粒子群算法结合支持向量机回归法用于近红外光谱建模

研究了最小二乘法支持向量机(LSSVM)应用于烟丝样品和小麦样品的近红外光谱建模,采用粒子群优化算法(PSO)优化LSSVM的参数。通过对烟草样品和小麦样品的近红外光谱建模和预测,并与常规的偏最小二乘法(PLS)比较发现,PSO-LSSVM法具有更好的预测效果和稳健性。     

Geographic Characterization of Leccinum rugosiceps by Ultraviolet and Infrared Spectral Fusion

Leccinum rugosiceps is an edible mushroom belonging to genus Leccinum of Boletaceae. Its fruiting bodies are richer in nutrients than many vegetables and fruit. The model of support vector machine was established for the discrimination of L. rugosiceps from regions based on rapid and low-cost ultraviolet and infrared spectroscopies. The mid-level data fusion was performed by support vector machine. Compared to a single spectroscopic technique, mid-level data fusion provided higher accuracy by selecting the most significant variance from data matrixes based on partial least squares discriminant analysis. The accuracy of the classification of samples in the calibration and test sets were 85.00 and 94.74%, higher than separate measurements by ultraviolet or infrared spectroscopy. This approach has applications for authentication and quality assessment of L. rugosiceps.     

Characterization of Gentiana rigescens by Ultraviolet–Visible and Infrared Spectroscopies with Chemometrics

Gentiana rigescens is a medicinal plant for treatment of rheumatism, convulsions, and jaundice. The present paper reports the potential for chemometric characterization of G. rigescens using ultraviolet–visible and infrared spectroscopies, individually and together. Low- and mid-level data fusions were considered in this study. Partial least square discriminant analysis and support vector machine were used to analyze single and fused spectral data, respectively. The data fusion strategy improved the classification capacity. In particular, the mid-level data fusion provided the best results by selecting important variance from the data matrixes, with 100% correct classification of test samples by partial least square discriminant analysis and support vector machine characterization. The results demonstrated that the combined use of ultraviolet–visible and infrared spectroscopies is more suitable for the discrimination of G. rigescens than the individual methods.     

Correlation Studies of <Emphasis Type="Italic">HEPT</Emphasis> Derivatives Using Swarm Intelligence and Support Vector Machines

Summary. Two novel algorithms based on particle swarm optimization (PSO) and support vector machine (SVM) have been employed to obtain predictive QSAR models of anti-HIV-1 activity of HEPT derivatives. The results obtained by using the adopted PSO and SVM for structure-activity correlation determination were in close agreement with previous multiple linear regression models, which are reasonably satisfying, based on both statistical significance and predictive ability.     

Correlation Studies of HEPT Derivatives Using Swarm Intelligence and Support Vector Machines

Two novel algorithms based on particle swarm optimization (PSO) and support vector machine (SVM) have been employed to obtain predictive QSAR models of anti-HIV-1 activity of HEPT derivatives. The results obtained by using the adopted PSO and SVM for structure-activity correlation determination were in close agreement with previous multiple linear regression models, which are reasonably satisfying, based on both statistical significance and predictive ability.     

A wavelength selection method based on random decision particle swarm optimization with attractor for near‐infrared spectral quantitative analysis

In this paper, we proposed a wavelength selection method based on random decision particle swarm optimization with attractor for near‐infrared (NIR) spectra quantitative analysis. The proposed method was incorporated with partial least square (PLS) to construct a prediction model. The proposed method chooses the current own optimal or the current global optimal to calculate the attractor. Then the particle updates its flight velocity by the attractor, and the particle state is updated by the random decision with the new velocity. Moreover, the root‐mean‐square error of cross‐validation is adopted as the fitness function for the proposed method. In order to demonstrate the usefulness of the proposed method, PLS with all wavelengths, uninformative variable elimination by PLS, elastic net, genetic algorithm combined with PLS, the discrete particle swarm optimization combined with PLS, the modified particle swarm optimization combined with PLS, the neighboring particle swarm optimization combined with PLS, and the proposed method are used for building the components quantitative analysis models of NIR spectral datasets, and the effectiveness of these models is compared. Two application studies are presented, which involve NIR data obtained from an experiment of meat content determination using NIR and a combustion procedure. Results verify that the proposed method has higher predictive ability for NIR spectral data and the number of selected wavelengths is less. The proposed method has faster convergence speed and could overcome the premature convergence problem. Furthermore, although improving the prediction precision may sacrifice the model complexity under a certain extent, the proposed method is overfitted slightly. Copyright © 2015 John Wiley & Sons, Ltd.     

