Application of Intelligent Optimization Algorithms to Wavelength Selection of Near-Infrared Spectroscopy
BIN Jun1, FAN Wei1*, ZHOU Ji-heng1*, LI Xin1, LIANG Yi-zeng2
1. College of Bioscience and Biotechnology, Hunan Agricultural University, Changsha 410128, China 2. College of Chemistry and Chemical Engineering, Central South University, Changsha 410083, China
Abstract：Near infrared spectroscopy (NIRS) is a kind of indirect analysis technology, whose application depends on the setting up of relevant calibration model. In order to improve interpretability, accuracy and modeling efficiency of the prediction model, wavelength selection becomes very important and it can minimize redundant information of near infrared spectrum. Intelligent optimization algorithm is a sort of commonly wavelength selection method which establishes algorithm model by mathematical abstraction from the background of biological behavior or movement form of material, then iterative calculation to solve combinatorial optimization problems. Its core strategy is screening effective wavelength points in multivariate calibration modeling by using some objective functions as a standard with successive approximation method. In this work, five intelligent optimization algorithms, including ant colony optimization (ACO), genetic algorithm (GA), particle swarm optimization (PSO), random frog (RF) and simulated annealing (SA) algorithm, were used to select characteristic wavelength from NIR data of tobacco leaf for determination of total nitrogen and nicotine content and together with partial least squares (PLS) to construct multiple correction models. The comparative analysis results of these models showed that, the total nitrogen optimums models of dataset A and B were PSO-PLS and GA-PLS models. GA-PLS and SA-PLS models were the optimums for nicotine, respectively. Although not all predicting performance of these optimization models was superior to that of full spectrum PLS models, they were simplified greatly and their forecasting accuracy, precision, interpretability and stability were improved. Therefore, this research will have great significance and plays an important role for the practical application. Meanwhile, it could be concluded that the informative wavelength combination for total nitrogen were 4 587~4 878 and 6 700~7 200 cm-1, and that for tobacco nicotine were 4 500~4 700 and 5 800~6 000 cm-1. These selected wavelengths have actually physical significance.
[1] Fang Yi, Park Jong I, Jeong Young-Seon, et al. Annals of Operations Research, 2009, 190(1): 3. [2] Bin Jun, Ai Fangfang, Liu Nian, et al. Journal of Chemometrics, 2013, 27(12): 457. [3] Swierenga H, Wulfert F, de Noord O E, et al. Analytica Chimica Acta, 2000, 411: 121. [4] Balabin R M，Smirnov S V. Analytica Chimica Acta, 2011, 692(1-2): 63. [5] Roy P P，Roy K. QSAR & Combinatorial Science, 2008, 27(3): 302. [6] Wang Ling. Intelligent Optimization Algorithms with Applications. Beijing：Tsinghua University & Springer Press, 2001. [7] Jin Huimin, Ma Liang, Wang Zhoumian. Computer Engineering, 2006, 32(10): 201. [8] Allegrini F，Olivieri A C. Analytica Chimica Acta, 2011, 699(1): 18. [9] Zhu Yaodi, Zou Xiaobo, Huang Xiaowei, et al. Journal of Applied Solution Chemistry and Modeling, 2013, 2: 25. [10] Jarvis R M，Goodacre R. Bioinformatics, 2005, 21(7): 860. [11] Khajeh A, Modarress H, Zeinoddini-Meymand H. Journal of Chemometrics, 2012, 26(11-12): 598. [12] Jiang Huaqin, Yan Zhengbing, Liu Xinggao. Neurocomputing, 2013, 119: 469. [13] Li Hongdong, Xu Qingsong, Liang Yizeng. Analytica Chimica Acta, 2012, 740: 20. [14] Yun Yonghuan, Li Hongdong, Wood L R, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2013, 111: 31. [15] Brusco Michael J. Computational Statistics & Data Analysis, 2014, 77: 38.
