Characteristic Wavelength Variable Optimization of Near-Infrared Spectroscopy Based on Kalman Filtering
WANG Li-qi1, GE Hui-fang1, LI Gui-bin1, YU Dian-yu2, HU Li-zhi2, JIANG Lian-zhou2*
1. School of Computer and Information Engineering, Harbin University of Commerce, Harbin 150028, China 2. School of Food, Northeast Agricultural University, Harbin 150030, China
Abstract：Combining classical Kalman filter with NIR analysis technology, a new method of characteristic wavelength variable selection, namely Kalman filtering method, is presented. The principle of Kalman filter for selecting optimal wavelength variable was analyzed. The wavelength selection algorithm was designed and applied to NIR detection of soybean oil acid value. First, the PLS (partial least squares) models were established by using different absorption bands of oil. The 4 472～5 000 cm-1 characteristic band of oil acid value, including 132 wavelengths, was selected preliminarily. Then the Kalman filter was used to select characteristic wavelengths further. The PLS calibration model was established using selected 22 characteristic wavelength variables, the determination coefficient R2 of prediction set and RMSEP (root mean squared error of prediction) are 0.970 8 and 0.125 4 respectively, equivalent to that of 132 wavelengths, however, the number of wavelength variables was reduced to 16.67%. This algorithm is deterministic iteration, without complex parameters setting and randomicity of variable selection, and its physical significance was well defined. The modeling using a few selected characteristic wavelength variables which affected modeling effect heavily, instead of total spectrum, can make the complexity of model decreased, meanwhile the robustness of model improved. The research offered important reference for developing special oil near infrared spectroscopy analysis instruments on next step.
王立琦1，葛慧芳1，李贵滨1，于殿宇2，胡立志2，江连洲2* . 基于卡尔曼滤波的近红外光谱特征波长变量优选方法 [J]. 光谱学与光谱分析, 2014, 34(04): 958-961.
WANG Li-qi1, GE Hui-fang1, LI Gui-bin1, YU Dian-yu2, HU Li-zhi2, JIANG Lian-zhou2* . Characteristic Wavelength Variable Optimization of Near-Infrared Spectroscopy Based on Kalman Filtering. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(04): 958-961.
[1] JIE Deng-fei, XIE Li-juan, RAO Xiu-qin, et al(介邓飞, 谢丽娟, 饶秀勤, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2013, 29(12): 264. [2] WANG Ju-xiang, XING Zhi-na, SHEN Gang, et al(王菊香, 邢志娜, 申 刚, 等). Computers and Applied Chemistry(计算机与应用化学), 2013, 30(1): 39. [3] SHI Ji-yong, ZOU Xiao-bo, ZHAO Jie-wen, et al(石吉勇, 邹小波, 赵杰文, 等). Journal of Infrared and Millimeter Waves(红外与毫米波学报), 2011, 30(5): 458. [4] ZHANG Ming-jin, DU Yi-ping(张明锦, 杜一平). Chinese Journal of Analysis Laboratory(分析试验室), 2013, 32(2): 12. [5] LIU Guo-hai, JIANG Hui, MEI Cong-li(刘国海, 江 辉, 梅从立). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2013, 29: 218. [6] Balabin R M, Smirnov S V. Analytica Chimica Acta, 2011, 692: 63. [7] Jing Hui, Liu Guohai, Mei Congli, et al. Analytical and Bioanalytical Chemistry, 2012, 404: 603. [8] LI Jiang-bo, ZHAO Chun-jiang, CHEN Li-ping, et al(李江波, 赵春江, 陈立平, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2013, 44(3): 153. [9] HONG Ming-jian, WEN Zhi-yu, ZHANG Xiao-hong(洪明坚, 温志渝, 张小洪). Chinese Journal of Scientific Instrument(仪器仪表学报), 2011, 32(5): 1114. [10] PENG Ding-cong(彭丁聪). Software Guide(软件导刊), 2009, 8(11): 32. [11] The National Standard of the People’s Republic of China: Inspection of Vegetable Oils Methods of Determination of Acid Value. GB 5530—85. [12] Hourant P, Baeten V, MoralesM T, et al. Applied Spectroscopy, 2000, 54: 1168.
