毛细管电泳径向基神经网络校正法定量分析核苷

采用径向基神经网络算法对一组已知样品的核苷及内标物浓度与毛细管电泳峰面积数据进行回归计算,建立峰面积与核苷浓度之间的关系模型,对未知样品中待测核苷浓度作出预测,形成了毛细管电泳定量分析新方法．将其用于鸟嘌呤核苷含量测定,所建模型预测结果平均相对误差为0．86％,明显低于线性回归及BP神经网络模型的2．60％和1．07％．研究结果表明,本方法简便易用,能有效提高毛细管电泳定量分析的准确度,优于线性回归及BP神经网络法．     

基于启发式方法和支持向量机方法预测有机物的热导率

构建147个有机物分子结构与其热导率值之间的定量结构-性质关系(QSPR)模型, 探讨影响有机物热导率的结构因素. 以147个化合物作为样本集, 随机选择118个作为训练集, 29个作为测试集. 应用CODESSA软件计算了组成、拓扑、几何、静电和量子化学等描述符, 通过启发式方法(HM)筛选得到5个结构参数并建立线性回归模型; 用所选5个结构参数作为支持向量机(SVM)的输入, 建立非线性的支持向量机回归模型. 预测结果表明: 支持向量机回归模型的性能(复相关系数R²=0.9240)虽略低于启发式回归模型的性能(R²=0.9267), 但是支持向量机方法预测性能(R²=0.9682)高于启发式方法的预测性能(R²=0.9574), 对于QSPR模型来说, 预测性能更重要. 因此, 总体来说支持向量机方法优于启发式方法. 支持向量机方法和启发式方法的提出为工程上提供了一种根据分子结构预测有机物热导率的新方法.     

基于最小二乘支持向量机的色谱指纹图谱预测银杏叶总抗氧化活性

在色谱图基线校正和色谱峰匹配基础上,提出以40个银杏叶提取物HPLC指纹图谱的色谱图轮廓作为输入,相应的提取物总抗氧化活性作为输出,建立最小二乘支持向量机回归模型,并对包含10个样本的测试集进行了预测.最小二乘支持向量机的测试集预测误差均方根(RMSEP)为0.0230,预测结果优于目前普遍使用的误差反向传播神经网络和偏最小二乘回归.与采用色谱峰面积为分析变量的模型预测结果比较表明:采用消除干扰后的色谱图全谱轮廓保留了样本的全部信息,预测结果更好     

支持向量机分类和回归用于肽的QSAR研究

使用支持向量机技术对两类肽化合物体系进行了分类和回归研究,并将其系统地与K最邻近法、多元线性回归、偏最小二乘、人工神经网络进行了比较。结果表明,对于小样本、非线性问题,支持向量机具有较强的稳定性能及泛化能力,在大多数情况下能够得到优于传统方法的建模效果。对于分类问题,支持向量机对训练集和测试集都达到了100%的分类正确率;对于回归问题,支持向量机虽对训练集样本拟合效果略低于人工神经网络,但对外部测试集却表现出较强的预测能力。     

基于机器学习方法的丙型肝炎病毒聚合酶NS5B非核苷抑制剂的定量构效关系研究

对89 个苯并异噻唑和苯并噻嗪类丙型肝炎病毒(HCV) NS5B聚合酶非核苷抑制剂进行了定量构效关系(QSAR)研究. 采用遗传算法组合偏最小二乘(GA-PLS)和线性逐步回归分析(LSRA)两种特征选择方法选择最优描述符子集, 然后建立多元线性回归和偏最小二乘线性回归模型. 并首次尝试使用遗传算法耦合支持向量机方法(GA-SVM)对两种特征选择方法所选的描述符子集分别建立非线性支持向量机回归模型. 三种机器学习方法所建模型均得到比较满意的预测效果. 采用LSRA所选的6 个描述符建立的三个QSAR模型对于测试集的相关系数为0.958-0.962, GA-SVM法给出最好的预测精度(0.962). 采用GA-PLS所选的7个描述符建立的三个QSAR模型对于测试集的相关系数为0.918-0.960, 偏最小二乘回归模型的结果最好(0.960). 本工作提供了一种有效的方法来预测丙型肝炎病毒抑制剂的生物活性, 该方法也可以扩展到其他类似的定量构效关系研究领域.     

