Abstract:Genetic algorithm (GA) is an effective method in regions selection applied in building multivariate calibration model based on partial least squares regression. If genetic algorithm is run repeatedly as a block, the optimal solution is obtained faster, the numbers of data used to build calibration model are further reduced, and the prediction precision is further improved. An efficient method named region selecting by genetic algorithms (R-SGA) for building a PLS calibration model of NIR is presented in the present paper, in which each gene of chromosome represents a sub-region. In the R-SGA method, one needs to divide averagely the full spectral band into many sub-regions, and to build a research space with all the combinations of these sub-regions. The FT-NIR spectra were processed by GA after MSC and Savitky-Golay smoothing, a PLS calibration model of NIR was built by using the optimal combinations of these sub-regions. Meanwhile, the full region selecting PLS (FS-PLS) and experiential region selecting PLS (ES-PLS) models were developed using spectra after first-order derivative pretreatment. The seven intervals selected by region selecting by R-SGA which contained 434 variables were used as calibration set in GA-PLS. The prediction precision of GA-PLS model was better than FS-PLS and ES-PLS models, with RC=0.966, RMSEC=0.469, RV=0.954 and RMSEP=0.797. It was concluded that by using GA technique, in the pretreatment of apple SSC model by PLS, it is possible to optimize data selecting, enhance the precision of prediction and reduce the number of variables of calibration.
王加华,韩东海*. 基于遗传算法的苹果糖度近红外光谱分析[J]. 光谱学与光谱分析, 2008, 28(10): 2308-2311.
WANG Jia-hua,HAN Dong-hai*. Analysis of Near Infrared Spectra of Apple SSC by Genetic Algorithm Optimization. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2008, 28(10): 2308-2311.
[1] Holland J H. Adaptation in Natural and Artificial Systems, University of Michigan Press, Ann Arbor, MI, 1975. [2] Arcos M J, Ortiz M C, Belen Villahoz, et al. Anal. Chim. Acta, 1997, 339: 63. [3] Li T H, Lucasius C B, Kateman G. Anal. Chim. Acta, 1992,268: 123. [4] Bangalore A S, Shaffer R E, Small G W. Anal. Chem., 1996, 68: 4200. [5] Brandye M Smith, Paul J Gemperline. Anal. Chim. Acta,2000, 423: 167. [6] GU Xiao-yu, XU Ke-xin, WANG Yan(谷筱玉,徐可欣,汪 ). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2006,26(9): 1618. [7] LIU Fang, WANG Jun-de(刘 芳,王俊德). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2001,21(3): 331. [8] LIU Yan-de, YING Yi-bin, FU Xia-ping(刘燕德,应义斌,傅霞萍). Spectroscopy and Spectral Analysis(光谱学与光谱分析),2005,25(11): 1793. [9] ZHAO Jie-wen, ZHANG Hai-dong, LIU Mu-hua(赵杰文,张海东,刘木华). Acta Optica Sinica(光学学报),2006,26(1): 136. [10] Kawano S, Watanabe H, Iwamoto M. Journal of the Japanese Society for Horticultural Science, 1992, 61(2): 445. [11] Lu R, Ariana D. Applied Eng. Agric.,2002, 18, (5): 585. [12] Lammertyn J, Nicolai B, Ooms K. Trans. American Society of Agricultural Engineer(ASAE), 1998, 41(4): 1089. [13] ZHU Shi-ping, WANG Yi-ming, ZHANG Xiao-chao, et al(祝诗平,王一鸣,张小超,等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报),2004, 35(5): 153. [14] WANG Hong, LI Qing-bo, LIU Ze-yi, et al(王 宏,李庆波,刘则毅,等). Chinese Journal of Analytical Chemistry(分析化学),2002, 30(7): 779. [15] XU Lu(许 禄). Chemometrics Methods(化学计量学方法). Beijing: Science Press(北京: 科学出版社), 1997. [16] ZHOU Ming, SUN Shu-dong(周 明,孙树栋). Genetic Algorithm and Its Applications(遗传算法原理及应用). Beijing: National Defence Industry Press(北京: 国防工业出版社), 1999. [17] Chen J Y, Iyo C, Teradab F. J. Near Infrared Spectrosc.,2002, 10: 301. [18] Helland I S, Tormod N, Tomas I. Chemometrics and Intelligent Laboratory Systems, 1995,29: 233.