同时测定铁钴铜的小波软阈值核心偏最小二乘法

提出了一种小波软阈值核心偏最小二乘法，同时测定铁、钴、铜；该法结合小波软阈值法和主组分分析改进除噪声质量，与其它软阈值法比较选用了HYBRID法；通过最佳化，小波函数和低频截止收缩水平（L）分别选用Symmlet6和2；设计了一个名为软阈值小波核心偏最小二乘法（STWKPLS）的程序进行全部计算，实验结果表明该法是成功的，并且优于核心偏最小二乘法。     

小波变换结合多维偏最小二乘方法用于近红外光谱定量分析

将小波变换和多维偏最小二乘法相结合用于近红外光谱定量校正模型的建立.首先将原始光谱进行小波变换分解,得到系列小波细节系数,通过选取一组受外界因素少、信息强的小波系数组成三维光谱阵,然后再采用多维偏最小二乘法建立校正模型.实验结果表明,该方法所建近红外校正模型的预测能力更强,并更具稳健性.     

小波变换结合多维偏最小二乘方法用于近红外光谱定量分析

将小波变换和多维偏最小二乘法相结合用于近红外光谱定量校正模型的建立。首先将原始光谱进行小波变换分解，得到系列小波细节系数，通过选取一组受外界因素少、信息强的小波系数组成三维光谱阵，然后再采用多维偏最小二乘法建立校正模型。实验结果表明，该方法所建近红外校正模捌的预测能力更强，并更具稳健性。     

基于小波变换的航空润滑油酸值红外光谱分析

为利用红外光谱分析技术快速、准确测定在用航空润滑油酸值,将小波变换用于润滑油红外光谱预处理中,结合均值中心化法,提取光谱有效信息建模。光谱的小波变换选择符合光谱特征的db4小波为基函数,在分解尺度9下进行光谱分解,利用软阈值法滤除各层干扰噪声,重构消噪信号。该光谱预处理法与传统的Savitzky-Golay平滑导数结合均值中心化法相比,滤噪效果好,有效压缩了建模数据量。采用偏最小二乘法,选择最佳主因子数5,建立酸值模型,并对10个在用航空润滑油油样进行了分析。     

化学计量学-荧光分析法同时测定萘、1-萘酚和2-萘酚

根据正交信号校正(OSC)、小波包变换(WPT)及偏最小二乘法(PLS)的算法原理,编制了名为POSC-WPTPLS的程序,结合荧光分析法快速、灵敏、选择性较好的优点,将该程序用于同时测定荧光光谱严重重叠的萘、1-萘酚和2-萘酚多组分体系,并将3种化学计量学方法(OSC-WPT-PLS、WPT-PLS和PLS)进行比较...     

非线性偏最小二乘法在速效伤风胶囊紫外分光光度分析中的应用

本文介绍了非线性偏最小二乘法的基本原理及算法。以速效伤风胶囊的紫外分光光度分析为例,扑热息痛、咖啡因、扑尔敏、人工牛黄四组分的测定结果满意,且明显好于线性偏最小二乘法。本法为多组分混合体系的分光光度分析提供了更为理想的新途径。     

基于小波变换-遗传算法-偏最小二乘的草莓糖度检测研究

采用近红外漫反射光谱分析技术,对草莓糖度进行了无损检测研究。利用便携式近红外光谱仪采集草莓样品在600～1 100 nm波段内的漫反射光谱数据。首先利用小波变换(WT)多分辨率方法对光谱数据进行去噪预处理,然后利用遗传算法(GA)优选特征波长,最后运用偏最小二乘法(PLS)建立草莓糖度的WT-GA-PLS校正模型。该模型校正集的相关系数R_C为0.9395,校正集的均方根误差RMSEC为0.1615,预测集的相关系数R_P为0.9652,预测集的均方根误差EMSEP为0.5042。与全光谱模型(FS-PLS)和小波变换模型(WT-PLS)相比,该模型预测能力更强,稳健性更优。     

傅里叶变换用于铁和锌的同时光度测定

研究了傅里叶变换技术用于铁锌二组分的同时分光光度测定，采用傅里叶变换对吸光度数据进行预处理，再结合目标转换因子分析或偏最小二乘分析，结果较普通的目标转换因子分析或偏最小二乘法有显著改善。以傅里叶变换－偏最小二乘法就用于实际铝合金样品中铁和锌的同时测定，结果令人满意。     

偏最小二乘-同步荧光法测定人尿中黄蝶呤

建立了人尿中黄蝶呤含量测定的同步荧光分析方法。在pH 7.8 KH2PO4-NaOH缓冲溶液中,于Δλ为70 nm的条件下对黄蝶呤及其它蝶呤类化合物进行同步荧光扫描,所得的重叠波谱数据用主成分回归法(PCR)、偏最小二乘法(PLS)、经典最小二乘法(CLS)和径向基人工神经网络(RBF-ANN)等多元校正法进行处理,结果表明偏最小二乘法(PLS)的分析结果最好,其标准偏差为4.29%。该方法简便、快速、准确,避免了较繁琐的样品前处理过程,应用于人尿中黄蝶呤分析,结果令人满意。     

