Application of PCA-SVR to NIR Prediction Model for Tobacco Chemical Composition
LIU Xu1,2,CHEN Hua-cai3*,LIU Tai-ang4,LI Yin-ling4,LU Zhi-rong4,LU Wen-cong1,2
1. Laboratory of Chemical Data Mining, Department of Chemistry, College of Sciences, Shanghai University, Shanghai 200444, China 2. School of Materials Science and Engineering, Shanghai University, Shanghai 200072, China 3. China Jiliang University, Hangzhou 310018, China 4. Beijing Petrochemical Design Institute, Beijing 100101, China
Abstract：Near infrared diffuse reflectance spectra of 50 tobacco samples were pretreated with PCA. The calibration models of determination of the main components in tobacco were developed with support vector regression (SVR). The models were tested with leave-one-out (LOOCV) method and optimized with parameters of kernel function, penalty coefficient C and insensitive loss function. The root mean square errors (RMSE) with leave-one-out cross validation of the optimal models of nicotine, and total sugars, reductive sugar, and total nitrogen were 0.313, 1.581, 1.412 and 0.117 respectively. Based on the comparison of RMSE of the SVM model with those of the partial least square (PLS), multiplicative linear regression (MLR) and back propagation artificial neuron network (BP-ANN) models, it was found that the SVR model was the most robust one. This study suggested that it is feasible to rapidly determine the main components concentrations by near infrared spectroscopy method based on SVR.
刘旭1,2,陈华才3*,刘太昂4,李银玲4,陆治荣4,陆文聪1, 2. PCA-SVR联用算法在近红外光谱分析烟草成分中的应用[J]. 光谱学与光谱分析, 2007, 27(12): 2460-2463.
LIU Xu1,2,CHEN Hua-cai3*,LIU Tai-ang4,LI Yin-ling4,LU Zhi-rong4,LU Wen-cong1,2 . Application of PCA-SVR to NIR Prediction Model for Tobacco Chemical Composition. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2007, 27(12): 2460-2463.
