水平衰减全反射傅里叶变换红外光谱法结合化学计量学鉴别问荆与节节草

采用水平衰减全反射傅里叶变换红外光谱法(HATR-FT-IR)测定中药问荆和同科植物节节草的FT-IR谱,运用连续小波变换(CWT)多分辨率分析法对吸收较为相似的问荆及节节草的FT-IR进行特征提取.选择第8、9、10分解层数下的特征值作为分析的基础,采用FT-IR-CWT-SVM法建立了问荆和节节草识别的模型.通过学习训练,对120个预测样品的识别准确率为90%以上.当采用径向基函数作为核函数时,识别准确率达100%.样品的FT-IR经小波特征提取后的特征值有所差异,采用SVM进行识别可以很好地把两者分类.通过对样品的FT-IR小波变换后所得特征值进行SVM的分类,能够有效地进行区别鉴定形态较为相似的同科植物问荆及节节草.     

衰减全反射-傅里叶变换红外光谱法测定橙子油中柠檬烯的含量

应用衰减全反射傅里叶变换红外光谱法测定橙子油中柠檬烯的含量。柠檬烯的特征峰(1 645.1±1)cm-1为定量测量峰,测定样品在15min内完成。柠檬烯的体积分数在9.60%~76.8%范围内与测量峰峰高呈线性关系。以橙子油样品为基体进行加标回收试验,所得回收率在99.7%~101%之间,测定值的相对标准偏差(n=5)为1.1%。     

大鼠胰腺及癌组织红外光谱连续小波特征提取及径向基人工神经网络识别

采用水平衰减全反射(HATR)傅里叶变换红外光谱法(FTIR)测定了SD大鼠胰腺正常组织与非正常组织的谱图,提出了一种新的基于FTIR的连续小波特征提取与径向基人工神经网络分类方法以提高FTIR对早期SD大鼠胰腺癌的诊断准确率。利用连续小波多分辨率分析法提取FTIR特征量,对于提取的特征量采用径向基函数神经网络进行模式分类。对SD大鼠的胰腺正常组织、早期癌组织及进展期癌组织的FTIR,利用连续小波多分辨率分析法提取9个特征量,进行RBF神经网络分类判断。当目标误差为0.01,径向基函数的分布常数为5时,网络达到最优化,总的正确识别率为96.67%。并对影响分类结果的网络参数、目标误差和分布常数对分类样品的影响做了讨论。实验结果表明:此方法对早期胰腺癌具有较高的诊断率。     

离散小波特征提取及人工神经网络分类法的傅里叶变换红外光谱法识别鳞毛蕨科3种植物

利用水平衰减全反射-傅里叶变换红外光谱法测定了3种药用鳞毛蕨科植物贯众、阔鳞鳞毛蕨和变异鳞毛蕨根部的FT-IR。运用基于离散小波多分辨率分析法对FT-IR吸收较为相似的3种药用蕨类植物根的FT-IR进行特征提取。选择第4、5分解层数的特征向量,进行人工神经网络(Artificial neural network,ANN)训练;再用训练出来的网络对不同产地的3种药用蕨类植物根所得FT-IR小波提取的特征向量进行分类。通过对240个不同样本的预测,说明能够采用基于FT-IR-离散小波特征提取及人工神经网络分类法对同科3种药用蕨类植物根的FT-IR进行识别。     

基于小波和小波包变换的苯丙酮尿症傅里叶变换衰减全反射红外光谱筛查模型的研究

应用小波和小波包变换对傅里叶变换衰减全反射红外光谱(FTIR/ATR)进行去噪处理,以提高苯丙酮尿症(PKU)筛查模型的性能。首先优化小波和小波包变换的参数,然后分别对原始光谱(OS)、9点平滑光谱(9S)和一阶微分9点平滑光谱(1D9S)进行去噪处理,以均方根误差(RMSE)、平均相对误差(MRE)、预测准确率(Acc)等为指标,考察小波和小波包变换对模型性能的影响。结果与变换前相比,模型性能均有所提高,其中小波变换以1D9S+sym12处理结果为最优,而小波包变换以1D9S+sym1为最优;Acc全部提高为100%。     

