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
Improving the prediction accuracy of wind power is an effective means to reduce the impact of wind power on power grid.Therefore,we proposed an improved African vulture optimization algorithm(AVOA)to realize the predi...Improving the prediction accuracy of wind power is an effective means to reduce the impact of wind power on power grid.Therefore,we proposed an improved African vulture optimization algorithm(AVOA)to realize the prediction model of multi-objective optimization least squares support vector machine(LSSVM).Firstly,the original wind power time series was decomposed into a certain number of intrinsic modal components(IMFs)using variational modal decomposition(VMD).Secondly,random numbers in population initialization were replaced by Tent chaotic mapping,multi-objective LSSVM optimization was introduced by AVOA improved by elitist non-dominated sorting and crowding operator,and then each component was predicted.Finally,Tent multi-objective AVOA-LSSVM(TMOALSSVM)method was used to sum each component to obtain the final prediction result.The simulation results show that the improved AVOA based on Tent chaotic mapping,the improved non-dominated sorting algorithm with elite strategy,and the improved crowding operator are the optimal models for single-objective and multi-objective prediction.Among them,TMOALSSVM model has the smallest average error of stroke power values in four seasons,which are 0.0694,0.0545 and 0.0211,respectively.The average value of DS statistics in the four seasons is 0.9902,and the statistical value is the largest.The proposed model effectively predicts four seasons of wind power values on lateral and longitudinal precision,and faster and more accurately finds the optimal solution on the current solution space sets,which proves that the method has a certain scientific significance in the development of wind power prediction technology.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 National Natural Science Foundation of China(Nos.61662042,62062049)Science and Technology Plan of Gansu Province(Nos.21JR7RA288,21JR7RE174).
文摘Improving the prediction accuracy of wind power is an effective means to reduce the impact of wind power on power grid.Therefore,we proposed an improved African vulture optimization algorithm(AVOA)to realize the prediction model of multi-objective optimization least squares support vector machine(LSSVM).Firstly,the original wind power time series was decomposed into a certain number of intrinsic modal components(IMFs)using variational modal decomposition(VMD).Secondly,random numbers in population initialization were replaced by Tent chaotic mapping,multi-objective LSSVM optimization was introduced by AVOA improved by elitist non-dominated sorting and crowding operator,and then each component was predicted.Finally,Tent multi-objective AVOA-LSSVM(TMOALSSVM)method was used to sum each component to obtain the final prediction result.The simulation results show that the improved AVOA based on Tent chaotic mapping,the improved non-dominated sorting algorithm with elite strategy,and the improved crowding operator are the optimal models for single-objective and multi-objective prediction.Among them,TMOALSSVM model has the smallest average error of stroke power values in four seasons,which are 0.0694,0.0545 and 0.0211,respectively.The average value of DS statistics in the four seasons is 0.9902,and the statistical value is the largest.The proposed model effectively predicts four seasons of wind power values on lateral and longitudinal precision,and faster and more accurately finds the optimal solution on the current solution space sets,which proves that the method has a certain scientific significance in the development of wind power prediction technology.