基于粒子群算法的最小二乘支持向量机在红花提取液近红外定量分析中的应用

提出一种基于粒子群算法的最小二乘支持向量机(PSO-LS-SVM)方法,用于建立红花提取过程关键质控指标的定量分析模型.近红外光谱数据经波段选择、预处理和主成分分析(降维)后,利用粒子群优化(PSO)算法对最小二乘支持向量机算法中的参数进行优化,然后使用最优参数建立固含量和羟基红花黄色素A(HSYA)浓度的定量校正模型.将校正结果与偏最小二乘法回归(PLSR)和BP神经网络(BP-ANN)比较,并将所建的3个模型用于红花提取过程未知样本的预测.结果表明,BP-ANN校正结果优于PSO-LS-SVM和PLSR,但是对验证集和未知样品集的预测能力较差,而PSO-LS-SVM和PLSR模型的校正、验证结果相近,相关系数均大于0.987,RMSEC和RMSEP值相近且小于0.074,RPD值均大于6.26,RSEP均小于5.70％.对于未知样品集,pSO-LS-SVM模型的RPD值大于8.06,RMSEP和RSEP值分别小于0.07％和5.84％,较BP-ANN和PLSR模型更低.本研究所建立的PSO-LS-SVM模型表现出较好的模型稳定性和预测精度,具有一定的实践意义和应用价值,可推广用于红花提取过程的近红外光谱定量分析.     

Biodiesel classification by base stock type (vegetable oil) using near infrared spectroscopy data

The use of biofuels, such as bioethanol or biodiesel, has rapidly increased in the last few years. Near infrared (near-IR, NIR, or NIRS) spectroscopy (>4000 cm⁻¹) has previously been reported as a cheap and fast alternative for biodiesel quality control when compared with infrared, Raman, or nuclear magnetic resonance (NMR) methods; in addition, NIR can easily be done in real time (on-line). In this proof-of-principle paper, we attempt to find a correlation between the near infrared spectrum of a biodiesel sample and its base stock. This correlation is used to classify fuel samples into 10 groups according to their origin (vegetable oil): sunflower, coconut, palm, soy/soya, cottonseed, castor, Jatropha, etc. Principal component analysis (PCA) is used for outlier detection and dimensionality reduction of the NIR spectral data. Four different multivariate data analysis techniques are used to solve the classification problem, including regularized discriminant analysis (RDA), partial least squares method/projection on latent structures (PLS-DA), K-nearest neighbors (KNN) technique, and support vector machines (SVMs). Classifying biodiesel by feedstock (base stock) type can be successfully solved with modern machine learning techniques and NIR spectroscopy data. KNN and SVM methods were found to be highly effective for biodiesel classification by feedstock oil type. A classification error (E) of less than 5% can be reached using an SVM-based approach. If computational time is an important consideration, the KNN technique (E = 6.2%) can be recommended for practical (industrial) implementation. Comparison with gasoline and motor oil data shows the relative simplicity of this methodology for biodiesel classification.     

Prediction of wood property in Chinese Fir based on visible/near-infrared spectroscopy and least square-support vector machine

A method for the quantification of density of Chinese Fir samples based on visible/near-infrared (vis–NIR) spectrometry and least squares-support vector machine (LS-SVM) was proposed. Sample set partitioning based on joint x–y distances (SPXY) algorithm was used for dividing calibration and prediction samples, it is of value for prediction of property involving complex matrices. A stepwise procedure is employed to select samples according to their differences in both x (instrumental responses) and y (predicted parameter) spaces. For comparison, the models were also constructed by Kennard–Stone method, as well as by using the duplex and random sampling methods for subset partitioning. The results revealed that the SPXY algorithm may be an advantageous alternative to the other three strategies. To validate the reliability of LS-SVM, comparisons were made among other modeling methods such as support vector machine (SVM) and partial least squares (PLS) regression. Satisfactory models were built using LS-SVM, with lower prediction errors and superior performance in relation to SVM and PLS. These results showed possibility of building robust models to quantify the density of Chinese Fir using near-infrared spectroscopy and LS-SVM combined SPXY algorithm as a nonlinear multivariate calibration procedure.     

