A novel model selection strategy using total error concept

Wu, Zhisheng; Ma, Qun; Lin, Zhaozhou; Peng, Yanfang; Ai, Lu; Shi, Xinyuan; Qiao, Yanjiang

doi:10.1016/j.talanta.2012.12.057

Cited by 19 publications

(16 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The subinterval combination was selected on the basis of the combination of high accuracy of the joint model and a low RMSECV value. For the extraction of APIs, the optimal parameters of the SiPLS model were taken from the literature [ 25 ]. Each optimal SiPLS model was built by a combination of three subintervals taken from 20 equidistant subintervals.…”

Section: Resultsmentioning

confidence: 99%

Online near-infrared analysis coupled with MWPLS and SiPLS models for the multi-ingredient and multi-phase extraction of licorice (Gancao)

et al. 2015

Self Cite

View full text Add to dashboard Cite

BackgroundThis study aims to analyze the active pharmaceutical ingredients (APIs) of licorice (Radix Glycyrrhizae; gancao), including glycyrrhizic acid, liquiritin, isoliquiritin and total flavonoids, in multi-ingredient and multi-phase extraction by online near-infrared technology with fiber optic probes and chemometric analysis.MethodsHigh-performance liquid chromatography and ultraviolet spectrophotometry determined the APIs content in different extraction phases by online near-infrared analysis, which included sample set selection by the Kennard–Stone algorithm, optimization of spectral pretreatment methods (i.e., orthogonal signal correction and wavelet denoising spectral correction), and model calibration by the partial least-squares algorithm, moving-window partial least-squares algorithm and synergy interval partial least-squares (SiPLS) algorithm. The relative errors and F values were used to assess the models in different extraction phases.ResultsThe root-mean-square error of correction, root-mean-square error of cross-validation and root-mean-square error of prediction of APIs in the SiPLS model was less than 0.07. The F values of glycyrrhizic acid, liquiritin, isoliquiritin and total flavonoids were 10,765, 32,431, 649 and 6080, respectively, which were larger than 6.90 (P < 0.01).ConclusionThe study demonstrated the feasibility of online NIR analysis in the multi-ingredient and multi-phase extraction of APIs from licorice.Electronic supplementary materialThe online version of this article (doi:10.1186/s13020-015-0069-2) contains supplementary material, which is available to authorized users.

show abstract

Section: Resultsmentioning

confidence: 99%

Online near-infrared analysis coupled with MWPLS and SiPLS models for the multi-ingredient and multi-phase extraction of licorice (Gancao)

et al. 2015

Self Cite

View full text Add to dashboard Cite

show abstract

“…mwPLS is a variable selection technique based on all continuous windows size "H" in the spectral data set. The RMSECV value of cross-validation was further used to find the best spectral region(s) of size H. Detail descriptions about iPLS and mwPLS theory and algorithms were reported in our previous references [8,9]. iPLS model performance did not perform significantly better than the full-spectrum PLS model in either of the two sampling modes (results not shown).…”

mentioning

confidence: 96%

“…Due to the principle of overtones and combinations, it can gather information rapidly with little or no sample preparation. It has been widely used in the quantitative and qualitative analysis of Chinese herbal medicines (CHM) [5][6][7][8][9]. NIR has been widely regarded as an excel-lent online/in-line tool for process monitoring in CHM [10].…”

mentioning

confidence: 99%

“…It fully complies with the ICH Q2(R1) regulatory documents (Validation of analytical procedures: text and methodology) in that it integrates all the required methodology parameters, i.e., accuracy, precision, lower limit of quantification (LLOQ), upper limit of quantization (ULOQ), range, and linearity [22][23][24]. Detailed information about the accuracy profile theory was discussed in our previous papers [5,[7][8][9]21]. However, there is no previous report on the development and validation of the NIR method using two sampling modes in CHM with an accuracy profile based on the different samples sets.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Micro-Electro-Mechanical Systems/Near-Infrared Validation of Different Sampling Modes and Sample Sets Coupled with Multiple Models

Shi

Wan

et al. 2015

Planta Med

Self Cite

View full text Add to dashboard Cite

The aim of the present study was to demonstrate the reliability of micro-electro-mechanical systems/near-infrared technology by investigating analytical models of two modes of sampling (integrating sphere and fiber optic probe modes) and different sample sets. Baicalin in Yinhuang tablets was used as an example, and the experimental procedure included the optimization of spectral pretreatments, selection of wavelength regions using interval partial least squares, moving window partial least squares, and validation of the method using an accuracy profile. The results demonstrated that models that use the integrating sphere mode are better than those that use fiber optic probe modes. Spectra that use fiber optic probe modes tend to be more susceptible to interference information because the intensity of the incident light on a fiber optic probe mode is significantly weaker than that on an integrating sphere mode. According to the test set validation result of the method parameters, such as accuracy, precision, risk, and linearity, the selection of variables was found to make no significant difference to the performance of the full spectral model. The performance of the models whose sample sets ranged widely in concentration (i.e., 1-4 %) was found to be better than that of models whose samples had relatively narrow ranges (i.e., 1-2 %). The establishment and validation of this method can be used to clarify the analytical guideline in Chinese herbal medicine about two sampling modes and different sample sets in the micro-electro-mechanical systems/near-infrared technique.

show abstract

“…In the process of establishing a PLS model, spectral pretreatment methods have been applied to extract relevant information and reduce the effect of noise and baseline drift 8 9 . Variable selection is then also used to identify highly informative features and eliminate useless variables from the original spectral dataset 10 11 . The latent factors that explain the spectral matrix are sorted in decreasing order according to their contribution to the spectral features.…”

mentioning

confidence: 99%

Optimization of Parameter Selection for Partial Least Squares Model Development

Zhao

Zhang

et al. 2015

Sci Rep

Self Cite

View full text Add to dashboard Cite

In multivariate calibration using a spectral dataset, it is difficult to optimize nonsystematic parameters in a quantitative model, i.e., spectral pretreatment, latent factors and variable selection. In this study, we describe a novel and systematic approach that uses a processing trajectory to select three parameters including different spectral pretreatments, variable importance in the projection (VIP) for variable selection and latent factors in the Partial Least-Square (PLS) model. The root mean square errors of calibration (RMSEC), the root mean square errors of prediction (RMSEP), the ratio of standard error of prediction to standard deviation (RPD), and the determination coefficient of calibration (Rcal2) and validation (Rpre2) were simultaneously assessed to optimize the best modeling path. We used three different near-infrared (NIR) datasets, which illustrated that there was more than one modeling path to ensure good modeling. The PLS model optimizes modeling parameters step-by-step, but the robust model described here demonstrates better efficiency than other published papers.

show abstract

A novel model selection strategy using total error concept

Cited by 19 publications

References 17 publications

Online near-infrared analysis coupled with MWPLS and SiPLS models for the multi-ingredient and multi-phase extraction of licorice (Gancao)

Online near-infrared analysis coupled with MWPLS and SiPLS models for the multi-ingredient and multi-phase extraction of licorice (Gancao)

Micro-Electro-Mechanical Systems/Near-Infrared Validation of Different Sampling Modes and Sample Sets Coupled with Multiple Models

Optimization of Parameter Selection for Partial Least Squares Model Development

Contact Info

Product

Resources

About