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。     

基于机器学习模型的改性双基推进剂的燃速预测

在分析了改性双基推进剂不同成分含量对其燃速性能影响的基础上,使用机器学习方法建立了以推进剂成分含量及压强为输入变量,推进剂燃速值为输出的预测模型。通过以相关系数(R~2)、均方根误差(RMSE)以及平均绝对误差(MAE)作为模型的性能评价指标,比较了不同机器学习方法的预测性能,包括随机森林、支持向量回归、极限梯度提升、人工神经网络、多元线性回归、偏最小二乘回归和K最近邻回归。结果表明,以多项式内积(Poly)为核函数的支持向量回归(Support Vector Regression, SVR)模型的预测效果最优,其模型的留一法交叉验证结果令人满意,R~2、RMSE、MAE分别为0.9927、0.5553、0.4033。最后,为进一步验证模型的准确性、稳定性,我们分别采用5折、10折交叉验证与留一法进行结果比较,并绘制模型的学习曲线。结果证实模型稳定可靠,过拟合程度低,可实现对改性双基推进剂燃速的准确预测,可为具有优越性能的推进剂配方设计与优化提供理论指导。     

二维色谱柱效的支持向量回归预测

以有效塔板数作为二维色谱的柱效指标,根据二维色谱在不同影响因素(包括预柱柱温、主柱柱温、柱间压差和主柱间的放空量)下的有效塔板数实测数据集,应用基于粒子群算法(PSO)寻优的支持向量回归(SVR)方法,建立了二维色谱柱效的SVR预测模型,并与BP神经网络(BPNN)模型进行了比较.结果表明:基于相同的训练样本和检验样本,二维色谱的SVR模型的平均绝对百分误差(MAPE, 13.3%)比其BPNN模型的MAPE小4%;增加训练样本数有助于提高支持向量回归(SVR)模型的泛化性能;基于留一交叉验证法(LOOCV)的SVR模型预测的平均绝对误差(MAE, 196.79 m-1)和MAPE(1.6%)均为最小,明显优于BPNN模型(2397.98 m-1, 17.3%)或SVR模型(1849.95 m-1, 13.3%)的预测效果.因此,SVR是一种预测二维色谱柱效的有效方法.     

支持向量回归建立成品汽油通用近红外校正模型的研究

针对目前采用偏最小二乘法建立成品汽油分析模型存在的问题,采用近几年新兴的支持向量回归方法建立了多种汽油标号通用的校正模型,其预测能力优于对应的偏最小二乘法,对汽油研究法辛烷值、烯烃和芳烃的预测标准偏差分别为0.37、1.28%和1.38%,可应用于实际的汽油管道自动调合近红外光谱在线分析.     

中药材三七提取液近红外光谱的支持向量机回归校正方法

提出近红外光谱的支持向量机回归校正建模方法.以中药材三七渗漉提取液为实际分析对象,对其近红外光谱数据进行预处理和主成分分析后,用支持向量机回归算法建立人参皂苷R_g1,R_b1和R_d以及三七总皂苷的近红外光谱校正模型.以R_g1,R_b1和R_d的HPLC测定值及三七总皂苷的比色法测定值为参照,将本文方法与偏最小二乘回归和径向基神经网络建模方法相比较,结果表明,本文所建模型的预测准确性优于后两者,可推广应用于中药提取过程的近红外光谱分析.     

Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk

This paper proposes the use of the least-squares support vector machine (LS-SVM) as an alternative multivariate calibration method for the simultaneous quantification of some common adulterants (starch, whey or sucrose) found in powdered milk samples, using near-infrared spectroscopy with direct measurements by diffuse reflectance. Due to the spectral differences of the three adulterants a nonlinear behavior is present when all groups of adulterants are in the same data set, making the use of linear methods such as partial least squares regression (PLSR) difficult. Excellent models were built using LS-SVM, with low prediction errors and superior performance in relation to PLSR. These results show it possible to built robust models to quantify some common adulterants in powdered milk using near-infrared spectroscopy and LS-SVM as a nonlinear multivariate calibration procedure.     

支持向量回归同时测定维生素B混合物的研究

用支持向量回归方法(SVR)建立校正模型,并对维生素B1、B2和B6的模拟样品进行测定。结果表明,维生素B1、B2和B6预测结果的回收率在96%~104%之间,测定结果准确。     

Random subspace regression ensemble for near-infrared spectroscopic calibration of tobacco samples.

An ensemble, a model-independent technique based on combining several models for classification/regression tasks, allows us to achieve a high accuracy that is often not achievable with single models. Such combinations have gained increasing attention in many fields. This paper proposes the use of random subspace (RS)-based regression ensemble as an alternative method for near-infrared (NIR) spectroscopic calibration of tobacco samples. Because of the considerable reduction of variables in a random subspace, multiple linear regression (MLR) is used as the base algorithm and the method is therefore also referred to as RS-MLR. The overall performance of the proposed RS-MLR method is compared to those of partial least square regression (PLSR), kernel principal component regression (KPCR) and kernel partial least square regression (KPLSR). The results reveal that the RS-MLR method not only has a simple concept but also can produce a more parsimonious and more accurate calibration model than PLSR, KPCR and KPLSR, at a lower computational cost. Besides, we also found that the RS-MLR method is very appropriate for the so-called small sample problems and that the calibration models built by RS-MLR are less sensitive to overfitting.     

