On the Relationship Between Kováts and Lee Retention Indices

A relationship between the Kováts and Lee retention indices was obtained for dimethylsilicone stationary phase and isothermal conditions. The temperature dependence of the retention indices was taken into account. Based on numerous experimental data for dimethylsilicone stationary phase, parameters of the linear temperature dependence of the Kováts indices were determined for the reference compounds of the Lee scale.     

基于激光诱导击穿光谱(LIBS)的煤灰熔点快速检测

炉内结渣是影响火电机组和气化工艺可靠运行的关键因素之一,准确预测灰熔点可以提前调整炉膛出口温度以避免结渣。本论文采用激光诱导击穿光谱（LIBS）采集煤灰样中金属元素的光谱,分别建立煤灰中的金属元素的谱线强度与煤灰熔点的随机森林模型、支持向量机回归模型和线性回归模型,直接预测煤灰熔点温度。采用基于马氏距离(MD)的异常数据剔除算法和基于稀疏矩阵的基线估计与降噪算法（BEADS）,对粉煤灰样的全光谱数据进行了预处理。随机森林模型对粉煤灰熔点的预测平均相对误差（MRE）为54.74%,支持向量机回归模型的预测平均相对误差为60.08%,而线性回归模型的预测平均相对误差达到了9.78%。研究结果表明,线性回归模型对煤灰熔点的预测结果更准确。     

基于支持向量学习机的HIV-1蛋白酶抑制剂的活性预测

为了预测人体免疫缺陷蛋白酶抑制剂的活性, 计算了表征分子的组成和拓扑特征的462个分子描述符, 用Kennard-Stone方法和随机方法进行了训练集和测试集设计, 用Monte Carlo 模拟退火方法进行变量筛选, 并分别用神经网络, 逻辑回归, k-近邻和支持向量学习机方法建立了HIV-1蛋白酶的抑制剂模型. 结果表明支持向量学习机优于其余机器学习方法, 用SVM方法所建立的最优模型的最后预测正确率达到98.24%.     

Sorting variables by using informative vectors as a strategy for feature selection in multivariate regression

A new procedure with high ability to enhance prediction of multivariate calibration models with a small number of interpretable variables is presented. The core of this methodology is to sort the variables from an informative vector, followed by a systematic investigation of PLS regression models with the aim of finding the most relevant set of variables by comparing the cross‐validation parameters of the models obtained. In this work, seven main informative vectors i.e. regression vector, correlation vector, residual vector, variable influence on projection (VIP), net analyte signal (NAS), covariance procedures vector (CovProc), signal‐to‐noise ratios vector (StN) and their combinations were automated and tested with the main purpose of feature selection. Six data sets from different sources were employed to validate this methodology. They originated from: near‐Infrared (NIR) spectroscopy, Raman spectroscopy, gas chromatography (GC), fluorescence spectroscopy, quantitative structure‐activity relationships (QSAR) and computer simulation. The results indicate that all vectors and their combinations were able to enhance prediction capability with respect to the full data sets. However, regression and NAS informative vectors from partial least squares (PLS) regression, both built using more latent variables than when building the model presented in most of tested data sets, were the best informative vectors for variable selection. In all the applications, the selected variables were quite effective and useful for interpretation. Copyright © 2008 John Wiley & Sons, Ltd.     

Determination of Parameter Uncertainty for Quantitative Analysis of Shaddock Peel Pectin using Linear and Nonlinear Near-infrared Spectroscopic Models

Fourier transform near-infrared spectrometry has been used in combination with multivariate chemometric methods for wide applications in agriculture and food analysis. In this paper, we used linear partial least square and nonlinear least square support vector machine regression methods to establish calibration models for Fourier transform near-infrared spectrometric determination of pectin in shaddock peel samples. In particular, the tunable kernel parameters of the linear and nonlinear models were set changing in a moderate range and were optimally selected in conjunction with a Savitzky–Golay smoother. The smoothing parameters and the linear/nonlinear modeling parameters were combined for simultaneous optimization. To investigate the robustness of calibration models, parameter uncertainty were estimated in a direct way for the optimal linear and nonlinear models. Our results show that the nonlinear least square support vector machine method gives more accurate predictive results and is substantially more robust compared to the spectral noise when compared with the linear partial least square regression. Furthermore, the optimized least square support vector machine model was evaluated by the randomly selected test samples and the model test effect was much satisfactory. We anticipate that these linear and nonlinear methods and the methodology of determination of model parameter uncertainty will be applied to other analytes in the fields of near-infrared or Fourier transform near-infrared spectroscopy.     

基于支撑向量机方法的有机化合物的生成Gibbs自由能的预测

基于支撑向量机方法的有机化合物的生成Gibbs自由能的预测;支撑向量机;多元线形回归;吉布斯自由能     

Characterization of Peanut Oil by Infrared Spectroscopy with an Improved Gaussian Mixture Model

The Gaussian mixture model (GMM) and regression (GMR) are widely used statistical tools in pattern classification and nonlinear regression. In this paper, the suitability score was used for variable selection to improve GMM and GMR. The improved GMM was used to characterize peanut oil adulterated with palm oil using Fourier transform infrared spectroscopy. The improved GMR was applied to determine the concentration of palm oil contaminant present. As comparison, GMM and GMR with principal component analysis for feature extraction, support vector machine, back-propagation artificial neural network, nearest centroid classification, and partial least-squares analysis were also used to classify and quantify peanut oil. It was demonstrated that the method is a new classification and regression strategy for the detection of adulterated edible oil.     

多环芳香硫化合物的定量结构-气相色谱保留指数关系

应用分子电性距离矢量(MEDV)对114个多环芳香硫化合物(PASHs)进行结构表征,通过多元线性回归建立了PASHs的气相色谱保留指数与MEDV参数之间的定量结构-保留值关系模型;同时采用逐步回归分析进行变量筛选,继而以留一法交互检验对所得优化模型进行预测能力评价,所建立的模型的相关系数为0.9947,交互检验相关系数为0.9940,表明该优化模型具有良好的稳定性和预测能力。此外,通过将样本集按2:1分成校准集和测试集预测,统计分析结果显示所建的模型具有良好的相关性和稳定性。本文所建的定量结构-保留值关系(QSRR)模型为预测PASHs的气相色谱保留指数提供了一个便捷有效的新方法。     

基于QSAR模型的有机磷化合物毒性预测

随着有机磷化合物(OPs)的广泛应用,其在越来越多的环境介质中被检测出来。大多数OPs具有毒性,但人们缺乏快速且有效的预测手段来对毒性进行评估。本文将结合E-Dragon软件计算的分子描述符,采用不同的QSAR模型对36个OPs的毒性进行预测。文中采用后退法作为描述符筛选方法,以均方根误差(RMSE)作为评价标准,共找到14个对线性核函数支持向量机(SVM)模型贡献较大的描述符;在最终得到的SVM模型交叉验证结果中,计算值与实际值的相关系数为0. 913,均方根误差为0. 388;外部测试验证结果中,平均相对误差为9. 10%。此外,采用多元线性回归(MLR)、人工神经网络(ANN)以及偏最小二乘回归(PLS)模型对OPs的毒性进行预测,交叉验证结果显示,三个模型的计算值与实际值的相关系数分别为0. 878、0. 686与0. 620,没有SVM模型的预测能力好。因此采用线性核函数的SVM模型对OPs进行毒性预测是一个行之有效的方法。