傅里叶变换红外光谱诊断地中海贫血症

为建立简单快速的地中海贫血诊断方法,本研究探讨了以傅里叶变换红外光谱结合水平衰减全反射(FTIR-HATR)技术在地中海贫血诊断中的制样方法及光谱的数据处理方法.在制样预处理中,通过对样品进行稀释并干燥成膜消除水分子对光谱吸收干扰,保持ATR光谱中各波长对样品的穿透深度一致.结果表明,当1652 cm-1吸收度小于1.5时(即透射率T小于4%时),各波峰强度与血红蛋白浓度呈良好的线性关系(r>0.995)及实验重复性(RSD<4%).在数据处理上,改进的相对强度方法用于800～1780 cm-1和2480～3600 cm-1区间的分析.通过与常规的傅里叶去卷积谱及差谱方法相比,本方法可消除样品浓度所带来的影响因素,灵敏地揭示群体数据中组分与结构在不同组间的显著差异,如1638 cm-1处重叠的蛋白二级结构峰,1172 cm-1、1440 cm-1表征脂类物质的吸收峰,1064 cm-1表征磷酸化合物峰位及表征SH的2553 cm-1附近的吸收峰在正常组与地中海贫血组间存在显著差异.从而避免了几个峰位的相对强度所反映的信息不足及选择参比峰的困扰,对揭示整体的差异变化规律有着重要的作用.     

傅里叶变换-红外光谱法快速测定面粉中滑石粉

提出了应用衰减全反射(ATR)傅里叶变换-红外光谱(FT-IRS)法快速检测面粉中混入的滑石粉,测定中采用中红外检测器。根据滑石粉的标准红外光谱图并为避免面粉的吸收干扰,选择滑石粉在3 674.96 cm-1及668.16 cm-1两处的特征吸收峰作为判定面粉中是否含有滑石粉的依据,并且其吸收强度随滑石粉含量的增加而增加。由于面粉中滑石粉质量分数低于0.5%和0.2%时,分别在上述两吸收峰波长处已不呈现吸收,方法中将1%(质量分数)作为滑石粉的检出限。此外,根据吸收峰的吸收强度可估算出滑石粉的含量。方法中选用的主要仪器工作条件为:①扫描范围为4 000～650 cm-1;②分辨率为8 cm-1;③扫描信号累加次数为32;④衰减全反射压力常数为100。     

傅里叶变换红外光谱法结合聚类分析对大叶藓及其易混种类的鉴别

采用傅里叶变换红外光谱法结合聚类分析对大叶藓及其易混种类(平肋提灯藓、树形疣灯藓、皱叶匐灯藓、尖叶匐灯藓)进行了鉴别。以红外光谱图4 000~500cm-1范围内的吸收峰吸光度为指标,应用组间连接法对5种藓类植物进行聚类分析,结果表明:大叶藓与提灯藓科易混类群距离较远。     

三阶导数衰减全反射傅里叶变换红外光谱对车漆的快速鉴别研究

为了解决公安工作中对嫌疑车辆的掉落车漆进行无损、快速和准确的鉴别,本实验提出一种基于三阶导数衰减全反射傅里叶变换红外光谱结合主成分分析和Fisher判别分析的方法。通过实验收集并分析了59个车漆样本的光谱数据及其三阶导数谱图,在实验预处理上采用峰面积归一化、Savitzky-Golay平滑和自动基线校正,建立判别分析模型,对每个样本的原始光谱图进行求导,得出各个样本的高阶导数衰减全反射傅里叶变换红外光谱并汇总所有样本的各个阶次的导数数据,建立不同阶次导数光谱数据的判别分析模型,对其区分准确率进行对比。实验研究结果表明,车漆样本的三阶导数光谱技术结合主成分分析的判别分析模型区分准确率高达到98.3%,可准确度地对6个不同品牌的车漆进行有效区分。经过多次实验分析数据,三阶导数光谱可以有效放大各个样本的数据差异、挖掘隐藏于复杂谱峰中的有用信息,可以更准确的对其进行区分,实验结果表明三阶导数衰减全反射傅里叶变换红外光谱结合主成分分析和判别分析的方法是一种有效的红外显微图像分析方法,可为其他的物理证据的鉴定与分析提供一定参考和借鉴。     