Application of genetic algorithm‐support vector regression (GA‐SVR) for quantitative analysis of herbal medicines

In this paper, a genetic algorithm‐support vector regression (GA‐SVR) coupled approach was proposed for investigating the relationship between fingerprints and properties of herbal medicines. GA was used to select variables so as to improve the predictive ability of the models. Two other widely used approaches, Random Forests (RF) and partial least squares regression (PLSR) combined with GA (namely GA‐RF and GA‐PLSR, respectively), were also employed and compared with the GA‐SVR method. The models were evaluated in terms of the correlation coefficient between the measured and predicted values (Rp), root mean square error of prediction, and root mean square error of leave‐one‐out cross‐validation. The performance has been tested on a simulated system, a chromatographic data set, and a near‐infrared spectroscopic data set. The obtained results indicate that the GA‐SVR model provides a more accurate answer, with higher Rp and lower root mean square error. The proposed method is suitable for the quantitative analysis and quality control of herbal medicines. Copyright © 2012 John Wiley & Sons, Ltd.     

Suppression of electroosmotic flow and its application to determination of electrophoretic mobilities in a poly(vinylpyrrolidone)-coated capillary

A hydrophilic polymer, poly(vinylpyrrolidone) (PVP), was employed for suppressing the electroosmotic flow (EOF). A capillary was filled with aqueous PVP solution for coating the capillary wall with PVP; the PVP solution was then replaced by a migration buffer solution containing no PVP. Three types of PVP with different molecular weights were examined. The EOF was suppressed more effectively as the molecular weight of PVP increased. The EOF in the coated capillary was approximately 10-fold smaller than that of a bare capillary and was constant in the pH range of 6-8. The suppressed EOF was stable even when no PVP was added to the migration buffer. However, the EOF increased significantly when sodium dodecyl sulfate was added into the migration buffer. The method was applied for determining the electrophoretic mobilities of inorganic anions that have negative electrophoretic mobilities larger than the electroosmotic mobility of the bare capillary. A novel method for determining the electrophoretic mobilities was proposed based on the linear relationship between electric current and electrophoretic mobility. The electrophoretic mobility was proportional to the electric current. Therefore, the intercept of the regression equation represents the electrophoretic mobility at room temperature. The electrophoretic mobilities were in good agreement with the absolute electrophoretic mobilities.     

Protein and peptide mobility in capillary zone electrophoresis : A comparison of existing models and further analysis

Capillary zone electrophoresis of peptide fragments from the tryptic digest of human recombinant insulin-like growth factor I (rhIGF-I) has been carried out and the observed mobilities used to compare the relative applicability of existing mobility models. In addition, the physical forces affecting electromigration have been systematically analyzed in order to more accurately describe the physical chemistry involved. Such an approach should further improve the ability to predict electrophoretic mobility in capillary zone electrophoresis.     

Support vector regression and ANN approach for predicting the ground water quality

The current study investigates the potential of well-known artificial neural network (ANN), Support vector regression (SVR), multilinear and multi-nonlinear regression techniques to predict total dissolve solids (TSO) and electrical conductivity (ECO), which are essential water quality indicators. To develop the anticipated models, seven effective parameters: Ca²⁺ Mg²⁺ Na⁺ Cl^- SO₄^2- HCO₃^- and pH were used as input variables. The external validation criteria were employed to address the modeling overfitting. The outcome of the study demonstrated a strong association between experimental and models predicted data. The coefficient of determination was 0.97, 0.96, 0.92, and 0.94 for SVR, ANN, MLR, and MNLR models, respectively. The lowest error value of 5.37 and 7.92 was attained by SVR model for training and testing data, respectively. Performance of the proposed techniques showed relative dominance of SVR compared to ANN, MLR and MNLR. Sensitivity analysis demonstrated that the HCO₃^- is the most sensitive parameter for both TSO and ECO followed by Cl^- and SO₄^2-. The models assessment on external criteria ensured generalized results. Conclusively, the outcome of the present research indicated that formulation of machine learning models for prediction of water quality parameters are cost effective and helpful in river water quality assessment, management and policy making.     

Combining of intelligent models through committee machine for estimation of wax deposition

Deposition of the wax is one of the thorny issues in the petroleum industry, invoking costly problems during the transportation and production of crude oil. Owing to its devastating impacts on oil companies' economy, it is essential to develop a simple and robust strategy for the quantitative estimation of wax deposition. In this paper, support vector regression (SVR) is first proposed to estimate the amount of wax deposition. Subsequently, an artificial neural network (ANN) is developed for wax deposition prediction. Eventually, a sophisticated committee machine (CM) is constructed for combining the results of the SVR and ANN models. Optimal contribution of each model in final prediction of the wax deposit is determined through genetic algorithm in CM. Statistical error analysis shows that the CM model performs better than the individual models performing alone.