化学计量学方法同时测定铁、铝和铍

采用正交信号校正(OSC)-小波包变换(WPT)-偏最小二乘法(PLS)(OSCW-PTPLS)相结合的化学计量学方法,用于不经化学分离解析光谱严重重叠的Fe(Ⅲ)、Al(Ⅲ)和Be(Ⅱ)混合物。该法结合OSC,WPT和PLS三种技术提高了获取特征信息的能力和回归质量。本文测定的三种金属离子可与铬天青S和溴化十六烷基吡啶(CPB)在pH=5.60的邻苯二甲酸氢钾-NaOH缓冲溶液中发生高灵敏度和低选择性的显色反应。设计了一个名为POSCWPTPLS的程序来执行相关计算。实验结果显示OSCWPTPLS方法优于PLS方法。     

化学计量学在电分析化学中的新进展

评述了化学计量学的各种方法,如主成分分析、偏最小二乘、小波分析、人工神经网络等在电分析化学中的进展,主要介绍了这些方法在电分析化学中的应用,并展望了化学计量学在电分析化学中的应用前景。     

Wavelet unfolded partial least squares for near-infrared spectral quantitative analysis of blood and tobacco powder samples

Continuous wavelet transform (CWT) has been shown to be a high-performance signal processing technique in multivariate calibration. However, the signal processed by CWT with a specific wavelet may account for only a part of the information. To effectively utilize more abundant information contained in analytical signals, a method, named as wavelet unfolded partial least squares (WUPLS), was proposed. In the approach, the measured dataset is firstly extended by CWT with different wavelets, and then partial least squares (PLS) is employed to develop the quantitative model between the extended dataset and the target values. In order to select the representative wavelets, principal component analysis (PCA) is used to investigate the distribution of the signals obtained by CWT with different wavelets. The performance of the method was tested with blood and tobacco powder samples. Compared with the results obtained by PLS methods, the WUPLS method combined with signal processing techniques is proven to be a promising tool for improving the near-infrared (NIR) spectral analysis of complex samples.     

Simultaneous quantitative analysis of overlapping spectrophotometric signals using wavelet multiresolution analysis and partial least squares

The mathematical bases and program algorithms of discrete wavelet transform (DWT), multiresolution and Mallat’s pyramid algorithm were described. The multiresolution analysis (MRA) based on Daubechies orthogonal wavelet basis was studied as a tool for removing noise and irrelevant information from spectrophotometric spectra. After wavelet MRA pre-treatment, eight error functions were calculated for deducing the number of factors. A partial least squares based on wavelet MRA (WPLS) method was developed to perform simultaneous spectrophotometric determination of Fe(II) and Fe(III) with overlapping peaks. Data reduction was performed using wavelet MRA and principal component analysis (PCA) algorithm. Two programs, SPWMRA and SPWPLS, were designed to perform wavelet MRA and simultaneous multicomponent determination. Experimental results showed the WPLS method to be successful even where there was severe overlap of spectra.     

荧光光度法同时测定邻苯二酚、间苯二酚与对苯二酚

将一种直接信号校正(DOSC)-小波包变换(WPT)-偏最小二乘法(PLS)(DOSC-WPT-PLS)新方法用于解析荧光光谱严重重叠的邻苯二酚?间苯二酚和对苯二酚混合物,并对其进行测定。该法将DOSC、WPT及PLS 3种方法结合从而提高了获取特征信息的能力和回归质量。DOSC方法用于除去与浓度无关的结构噪音。利用WPT的时域和频域局部化的特点改进了除噪质量和数据压缩及信息提取能力。PLS方法用于多变量校准和噪音消除。处理该3种组分的荧光光谱数据,并实现了3种化合物的同时测定。设计了PDOSCWPTPLS程序执行相关计算,并对以上3种化学计量学方法进行了比较,其总体相对预测标准偏差分别为4.3%、7.7%、11.5%,结果表明DOSC-WPT-PLS法优于WPT-PLS法和PLS法。将该法用于测定自来水中邻苯二酚?间苯二酚和对苯二酚的含量,其回收率分别为99%~110%?95%~108%和98%~104%,结果满意。     

