Variable Selection Methods Combined with Local Linear Embedding Theory Used for Optimization of Near Infrared Spectral Quantitative Models
HAO Yong1, SUN Xu-dong1, YANG Qiang2
1. College of Machanical and Electronic Engineering, East China Jiaotong University, Nanchang 330013, China 2. College of Machanical and Electronic Engineering, Rizhao Polytechnic, Rizhao 276826, China
摘要： 变量筛选策略结合局部线性嵌入(local linear embedding, LLE)理论用于近红外光谱(near infrared spectroscopy, NIRS)定量模型优化。蒙特卡罗无信息变量消除方法(monte carlo uninformation variable elimination, MCUVE)和连续投影算法(successive projections algorithm, SPA)以及两者结合的变量筛选策略用于NIRS冗余变量的剔除;偏最小二乘回归(partial least squares regression, PLSR)和LLE-PLSR用于复杂样品光谱定量模型的构建。结果表明：MCUVE方法既能有效的提取信息变量，同时可以提高模型的预测精度;LLE-PLSR可以得到比PLSR方法更加准确的定量分析模型;MCUVE结合LLE-PLSR是一种有效的光谱定量分析方法。
关键词：近红外光谱;蒙特卡罗无信息变量消除;连续投影算法;局部线性嵌入
Abstract：Variables selection strategy combined with local linear embedding (LLE) was introduced for the analysis of complex samples by using near infrared spectroscopy (NIRS). Three methods include monte carlo uninformation variable elimination (MCUVE), successive projections algorithm (SPA) and MCUVE connected with SPA were used for eliminating redundancy spectral variables. Partial least squares regression (PLSR) and LLE-PLSR were used for modeling complex samples. The results shown that MCUVE can both extract effective informative variables and improve the precision of models. Compared with PLSR models, LLE-PLSR models can achieve more accurate analysis results. MCUVE combined with LLE-PLSR is an effective modeling method for NIRS quantitative analysis.
Key words：Near infrared spectroscopy (NIRS);Monte carlo uninformation variable elimination (MCUVE);Successive projections algorithm (SPA);Local linear embedding (LLE)
郝 勇1，孙旭东1，杨 强2 . 变量筛选方法结合局部线性嵌入理论用于近红外光谱定量模型优化 [J]. 光谱学与光谱分析, 2012, 32(12): 3208-3212.
HAO Yong1, SUN Xu-dong1, YANG Qiang2 . Variable Selection Methods Combined with Local Linear Embedding Theory Used for Optimization of Near Infrared Spectral Quantitative Models. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2012, 32(12): 3208-3212.
[1] Gaydou V, Kister J, Dupuy N. Chemometrics and Intelligent Laboratory Systems, 2011, 106(2): 190. [2] Yan Hui, Han Bangxing, Wu Qiongying, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2011, 79(1): 179. [3] Lidia Esteve Agelet, David D Ellis, Susan Duvick, et al. Journal of Cereal Science, 2012, 55(2): 160. [4] Liao Yitao, Fan Yuxia, Cheng Fang. Journal of Food Engineering, 2012, 109(4): 668. [5] Shen Fei, Ying Yibing, Li Bobin, et al. Food Research International, 2011, 44(5): 1521. [6] Sinelli N, Casiraghi E, Barzaghi S, et al. Food Research International, 2011, 44(5): 1427. [7] Asmund Rinnan, Frans van den Berg, Soren Balling Engelsen. Trends in Analytical Chemistry, 2009, 28(10): 1201. [8] Cai Chenbo, Yang Hongwei, Wang Bo, et al. Vibrational Spectroscopy, 2011, 56(2), 202. [9] Mohammadreza Khanmohammadi, Amir Bagheri Garmarudi, Nafiseh Khoddami, et al. Mirochemical Journal, 2010, 95(2): 337. [10] Han Qingjuan, Wu Hailong, Cai Chenbo, et al. Analytica Chimica Acta, 2008, 612(2): 121. [11] Cai Wensheng, Li Yankun, Shao Xueguang. Chemometrics and Intelligent Laboratory Systems, 2008, 90(2): 188. [12] Soares M C U, Galvao R K H, Araujo M C U, et al. Analytica Chimica Acta, 2011, 689(1): 22. [13] Liu Fei, He Yong. Food Chemistry, 2009, 115(4): 1430. [14] Hou Chenping, Wang Jing, Wu Yi, et al. Neurocomputing, 2009, 72(12): 2368. [15] Kalivas J H. Chemometrics and Intelligent Laboratory Systems, 1997, 37(2): 255. [16] Dyrby M, Engelsen S B,Nrgaard L, et al. Applied Spectroscopy, 2002, 56(5): 579. [17] Shao Xueguang, Ma Chaoxiong. Chemometrics and Intelligent Laboratory Systems, 2003, 69(1): 157.
