的激发光下,于453 nm处产生一个荧光发射峰;以荧光素为对照,考察了本方法的灵敏性.结果显示,荧光素的检出限仅为2.7 μg/L,而本方法的检测范围为0.5～146 μg/L,检出限达到0.5 μg/L.本方法的RSD为3.0%,重现性好;其它磺胺类药物对磺胺二甲氧基嘧啶的测定不产生明显干扰.运用本方法检测了饲料中磺胺二甲氧基嘧啶,结果与HPLC法相吻合.     

基于高光谱技术的玉石鉴定及模型研究

为了给玉石鉴定提供依据以及得到优化预测模型,分别对天然玉石和假玉石的可见光高光谱图像进行分析。针对高光谱图像数据的非线性、小样本以及空间光谱维数大等问题,本研究首先对原始光谱数据进行主成分分析(PCA),使高维光谱数据降维,通过对比分析其平均光谱图和方差贡献率图,发现天然玉石与假玉石的谱线之间存在很大的差距,证明了高光谱成像技术在玉石鉴定领域的可行性。然后分别采用费希尔(Fisher)判别法、反向传输(BP)神经网络以及支持向量机(SVM)判别法建立的三种数学模型对玉石进行分类模式判别,结果显示,用Fisher判别法能直接得到预测的类别归属,用BP神经网络以及SVM判别法得到的类别鉴定准确率分别为96.37%,82.5%。研究结果表明,高光谱技术结合BP人工神经网络预测建模方法可以作为快速和非破坏性预测玉石真假的有效手段。     

基于非接触式拉曼光谱分析人血与犬血的PCA-LDA鉴别方法

将拉曼光谱分析法与数理统计方法有机结合,构建人血与犬血种属判别模型,实现了不同种属血液样本的高效无损鉴别.采用拉曼光谱的无损测试模式对血液样本进行测试,考察了抗凝管管材、聚焦位置及曝光时间等对血液样本拉曼光谱的影响,在激发波长为632.8 nm,光谱扫描范围为200~1800 cm-1,功率衰减率50%,曝光时间5 s及累加次数为2次的优化条件下,获得了无损检测条件下的血液样本拉曼光谱图.针对血液样本组分复杂、拉曼光谱信号基底背景高等问题,提出了基于小波变换去噪,进行分段多项式基线校正的预处理方法,有效解决了血液样本拉曼光谱谱图的高噪音和基线漂移问题.实验选择30例正常人血和33例比格犬血为样本训练集,5例正常人血和5例比格犬血为测试集,基于主成分分析法(PCA)联合线性判别法(LDA)模型,训练集分类正确率达到95.23%,盲测集分类正确率达90.00%.这种基于非接触式血液样本拉曼光谱和PCA-LDA判断模型的测试方法在进出口检验检疫等涉及血液无损鉴别的领域具有广泛的应用价值和前景.     

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。     

基于高光谱技术的培养基上细菌菌落分类方法研究

利用高光谱技术对培养基上细菌(大肠杆菌、李斯特菌和金黄色葡萄球菌)菌落进行快速识别和分类。采集琼脂培养基上细菌菌落的高光谱反射图像(390~1040 nm),在对波段差图像进行大津阈值分割的基础上自动提取细菌菌落光谱,并建立细菌分类检测的全波长和简化偏最小二乘判别( PLS-DA)模型。全波长模型对预测集样本的分类准确率和置信预测分类准确率分别为100%和95.9%。此外,利用竞争性自适应重加权算法( CARS)、遗传算法( GA)和最小角回归算法( LARS-Lasso)进行波长优选并建立对应简化模型。其中,CARS简化模型在精度、稳定性及分类准确率方面均优于GA和LARS-Lasso简化模型,其对预测集样本的分类准确率和置信预测分类准确率分别达到了100%和98.0%。研究表明,高光谱是一种细菌菌落高精度、快速、无损识别检测的有效方法。简化模型中优选的波长可以为开发低成本检测仪器提供理论依据。     