Detection of Cholangiocarcinoma with Fourier Transform Infrared Spectroscopy and Radial Basis Function Neural Network Classification

The aim of this study was to explore the possibility of applying Fourier transform infrared(FTIR) spectroscopy as a medical diagnostic tool based on a neural network classifier for detecting and classifying cholangiocarcinoma. A total of 51 cases of bile duct tissues were obtained and later characterized by FTIR spectroscopy prior to pathological diagnosis. The criteria for classification included 30 parameters for each FTIR spectra, including peak position(P), intensity(I) and full width at half-maximum(FWHM), were measured, calculated and subsequently compared against the normal and cancer groups. The FTIR spectra were classified by the radial basis function(RBF) network model. For establishing the RBF, 23 cases were used to train the RBF classifier, and 28 cases were applied to validate the model. Using the RFB model, nine parameters were observed to be pronouncedly different between cancerous and normal tissue, including I₁₆₄₀, I₁₅₅₀, I₁₄₆₀, I₁₄₀₀, I₁₂₅₀, I₁₁₂₀, I₁₀₈₀, I₁₀₄₀ and P₁₀₄₀. In the RBF training classification, the accuracy, sensitivity, and specificity of diagnosis were 82.6%, 80.0%, and 84.6%, respectively. While validating the classification, the accuracy, sensitivity, and specificity of diagnosis were 78.6%, 75.0%, and 81.2%, respectively. The results suggest that FTIR spectroscopy combined with neural network classifier could be applied as a medical diagnostic tool in cholangiocarcinoma diagnosis.     

小波包压缩-RBF网络同时测定润滑油中铁、铜、锌

将小波包压缩-RBF网络方法用于润滑油中铁铜锌三组分分光光度同时测定该方法采用小波包函数对光谱数据进行压缩处理,用较大的小波色系数构成新的校正集和预测集代替原始的校正集和预测集,然后用RBF网络进行数据解析。研究表明,用bior2．4小波包处理原始测定数据,最佳小波基用logenerge熵标准,选择适当阈值将变量数由46个压缩成25个（压缩比为0．54）,整体预测效果最好。将此方法用于合成样预测．预测结果与实际浓度的相对误差绝对值在2．50％～9．40％之间;用于实际润滑油样品中铁、铜和锌的同时测定,解析值与原子吸收法（AAS）的测定值的相对误差绝对值作3．55％～7．86％之间。应用结果令人满意。     

近红外光谱-径向基神经网络在异烟肼片无损定量分析中的应用

应用异烟肼片粉末的近红外漫反射光谱数据分别结合偏最小二乘法(PLS)和径向基神经网络(RBFNN)建立定量分析模型,并用所建模型对预测集样品进行了预测,结果表明:应用RBFNN所建立的定量分析模型优于PLS模型,相关系数(r)值由0.99593提高到0.99734,交互验证均方根误差(RMSECV)值由0.00523下降到0.00423,预测均方根误差(RMSEP)值由0.00614下降到0.00501。     

Application of experimental design and radial basis function neural network to the separation and determination of active components in traditional Chinese medicines by capillary electrophoresis