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.     

Characterization of Paris polyphylla var. yunnanensis by Infrared and Ultraviolet Spectroscopies with Chemometric Data Fusion

Paris polyphylla var. yunnanensis has been used for its anti-tumor, anthelmintic, and hemostatic properties. In this investigation, Fourier transform infrared and ultraviolet spectroscopy combined with chemometrics were used for qualitative analysis of P. polyphylla var. yunnanensis from different geographical origins in Yunnan Province. A total of 82 samples for each region were divided into 57 in the calibration set and 25 in the validation set by Kennard–Stone algorithm. Support vector machine and partial least square discrimination on the basis of Fourier transform infrared, ultraviolet, and low- and mid-level data fusion were investigated. Different pretreatments were compared for the appropriate model. The results indicated that the combination of Savitzky–Golay (11 points), second derivative, and standard normal variation has the best performance for support vector machine and partial least square discrimination with the lowest root mean square error of estimation and root mean square error of cross validation and the highest cross validation accuracy rate. The accuracies of calibration and validation for mid-level data fusion in the model of support vector machine were 84.21 and 96% for the partial least square discrimination values of 96.49 and 84%, which was better performance than a single technique or low-level data fusion for the classification. Moreover, the chemical information of sample collected from Kunming and Xishuangbanna was distinguishable from the others. These results provide a rapid and robust strategy for quality control of P. polyphylla var. yunnanensis for further analysis.     

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.     

Determination of Fipronil in Acetamiprid Formulation by Attenuated Total Reflectance-Mid-Infrared Spectroscopy Combined with Partial Least Squares Regression

There is a high demand for rapid determination of fipronil in pesticide preparations because it has been restricted and even prohibited in many countries. An infrared-based methodology was developed for this analyte in acetamiprid formulations by attenuated total reflectance mid-infrared spectroscopy. The quantitative calibration models of fipronil were established by partial least squares regression. The determination coefficients (R²) of the model were above 0.99 while both the root mean square error of prediction and root mean square error of calibration were below 0.0011, which showed the partial least squares model accurately predicted fipronil concentrations in acetamiprid. The accuracy was further demonstrated by comparison with another two models' results of low (<1.0%, w/w) and high concentration sample sets (1.0%–4.5%, w/w). These results demonstrate the potential of infrared spectroscopy to quickly detect fipronil in acetamiprid.     

Discrimination of Scrophulariae Radix according to geographical origin and determination of active constituents by near infrared spectroscopy (NIRS)

The potential of near infrared reflectance spectroscopy (NIR) was investigated for its ability to non-destructively discriminate the geographic origins of Scrophularia spp., Andong, Uisung and China. Application of principal component analysis to NIR spectra leads to a clear separation of Andong sample from the others. Moreover, the contents of two neuroprotective constituents of Scrophularia spp., 8-O-(E-p-methoxycinnamoyl)-harpagide (HG), and E-p-methoxycinnamic acid (MCA), were determined by HPLC-DAD. Partial least squares (PLS) regression of NIR spectra combined with these analytical reference data yield the development of calibration models for the contents of the two constituents. The correlation coefficients of prediction models for HG and MCA were > 0.87. These outcomes indicated that the NIRS could be useful for the discrimination of Scrophularia spp.     

Near-infrared spectroscopic determination of human serum albumin, γ-globulin, and glucose in a control serum solution with searching combination moving window partial least squares

Near-infrared (NIR) spectra in the region of 5000-4000 cm⁻¹ with a chemometric method called searching combination moving window partial least squares (SCMWPLS) were employed to determine the concentrations of human serum albumin (HSA), γ-globulin, and glucose contained in the control serum IIB (CS IIB) solutions with various concentrations. SCMWPLS is proposed to search for the optimized combinations of informative regions, which are spectral intervals, considered containing useful information for building partial least squares (PLS) models. The informative regions can easily be found by moving window partial least squares regression (MWPLSR) method. PLS calibration models using the regions obtained by SCMWPLS were developed for HSA, γ-globulin, and glucose. These models showed good prediction with the smallest root mean square error of predictions (RMSEP), the relatively small number of PLS factors, and the highest correlation coefficients among the results achieved by using whole region and MWPLSR methods. The RMSEP values of HSA, γ-globulin, and glucose yielded by SCMWPLS were 0.0303, 0.0327, and 0.0195 g/dl, respectively. These results prove that SCMWPLS can be successfully applied to determine simultaneously the concentrations of HSA, γ-globulin, and glucose in complicated biological fluids such as CS IIB solutions by using NIR spectroscopy.     

