Abstract:In the present article, near infrared spectra of 89 wood samples of different geographical provenances and species were measured, and back propagation artificial neural networks(BPANN) and generalized regression neural network(GRNN) were used for modeling of wood species NIRS identifying. Parameters for two neural networks were chosen via analysis of variance, respectively;and networks were trained with optimum parameters. Considering the difference between spectra, spectra with different levels of white noise and different levels of bias were simulated and predicted by using the models built. It was found that both the two models had satisfactory prediction results, identification correct rates obtained by BPANN model applied to spectra with bias level no higher than 2% and noise level no higher than 4% were above 97%;correct rates obtained by GRNN model applied to spectra with bias level no higher than 2% and noise level no higher than 4% were above 99%.
Key words:Artificial neural networks;Wood species identification;NIRS;Analysis of variance
马明宇1,王桂芸1,黄安民2,张卓勇1*,相玉红1,顾 轩1 . 人工神经网络结合近红外光谱用于木材树种识别[J]. 光谱学与光谱分析, 2012, 32(09): 2377-2381.
MA Ming-yu1, WANG Gui-yun1, HUANG An-min2, ZHANG Zhuo-yong1*, XIANG Yu-hong1, GU Xuan1 . Study on Artificial Neural Network Combined with Near Infrared Spectroscopy for Wood Species Identification. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2012, 32(09): 2377-2381.
[1] Wheeler E A,Baas P,Rodgers S. IAWA Journal,2007,28(3):229. [2] Mallik A,Tarrío-Saavedra J,Francisco-Fernández M,et al. Chemometrics and Intelligent Laboratory Systems,2011,107(2):351. [3] Kagawa A,Leavitt S W. J. Wood Sci.,2010,56(3):175. [4] Tang X,Zhao G,Ping L. Plant Mol. Biol.,2011,77(6):609. [5] Borga P,H?m?l?inen M,Theander O. Holzforschung,1992,46(4):299. [6] Watanabe K,Mansfield D S,Avramidis S. Eur. J. Wood Prod.,2012,70(1):61. [7] Cooper P A,Jeremic D,Radivojevic S,et al. Can. J. For. Res.,2011,41:2150. [8] Sandak A,Sandak J,Negri M. Wood Sci. Technol.,2011,45(1):35. [9] JIANG Ze-hui,YANG Zhong,XU Zhong-yun,et al(江泽慧,杨 忠,许忠允,等). China Patent,CN1936552,2003. [10] Mutlu A,Boyaci I H,Genis H E. Eur. Food Res. Technol.,2011,233(2):267. [11] Zhang H,Hu H,Zhang X. Acta Physiol Plant,2011,33(6):2461. [12] Balabin R M,Safieva R Z. Energy Fuels,2011,25(5):2373. [13] Hecht-Nielsen,R. Proc IJCNN,Washington D. C.,1989,1:593. [14] CHEN Bao-lin(陈宝林). Optimization Theory and Algorithm(最优化理论与算法). 2nd ed(第2版). Beijing:Tsinghua University Press(北京:清华大学出版社),2005. 291. [15] Moller M F. Neural Networks,1993,6(4):525. [16] Specht D F. Trans. Neural Networks,1991,2(6):568.