Orthogonal design has been used to the optimization of separation and determination of two active components in traditional Chinese medicines by capillary electrophoresis. The concentration of phosphate, applied voltage, organic modifier content and buffer pH were selected as variable parameters. Their different effects on peak resolution were studied by the experimental design method. Optimized separation conditions were obtained and successfully applied to the separation and determination of aconitine and hypaconitine in Aconitum medicinal herbs. Good separation was achieved within 7 min using a buffer system composed of 20 mmol L⁻¹ phosphate and 35% acetonitrile at pH 9.5. The applied voltage was 14 kV and the detection was set at 235 nm. In addition, a radial basis function neural network with a “4-18-1” structure was developed based on the experimental results of orthogonal design and uniform design, and was applied to the prediction of peak resolution of the two active components under the optimum separation conditions given by orthogonal design. The predicted results were in good agreement with the experimental values, indicating that radial basis function neural network is a potential way for the selection of separation conditions in capillary electrophoresis.     

径向基神经网络奥斯特杨方波伏安法同时测定铬和锌

径向基函数神经网络(RBFN)和核心偏最小二乘法(KPLS)用于分析重叠的Cr（Ⅲ）和Zn(Ⅱ）的奥斯特杨(Osteryoung)方波伏安图，程序SPRBFN和SPKPLS被设计用于全部计算。在RBFN方法中，普通高斯函数可用作隐藏层非线性转移函数。由于其局部性质，RBFN能被快速训练，避免陷入局部最小。对两个方法预测能力的研究结果显示其所有组分的相对预测标准偏差(RSEP)分别为0．677％和13．0％。因此，RBFN方法较之K眦方法可提供更为精确的结果，而且在解决局部最小，改进收敛速率方面也不失为一个重要的工具。     

HATR-FTIR-排序法识别中药材紫花地丁及其伪品的研究

采用水平衰减全反射傅里叶变换红外光谱(HATR-FTIR)法测定了紫花地丁及其伪品如白花地丁、犁头草、辽宁堇菜及匍伏堇的根木质部和茎外表皮部的傅里叶变换红外光谱,采用主成分分析法(PCA)比较了正伪品之间的差异程度。结果表明：基于傅里叶变换红外光谱的主成分分析在反映同科同属不同种植物化学组成差异程度上具有应用价值。     

基于改进排序遗传算法的径向基函数神经网络色谱峰解析

构造了以塔板模型为基函数的径向函数神经网络（P－RBFNN），为了使P－RBFNN具有结构重组能力，又在网络学习算法中引入鲁棒（Rubust)和随机全局最优的两阶段排序遗传算法：结构学习和进化。P－RBFNN结合改进的排序遗传算法很适合组分数未知的色谱（含重叠）峰解析。     

Application of Near Infrared Diffuse Reflectance Spectroscopy with Radial Basis Function Neural Network to Determination of Rifampincin Isoniazid and Pyrazinamide Tablets

Partial least squares(PLS),back-propagation neural network(BPNN)and radial basis function neural network(RBFNN)were respectively used for estalishing quantative analysis models with near infrared(NIR)diffuse reflectance spectra for determining the contents of rifampincin(RMP),isoniazid(INH)and pyrazinamide(PZA)in rifampicin isoniazid and pyrazinamide tablets.Savitzky-Golay smoothing,first derivative,second derivative,fast Fourier transform(FFT)and standard normal variate(SNV)transformation methods were applied to pretreating raw NIR diffuse reflectance spectra.The raw and pretreated spectra were divided into several regions,depending on the average spectrum and RSD spectrum.Principal component analysis(PCA)method was used for analyzing the raw and pretreated spectra in different regions in order to reduce the dimensions of input data.The optimum spectral regions and the models' parameters were chosen by comparing the root mean square error of cross-validation(RMSECV)values which were obtained by leave-one-out cross-validation method.The RMSECV values of the RBFNN models for determining the contents of RMP,INH and PZA were 0.00288,0.00226 and 0.00341,respectively.Using these models for predicting the contents of INH,RMP and PZA in prediction set,the RMSEP values were 0.00266,0.00227 and 0.00411,respectively.These results are better than those obtained from PLS models and BPNN models.With additional advantages of fast calculation speed and less dependence on the initial conditions,RBFNN is a suitable tool to model complex systems.