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.     

Classification of Rhizoma et Radix Notoperygii by HPLC Fingerprints with the Aid of Chemometrics

Chromatographic profiles of Rhizoma et Radix Notoperygii (RRN, “Qianghuo” in Chinese), a complex traditional Chinese medicine (TCM), were collected by high-performance liquid chromatography with diode array detection (HPLC-DAD) at 330 nm. These data profiles were used as fingerprints to investigate quality control classification modeling of the RRN samples. In contrast to the classical methods for discrimination of TCMs, that is, just using common HPLC peaks, all chromatographic profile data were pre-processed by the correlation optimized warping method and polynomial functions; then, these data were submitted as fingerprints (variables) for classification on the basis of sample origin. Chemometrics methods used for calibration modeling and subsequent sample classification-least square support vector machine (LS-SVM), artificial neural network (ANN), and partial least square discriminant analysis (PLS-DA); all produced satisfactory calibrations as well as classification results.     

基于近红外光谱的食用植物油中反式脂肪酸含量快速定量检测及模型优化研究

利用近红外光谱技术对食用植物油中反式脂肪酸(Trans fatty acids,TFA)含量进行快速定量检测,并通过波段选择、预处理方法、变量筛选及建模方法对TFA含量预测模型进行优化.采用AntarisⅡ傅里叶变换近红外光谱仪在4000~10000 cm-1光谱范围采集98个食用植物油样本的近红外透射光谱,然后采用气相色谱法测定TFA的真实含量.首先,对样本原始光谱进行波段、预处理方法优选;在此基础上,采用竞争自适应重加权法(Competitive adaptive reweighted sampling,CARS)筛选TFA相关的重要变量,最后应用主成分回归、偏最小二乘和最小二乘支持向量机方法分别建立食用植物油中TFA含量的预测模型.研究结果表明,近红外光谱技术检测食用植物油中的TFA含量是可行的,优化后的最佳预测模型的校正集和预测集R2分别为0.992和0.989,RMSEC和RMSEP分别为0.071%和0.075%.最佳预测模型所用的变量仅26个,占全波段变量的0.854%.此外,与全波段偏最小二乘预测模型相比,其预测集R2由0.904上升为0.989,RMSEP由0.230%下降为0.075%.由此表明,模型优化非常必要,CARS能有效筛选TFA相关的重要变量,极大减少建模变量数,从而简化预测模型,并较大提高预测模型的精度和稳定性.     

Classification and quantification analysis of Radix scutellariae from different origins with near infrared diffuse reflection spectroscopy

A rapid near infrared spectroscopy analysis method was developed for the geographical origin discrimination and content determination of Radix scutellariae, a kind of Traditional Chinese Medicine (TCM). 81 R. scutellariae samples from six different origins were analyzed with HPLC-UV as reference method. The NIR spectra were collected in integrating-sphere diffused reflection mode and processed with different spectra pretreated methods. Discriminant analysis (DA) and discriminant partial least squares (DPLS) were applied to classify the geographical origins of those samples, and the latter had a better predictive ability with 100% accuracy after two exceptional samples eliminated from the calibration set. For the quantitative calibration, the samples were divided into calibration set and validation set by Kennard-Stone algorithm. The models of baicalin, wogonoside, baicalein, wogonin were established with partial least squares (PLS) algorithm and the optimal principal component (PC) numbers were selected with Leave-One-Out (LOO) cross-validation. The established models were evaluated with the root mean square error of prediction (RMSEP) and corresponding correlation coefficients. The correlation coefficients of all the four calibration models are above 0.920, and the RMSEPs of baicalin, wogonoside, baicalein and wogonin are 0.752%, 0.094%, 0.418% and 0.139%, respectively. This research indicated that the NIR diffuse reflection spectroscopy could be used for the rapid analysis of R. scutellariae, which is beneficial to the quality control of this raw material in TCM pharmaceutical factory, and will also help to solve analogous problems.