Using consensus interval partial least square in near infrared spectra analysis

Ji, Guoli; Huang, Guangzao; Yang, Zijiang; Wu, Xiaohui; Chen, Xiaojing; Yuan, Mingshun

doi:10.1016/j.chemolab.2015.03.008

Cited by 28 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, selection of optimal wavenumbers is significant for building a simplified model [20, 25]. Interval partial least squares (iPLS) regression is a wavenumber selection method proposed by Norgaard [20], which can extract the spectral wavenumbers highly related to the chemical structure, thus achieving the objective to improve the stability of the prediction model and increase the interpretability of the relationship between the spectral response and chemical structure [20]. The successive projections algorithm (SPA)proposed by Araújo et al [26] has also been proved to be a useful and effective tool for variable selection, which solves the collinearity problem with minimal redundancy [27].…”

Section: Methodsmentioning

confidence: 99%

“…Thus, wavenumber selection is a very important step in dealing with spectra data. So far, many wavenumber selection methods have been utilized in spectral studies, including regression coefficient analysis (RCA) [18], successive projections algorithm (SPA) [19], interval partial least squares regression (iPLS) [20], and interval random frog (iRF) [21]. Among these methods, SPA and iPLS have been proved that they employ simple operation and demand a smaller computational workload.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optical Determination of Lead Chrome Green in Green Tea by Fourier Transform Infrared (FT-IR) Transmission Spectroscopy

Liu

Zhang

et al. 2017

PLoS ONE

View full text Add to dashboard Cite

The potential of Fourier transform infrared (FT-IR) transmission spectroscopy for determination of lead chrome green in green tea was investigated based on chemometric methods. Firstly, the qualitative analysis of lead chrome green in tea was performed based on partial least squares discriminant analysis (PLS-DA), and the correct rate of classification was 100%. And then, a hybrid method of interval partial least squares (iPLS) regression and successive projections algorithm (SPA) was proposed to select characteristic wavenumbers for the quantitative analysis of lead chrome green in green tea, and 19 wavenumbers were obtained finally. Among these wavenumbers, 1384 (C = C), 1456, 1438, 1419(C = N), and 1506 (CNH) cm-1 were the characteristic wavenumbers of lead chrome green. Then, these 19 wavenumbers were used to build determination models. The best model was achieved by least squares support vector machine (LS-SVM)algorithm with high coefficient of determination and low root-mean square error of prediction set (R2p = 0.864 and RMSEP = 0.291). All these results indicated the feasibility of IR spectra for detecting lead chrome green in green tea.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optical Determination of Lead Chrome Green in Green Tea by Fourier Transform Infrared (FT-IR) Transmission Spectroscopy

Liu

Zhang

et al. 2017

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…where b ji represents the regression coefficient of the ith variable in the jth model. Meanwhile, the merit RMSECV can be calculated using formula (6) and is used to reflect the model bias. A smaller RMSECV value corresponds to a higher prediction accuracy of the calibration model.…”

Section: Evaluation Merit Of the Modelmentioning

confidence: 99%

“…However, when full wavelengths are considered as input variables, many uninformative and noise variables may interfere with the input, which results in a reduction in the accuracy and robustness of a prediction model . To solve this problem, variable selection algorithms such as the genetic algorithm (GA), interval partial least squares (IPLS), successive projections algorithm (SPA), and competitive adaptive reweighted sampling (CARS) are usually used to select the most useful variables from full wavelengths before modeling . Thereafter, the regression model is built based on the selected variables.…”

Section: Introductionmentioning

confidence: 99%

Tuning parameter identification for variable selection algorithm using the sum of ranking differences algorithm

Nie

Meng

Chen

et al. 2019

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

Variable selection algorithms are often adopted to select the optimal variable from a full set of variables and are efficient for reducing the variable dimension and improving the model accuracy. Nonetheless, the parameters of the variable selection method and regression model, such as the number of latent variables of the partial least squares (PLS) model and the threshold value of the variable importance index, need to be identified. The parameters directly determine the final performance of the model. Currently, these parameters are often determined subjectively. As a result, the model results may be accidental because of the subjective determination of the parameters. To objectively identify these parameters, the sum of ranking differences (SRD) coupled with partial least squares‐variable importance in projection (PLS‐VIP‐SRD) and partial least squares‐uninformative variable elimination (PLS‐UVE‐SRD) algorithms was applied to determine the latent variable of the PLS model and the threshold value of the variable importance index. Furthermore, public near‐infrared data of corn were used as the calculation data. The final results show that the PLS‐VIP‐SRD and PLS‐UVE‐SRD models can more effectively and objectively determine the optimal parameter combination than the PLS‐VIP and PLS‐UVE models. Moreover, the selected variables are easier to interpret, and the prediction accuracy is also improved to some extent.

show abstract

“…Partial least squares (PLS) is a regression method used as a dimension reduction process when there is serious correlation between independent variables and selected variables [10,11] . To produce the optimal QSAR model, we first built the QSAR model of all variables based on PLS, using identification of significant values to remove the independent variables (P < 0.05) and establish a new QSAR model.…”

Section: Construction Of 2d-qsarmentioning

confidence: 99%

Relationship between soybean yield/quality and soil quality in a major soybean-producing area based on a 2D-QSAR model

Gao

Li²

2017

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. Based on experimental data of the soybean yield and quality from 30 sampling points, a quantitative structureactivity relationship model (2D-QSAR) was established using the soil quality (elements, pH, organic matter content and cation exchange capacity) as independent variables and soybean yield or quality as the dependent variable, with SPSS software. During the modeling, the full data set (30 and 14 compounds) was divided into a training set (24 and 11 compounds) for model generation and a test set (6 and 3 compounds) for model validation. The R2 values of the resulting models and data were 0.826 and 0.808 for soybean yield and quality, respectively, and all regression coefficients were significant (P < 0.05). The correlation coefficient R2pred of observed values and predicted values of the soybean yield and soybean quality in the test set were 0.961 and 0.956, respectively, indicating that the models had a good predictive ability. Moreover, the Mo, Se, K, N and organic matter contents and the cation exchange capacity of soil had a positive effect on soybean production, and the B, Mo, Se, K and N contents and cation exchange coefficient had a positive effect on soybean quality. The results are instructive for enhancing soils to improve the yield and quality of soybean, and this method can also be used to study other crops or regions, providing a theoretical basis to improving the yield and quality of crops.

show abstract

Using consensus interval partial least square in near infrared spectra analysis

Cited by 28 publications

References 35 publications

Optical Determination of Lead Chrome Green in Green Tea by Fourier Transform Infrared (FT-IR) Transmission Spectroscopy

Optical Determination of Lead Chrome Green in Green Tea by Fourier Transform Infrared (FT-IR) Transmission Spectroscopy

Tuning parameter identification for variable selection algorithm using the sum of ranking differences algorithm

Relationship between soybean yield/quality and soil quality in a major soybean-producing area based on a 2D-QSAR model

Contact Info

Product

Resources

About