基于组合偏最小二乘的特征波段优选方法在氨、碱化处理玉米秸秆粗蛋白检测中的研究

该文构建了玉米秸秆粗蛋白定量分析模型,并对光谱特征波段选取方法进行探讨及验证。首先对107个样本进行预处理,剔除两个异常样本后采用DB2小波缺省阈值4层分解方式进行光谱重构,预处理后粗蛋白模型交互验证决定系数R2CV从0.788 9提高至0.920 8,采用间隔偏最小二乘(IPLS)及其改进型方法后向区间间隔偏最小二乘(BIPLS)、组合间隔偏最小二乘(SIPLS)进行特征波段选取,并对比主成分分析、竞争性自适应重加权采样法、相关系数法、遗传算法、移动窗口最小二乘等结果,发现基于IPLS及其改进型BIPLS、SIPLS均可有效、准确定位特征波段区间,其中采用SIPLS 30 波段间隔在10 128~10 398 cm-1与11 196~11 462 cm-1时具有最优模型,验证集相关系数(rp)为0.978 4,验正集决定系数(R2P)为0.957 2,验正集均方误差根(RMSEP)为0.221 1,相比于其他波段选取方法表现出较好的实时准确性,该方法可为玉米秸秆氨碱化最优条件判定提供重要的数据支撑。     

Multivariate calibration of spectral data using dual-domain regression analysis

To date, few efforts have been made to take simultaneous advantage of the local nature of spectral data in both the time and frequency domains in a single regression model. We describe here the use of a novel chemometrics algorithm using the wavelet transform. We call the algorithm dual-domain regression, as the regression step defines a weighted model in the time-domain based on the contributions of parallel, frequency-domain models made from wavelet coefficients reflecting different scales. In principle, any regression method can be used, and implementation of the algorithm using partial least squares regression and principal component regression are reported here. The performance of the models produced from the algorithm is generally superior to that of regular partial least squares (PLS) or principal component regression (PCR) models applied to data restricted to a single domain. Dual-domain PLS and PCR algorithms are applied to near infrared (NIR) spectral datasets of Cargill corn samples and sets of spectra collected on batch chemical reactions run in different reactors to illustrate the improved robustness of the modeling.     

A partial least squares and wavelet-transform hybrid model to analyze carbon content in coal using laser-induced breakdown spectroscopy

A partial least squares (PLS) and wavelet transform hybrid model are proposed to analyze the carbon content of coal by using laser-induced breakdown spectroscopy (LIBS). The hybrid model is composed of two steps of wavelet analysis procedures, which include environmental denoising and background noise reduction, to pretreat the LIBS spectrum. The processed wavelet coefficients, which contain the discrete line information of the spectra, were taken as inputs for the PLS model for calibration and prediction of carbon element. A higher signal-to-noise ratio of carbon line was obtained after environmental denoising, and the best decomposition level was determined after background noise reduction. The hybrid model resulted in a significant improvement over the conventional PLS method under different ambient environments, which include air, argon, and helium. The average relative error of carbon decreased from 2.74 to 1.67% under an ambient helium environment, which indicated a significantly improved accuracy in the measurement of carbon in coal. The best results obtained under an ambient helium environment could be partly attributed to the smallest interference by noise after wavelet denoising. A similar improvement was observed in ambient air and argon environments, thereby proving the applicability of the hybrid model under different experimental conditions.     

A consensus least squares support vector regression (LS-SVR) for analysis of near-infrared spectra of plant samples

Consensus modeling of combining the results of multiple independent models to produce a single prediction avoids the instability of single model. Based on the principle of consensus modeling, a consensus least squares support vector regression (LS-SVR) method for calibrating the near-infrared (NIR) spectra was proposed. In the proposed approach, NIR spectra of plant samples were firstly preprocessed using discrete wavelet transform (DWT) for filtering the spectral background and noise, then, consensus LS-SVR technique was used for building the calibration model. With an optimization of the parameters involved in the modeling, a satisfied model was achieved for predicting the content of reducing sugar in plant samples. The predicted results show that consensus LS-SVR model is more robust and reliable than the conventional partial least squares (PLS) and LS-SVR methods.     

Resolution of overlapping signals in spectrometry using a wavelet packet transform and an Elman recurrent neural network

A novel method named a wavelet packet transform based Elman recurrent neural network (WPTERNN) was proposed for the simultaneous UV–visible spectrometric determination of Cu(II), Cd(II) and Zn(II). This method combined wavelet packet denoising with an Elman recurrent neural network. A wavelet packet transform was applied to perform data compression, to extract relevant information, and to eliminate noise and collinearity. An Elman recurrent network was applied for nonlinear multivariate calibration. In this case, using trials, the kind of wavelet function, the decomposition level, and the number of hidden nodes for the WPTERNN method were selected as Daubechies 14, 3, and 8, respectively. A program (PWPTERNN) was designed that could perform the simultaneous determination of Cu(II), Cd(II) and Zn(II). The relative standard errors of prediction (RSEP) obtained for all components using WPTERNN, a Elman recurrent neural network (ERNN), partial least squares (PLS), principal component regression (PCR), Fourier transform based PCR (FTPCR), and multivariate linear regression (MLR) were compared. Experimental results demonstrated that the WPTERRN method was successful even where there was severe overlap of spectra. The results obtained from an additional test case also demonstrated that the WPTERNN method performed very well. Figure The part of WP coefficients obtained by wavelet packet transforms