The multiple determination tasks of chemical properties are a classical problem in analytical chemistry. The major problem is concerned in to find the best subset of variables that better represents the compounds. The...The multiple determination tasks of chemical properties are a classical problem in analytical chemistry. The major problem is concerned in to find the best subset of variables that better represents the compounds. These variables are obtained by a spectrophotometer device. This device measures hundreds of correlated variables related with physicocbemical properties and that can be used to estimate the component of interest. The problem is the selection of a subset of informative and uncorrelated variables that help the minimization of prediction error. Classical algorithms select a subset of variables for each compound considered. In this work we propose the use of the SPEA-II (strength Pareto evolutionary algorithm II). We would like to show that the variable selection algorithm can selected just one subset used for multiple determinations using multiple linear regressions. For the case study is used wheat data obtained by NIR (near-infrared spectroscopy) spectrometry where the objective is the determination of a variable subgroup with information about E protein content (%), test weight (Kg/HI), WKT (wheat kernel texture) (%) and farinograph water absorption (%). The results of traditional techniques of multivariate calibration as the SPA (successive projections algorithm), PLS (partial least square) and mono-objective genetic algorithm are presents for comparisons. For NIR spectral analysis of protein concentration on wheat, the number of variables selected from 775 spectral variables was reduced for just 10 in the SPEA-II algorithm. The prediction error decreased from 0.2 in the classical methods to 0.09 in proposed approach, a reduction of 37%. The model using variables selected by SPEA-II had better prediction performance than classical algorithms and full-spectrum partial least-squares.展开更多
Soil quality monitoring is important in precision agriculture.This study aimed to examine the possibility of assessing the soil parameters in apple-growing regions using spectroscopic methods.A total of 111 soil sampl...Soil quality monitoring is important in precision agriculture.This study aimed to examine the possibility of assessing the soil parameters in apple-growing regions using spectroscopic methods.A total of 111 soil samples were collected from 11 typical sites of apple orchards,and the croplands surrounding them.Near-infrared(NIR) and mid-infrared(MIR) spectra,combined with partial least square regression,were used to predict the soil parameters,including organic matter(OM) content,pH,and the contents of As,Cu,Zn,Pb,and Cr.Organic matter and pH were closely correlated with As and the heavy metals.The NIR model showed a high prediction accuracy for the determination of OM,pH,and As,with correlation coefficients(r) of 0.89,0.89,and 0.90,respectively.The predictions of these three parameters by MIR showed reduced accuracy,with r values of 0.77,0.84,and 0.92,respectively.The heavy metals could also be measured by spectroscopy due to their correlation with organic matter.Both NIR and MIR had high correlation coefficients for the determination of Cu,Zn,and Cr,with standard errors of prediction of 2.95,10.48,and 9.49 mg kg-1 for NIR and 3.69,5.84,and 6.94 mg kg-1 for MIR,respectively.Pb content behaved differently from the other parameters.Both NIR and MIR underestimated Pb content,with r values of 0.67 and 0.56 and standard errors of prediction of 3.46 and 2.99,respectively.Cu and Zn had a higher correlation with OM and pH and were better predicted than Pb and Cr.Thus,NIR spectra could accurately predict several soil parameters,metallic and nonmetallic,simultaneously,and were more feasible than MIR in analyzing soil parameters in the study area.展开更多
文摘The multiple determination tasks of chemical properties are a classical problem in analytical chemistry. The major problem is concerned in to find the best subset of variables that better represents the compounds. These variables are obtained by a spectrophotometer device. This device measures hundreds of correlated variables related with physicocbemical properties and that can be used to estimate the component of interest. The problem is the selection of a subset of informative and uncorrelated variables that help the minimization of prediction error. Classical algorithms select a subset of variables for each compound considered. In this work we propose the use of the SPEA-II (strength Pareto evolutionary algorithm II). We would like to show that the variable selection algorithm can selected just one subset used for multiple determinations using multiple linear regressions. For the case study is used wheat data obtained by NIR (near-infrared spectroscopy) spectrometry where the objective is the determination of a variable subgroup with information about E protein content (%), test weight (Kg/HI), WKT (wheat kernel texture) (%) and farinograph water absorption (%). The results of traditional techniques of multivariate calibration as the SPA (successive projections algorithm), PLS (partial least square) and mono-objective genetic algorithm are presents for comparisons. For NIR spectral analysis of protein concentration on wheat, the number of variables selected from 775 spectral variables was reduced for just 10 in the SPEA-II algorithm. The prediction error decreased from 0.2 in the classical methods to 0.09 in proposed approach, a reduction of 37%. The model using variables selected by SPEA-II had better prediction performance than classical algorithms and full-spectrum partial least-squares.
基金Supported by the Major Science and Technology Program for Water Pollution Control and Treatment in China(No.2008ZX07425-001)
文摘Soil quality monitoring is important in precision agriculture.This study aimed to examine the possibility of assessing the soil parameters in apple-growing regions using spectroscopic methods.A total of 111 soil samples were collected from 11 typical sites of apple orchards,and the croplands surrounding them.Near-infrared(NIR) and mid-infrared(MIR) spectra,combined with partial least square regression,were used to predict the soil parameters,including organic matter(OM) content,pH,and the contents of As,Cu,Zn,Pb,and Cr.Organic matter and pH were closely correlated with As and the heavy metals.The NIR model showed a high prediction accuracy for the determination of OM,pH,and As,with correlation coefficients(r) of 0.89,0.89,and 0.90,respectively.The predictions of these three parameters by MIR showed reduced accuracy,with r values of 0.77,0.84,and 0.92,respectively.The heavy metals could also be measured by spectroscopy due to their correlation with organic matter.Both NIR and MIR had high correlation coefficients for the determination of Cu,Zn,and Cr,with standard errors of prediction of 2.95,10.48,and 9.49 mg kg-1 for NIR and 3.69,5.84,and 6.94 mg kg-1 for MIR,respectively.Pb content behaved differently from the other parameters.Both NIR and MIR underestimated Pb content,with r values of 0.67 and 0.56 and standard errors of prediction of 3.46 and 2.99,respectively.Cu and Zn had a higher correlation with OM and pH and were better predicted than Pb and Cr.Thus,NIR spectra could accurately predict several soil parameters,metallic and nonmetallic,simultaneously,and were more feasible than MIR in analyzing soil parameters in the study area.