N-(嘧啶-2-基)-N'-乙氧酰基硫脲的合成、晶体结构及量子化学

以2-氨基嘧啶、硫氰酸钾和氯甲酸乙酯为原料,在乙酸乙酯中合成了N-(嘧啶-2-基)-N'-乙氧酰基硫脲,用元素分析和红外光谱对化合物结构进行了表征。采用缓慢蒸发溶剂法在室温下于二甲基甲酰胺溶剂中培养出化合物单晶。晶体结构分析表明,化合物属于单斜系,P21/n空间群,晶胞参数为a=0.49095(19)nm,b=1.5143(6)nm,c=1.4071(6)nm,β=94.047(8)°,V=1.0435(7)nm3,Z=4,Dc=1.453g/cm3,μ=0.297mm-1,F(000)=480,R1=0.0526,wR2=0.1556。化合物分子中只存在2个分子内氢键,氢键及静电引力的共同作用使得化合物呈现复杂的空间结构。运用Gaussian 03程序,在6-311G的基组水平上,用HF、MP2以及B3LYP3种方法对标题化合物进行了几何全优化,并对其成键情况、自然键轨道(NBO)、分子总能量及前沿轨道能量进行了分析,结果表明,化合物中的硫脲基团及嘧啶环是主要的活性中心。     

原位实时近红外光谱研究核壳乳液聚合过程

将苯乙烯(St)和丙烯酸丁酯(BA)单体以不同的聚合方式制备核壳乳液和共聚乳液, 并采用近红外光谱技术实现了对乳液反应过程的原位实时监测, 通过对近红外光谱的谱带归属和主成分分析, 为近红外光谱技术判别乳液聚合过程提供了科学依据, 也为判断反向核壳乳液核壳翻转的拐点提出了一种新的方法. 采用簇类独立软模式法(SIMCA)建立了定性判别模型, 得到了很好的判别结果, 为进一步研究近红外光谱技术用于核壳乳液聚合过程奠定了基础.     

沉淀法合成蓝色长余辉发光材料Sr_2MgSi_2O_7:Eu~(2+),Dy~(3+)

采用沉淀法制备了高亮度的长余辉发光材料Sr_2MgSi_2O_7:Eu~(2+),Dy~(3+).通过XRD、荧光光谱和热释光谱对其进行表征.XRD测试表明所制备的Sr_2MgSi_2O_7:Eu~(2+),Dy~(3+),四方晶.荧光光谱测试表明,λ_(em)=467 nm作为监控波长,在275～450 nm之间有宽的激发光谱,峰值位于399 nm.用λ=399 nm激发样品,其发射光谱为一宽带,峰值位于467 nm.1050℃煅烧前躯体所制备的Sr_2MgSi_2O_7:Eu~(2+),Dy~(3+)发光性能最好.热释光谱峰值位于357 K,适合长余辉现象的产生.对Sr_2MgSi_2O_7:Eu~(2+),Dy~(3+)长余辉发光机理进行了讨论.     

CdS纳米棒的制备、表征及其形成机理

以三辛基膦(TOP)为单一配位溶剂,二水合乙酸镉和硫粉为前驱体,用高温热解的方法制备CdS纳米棒.通过X射线衍射(XRD)、透射电镜(TEM)、高分辨透射电镜(HRTEM)、紫外-可见(UV-Vis)分光光度计、荧光(PL)光谱、傅里叶变换红外(FTIR)光谱和核磁共振磷谱(31PNMR)等方法对样品的结构、形貌和光学特性进行了表征.考察了前驱体Cd/S摩尔比和反应物浓度对硫化镉纳米结构的影响.实验结果表明,该法制备的CdS纳米棒为纤锌矿结构,直径为4.0nm,长度为28.0nm,沿[001]方向择优生长,具有量子限域效应.同时,对CdS纳米晶的形成机理进行了初步的探讨.     

Classifying large chemical data sets: using a regularized potential function method

In recent years classifiers generated with kernel-based methods, such as support vector machines (SVM), Gaussian processes (GP), regularization networks (RN), and binary kernel discrimination (BKD) have been very popular in chemoinformatics data analysis. Aizerman et al. were the first to introduce the notion of employing kernel-based classifiers in the area of pattern recognition. Their original scheme, which they termed the potential function method (PFM), can basically be viewed as a kernel-based perceptron procedure and arguably subsumes the modern kernel-based algorithms. PFM can be computationally much cheaper than modern kernel-based classifiers; furthermore, PFM is far simpler conceptually and easier to implement than the SVM, GP, and RN algorithms. Unfortunately, unlike, e.g., SVM, GP, and RN, PFM is not endowed with both theoretical guarantees and practical strategies to safeguard it against generating overfitting classifiers. This is, in our opinion, the reason why this simple and elegant method has not been taken up in chemoinformatics. In this paper we empirically address this drawback: while maintaining its simplicity, we demonstrate that PFM combined with a simple regularization scheme may yield binary classifiers that can be, in practice, as efficient as classifiers obtained by employing state-of-the-art kernel-based methods. Using a realistic classification example, the augmented PFM was used to generate binary classifiers. Using a large chemical data set, the generalization ability of PFM classifiers were then compared with the prediction power of Laplacian-modified naive Bayesian (LmNB), Winnow (WN), and SVM classifiers.     

烟草组分的近红外光谱和支持向量机分析

测定了120个产自福建、安徽和云南烟草样品的近红外光谱. 在利用支持向量机(SVM)技术建立其定量、定性分析模型之前, 用小波变换技术对光谱变量进行了有效的压缩, 然后采用径向基核函数建立了75个烟草样品的分类模型, 同时建立了总糖、还原糖、烟碱和总氮4个组分的定量分析模型, 并利用45个烟草样品对模型进行了检验. 仿真实验表明, 建立的SVM分类模型分类准确率达到100%, 而4个组分的定量分析模型的预测决定系数(R2)、预测均方差(RMSEP)和平均相对误差(RME)3个指标值显示其模型泛化能力非常强, 预测效果良好, 可见这是一种有效的近红外光谱的建模分析方法.     

Rapid Diagnosis of Type II Diabetes Using Fourier Transform Mid-Infrared Attenuated Total Reflection Spectroscopy Combined with Support Vector Machine

Type II diabetes was diagnosed by Fourier transform mid-infrared (FTMIR) attenuated total reflection (ATR) spectroscopy in combination with support vector machine (SVM). Spectra of serum samples from 65 patients with clinical confirmed type II diabetes mellitus and 55 healthy volunteers were acquired using ATR-FTMIR and were first pretreated by three pretreatments (Savitzky–Golay smoothing, multiple scattering correction, and wavelet transforms algorithms) to reduce the interfering information before establishing the SVM models. The parameters of SVM (penalty factor C and kernel function parameter gamma) were optimized to improve the generalization abilities of the models. A grid search method (GS), genetic algorithm (GA), and particle swarm optimization (PSO) algorithm, were used to find out the optimal parameter values. The results showed that the maximum accuracies were 95.74, 97.87, and 89.36% for the optimized GS, GA, and PSO algorithms. The maximum sensitivities were 96, 100, and 92, and the maximum specificity were 95.45, 95.45, and 86.36%, respectively. The results indicated that the accuracy of type II diabetes was improved using the GS, GA, and PSO algorithms for optimizing the SVM parameters. The GA was found to be slightly better than the GS and PSO. The results of the experiment confirmed that the combination of the ATR-FTMIR spectroscopy and SVM was able to rapidly and accurately diagnose type II diabetes without reagents.     

Quantitative analysis of routine chemical constituents in tobacco by near-infrared spectroscopy and support vector machine

It is important to monitor quality of tobacco during the production of cigarette. Therefore, in order to scientifically control the tobacco raw material and guarantee the cigarette quality, fast and accurate determination routine chemical of constituents of tobacco, including the total sugar, reducing sugar, Nicotine, the total nitrogen and so on, is needed. In this study, 50 samples of tobacco from different cultivation areas were surveyed by near-infrared (NIR) spectroscopy, and the spectral differences provided enough quantitative analysis information for the tobacco. Partial least squares regression (PLSR), artificial neural network (ANN), and support vector machine (SVM), were applied. The quantitative analysis models of 50 tobacco samples were studied comparatively in this experiment using PLSR, ANN, radial basis function (RBF) SVM regression, and the parameters of the models were also discussed. The spectrum variables of 50 samples had been compressed through the wavelet transformation technology before the models were established. The best experimental results were obtained using the (RBF) SVM regression with gamma=1.5, 1.3, 0.9, and 0.1, separately corresponds to total sugar, reducing sugar, Nicotine, and total nitrogen, respectively. Finally, compared with the back propagation (BP-ANN) and PLSR approach, SVM algorithm showed its excellent generalization for quantitative analysis results, while the number of samples for establishing the model is smaller. The overall results show that NIR spectroscopy combined with SVM can be efficiently utilized for rapid and accurate analysis of routine chemical compositions in tobacco. Simultaneously, the research can serve as the technical support and the foundation of quantitative analysis of other NIR applications.