基于可见/近红外反射光谱的稻米品种与真伪鉴别

利用可见/近红外光谱技术对市场上5种稻米进行了鉴别.以ASD FieldSpec .3地物光谱仪采集了5种稻米的光谱数据, 各获取35个样本, 随机分成训练集(150份)和检验集(25份), 并分别采取全波段与特征波段(400～ 500nm、910～1400nm与1940～2300nm)两种方法建立模型进行分析.光谱经S.Golay平滑和标准归一化(SNV)处理后, 以主成分分析法(PCA)降维.将降维所得的前9个主成分数据作为BP人工神经网络(BP-ANN)的输入变量, 稻米品种作为输出变量, 建立3层BP-ANN鉴别模型.利用25个未知样对模型进行检验, 结果表明两类模型预测准确率均高达100%, 其中特征波段模型比全波段模型具有更高的预测精度, 说明利用可见/近红外技术结合PCA-BP 神经网络分析法进行稻米品种与真伪的快速、无损鉴别是可行的, 且提取特征波段是优化模型的有效方法之一.

Abstract

Five different varieties of rice bought from the supermarket were identified with visual/near infrared spectroscopy (NIRS) technology. The spectra were collected by using ASD FieldSpec . 3 spectrometer, and 35 samples were obtained for each variety of rice. All the samples were divided randomly into two groups, one group with 150 ones used as calibrated set, and the other with 25 ones as validated set. Then the samples were analyzed with the whole wave band and the charac- teristic wave band(400～500nm, 910～1400nm and 1940～2300nm) models, respectively. The samples data were pre- treated by the methods of S.Golay smoothing and standard normal variable (SNV), and then the pretreated spectra data were analyzed with principal component analysis (PCA). The anterior 9 principal components computed by PCA were used as the input variables of back-propagation artificial neural network (BP-ANN) which included one hidden layer, while the values of rice varieties were used as the output variables of BP-ANN, and then the three layers BP-ANN discrimination model was built. The 25 unknown samples in the validated set were predicted by ANN-BP model. The results show that the discriminating rates are 100% in both models, and the accuracy of characteristic wave band model is higher than that of the whole wave band model. The results indicate that it is feasible to discriminate the variety and authenticity of rice by visible/ near infrared reflectance spectra as a rapid and non-contact way, and selecting characteristic wave band is one of the valida- ted methods to improve the precision of the discrimination model.

参考文献

[1] CHU Xiao-Li, YUAN Hong-Fu, LU Wan-Zhen. Present sit- uation and prospect of near infrared spectrometer in China and abroad［J］. Analytical Instrumentation (褚小立, 袁洪福, 陆婉珍.近红外光谱仪国内外现状与展望. 分析仪器 ), 2006(2):1—10.

[2] LIU Yan-De, LUO Ji, CHEN Xing-Miao. Analysis of solu- ble solid content in Nanfeng mandarin fruit with visible near infrared spectroscopy［J］. J. Infrared Millim. Waves (刘燕德, 罗吉, 陈兴苗.可见/近红外光谱的南丰蜜桔可溶性固形物含量定量分析. 红外与毫米波学报 ), 2008, 27 (2):119—122.

[3] HAN Liang-Liang, MAO Pei-Sheng, WANG Xin-Guo, et al. Study on vigour test of oat seeds with near infrared re- flectance spectroscopy［J］. J. Infrared Millim. Waves (韩亮亮, 毛培胜, 王新国, 等.近红外光谱技术在燕麦种子活力测定中的应用研究. 红外与毫米波学报 ), 2008, 27 (2):86—90.

[4] LIU Xiu-hua, ZHANG Xue-Gong, SUN Su-qin. Auto-dis- crimination and characteristic wave band selection of Chi- nese traditional medicine origin based on near infrared spectra［J］. China Science Bulletin (刘沭华, 张学工, 孙素琴. 中药材产地的近红外光谱自动鉴别和特征谱段选择. 科学通报 ), 2005, 50 (4):393—398.

[5] WU Yong-Jun, LI Wei, XIANG Bing-Ren, et al. Identifi- cation of traditional Chinese medocone Baizhi with near-in- frared spectrum［J］. Journal of Chinese Medicinal Materials (吴拥军, 李伟, 相秉仁, 等.近红外光谱技术用于白芷类中药的鉴定研究. 中药材 ), 2001, 24 (1):26—28.

[6] LIU Gou-Lin, CAI Jin-Na, LI Wei, et al. Near-Infrared spectroscopy technique used in the classification of the Cnid- ium Monnieri (L.) Cusson［J］. Computer and Applied Chemistry (刘国林, 蔡金娜, 李伟, 等.近红外光谱技术在中药蛇床子分类中的应用. 计算机与应用化学 ), 2000, 17 (2):109—110.

[7] . Apparent am- ylose content of milled rice by near-infrared reflectance spectrophotometry[J]. Cereal Chemistry, 1995, 72: 182.

[8] . Prediction of rice starch quality parameters by near-infrared reflectance spectroscopy[J]. Food Science, 2001, 66: 936.

[9] . Estimating the amino acid composition in the milled rice powder by near-infrared re- flectance spectroscopy[J]. Field Crops Research, 2002, 75: 1.

[10] . Quantitative analysis of fat content in brown rice by near infrared spectroscopy (NIRS) technique[J]. Scientia Ag- ricultura Sinica (王海莲, 万向元, 胡培松, 等.稻米脂肪含量近红外光谱分析技术研究. 中国农业科学 ), 2005, 38(8): 1540.

[11] BI Jing-Cui, ZHANG Wen-Wei, XIAO Ying-Hui, et al. Analysis for protein content in rice by near infrared reflec- tance spectroscopy (NIRS) technique［J］. Acta Agronomi- ca Sinica (毕京翠, 张文伟, 肖应辉, 等.应用近红外光谱技术分析稻米蛋白质含量. 作物学报 ), 2006, 32 (15): 709—715.

[12] SHAO Yong-Ni, CAO Fang, HE Yong. Discrimination years of rough rice by using visible/near infrared spectros- copy based on independent component analysis and BP neural network［J］. J. Infrared Millim. Waves (邵咏妮, 曹芳, 何勇.基于独立组分分析和BP神经网络的可见/ 近红外光谱稻谷年份的鉴别. 红外与毫米波学报 ), 2007, 26 (6):433—436.

[13] Haykin S. Neural network-a comprehensive foundation ［M］. New York, USA: Macmillan College Publishing Company, 1994, 1—44.

[14] QI Xiao-Ming, ZHANG Lu-Da, DU Xiao-Lin, et al. Quantitative analysis using NIR by building PLS-BP model ［J］. Spectroscopy and Spectral Analysis (齐小明, 张录达, 杜晓林, 等.PLS-BP法近红外光谱定量分析研究. 光谱学与光谱分析 ), 2003, 23 (5):870—872.

[15] Workman J. Handbook of Organic Compounds: NIR, IR, Raman, and UV-VIS Spectra Featuring Polymers and Sur- factants ［M］. San Diego, USA: Academic Press, 2001: 77—197.

[16] . Short-wave near-infrared spectroscopy of biological fluids. 1In Quantitative analysis of fat, protein, and lactose in raw milk by partial least-squares regression and band assignment[J]. Anal Chem., 2001, 73: 64.

梁亮, 刘志霄, 杨敏华, 张佑祥, 汪承华. 基于可见/近红外反射光谱的稻米品种与真伪鉴别[J]. 红外与毫米波学报, 2009, 28(5): 353. LIANG Liang, LIU Zhi-Xiao, YANG Min-Hua, ZHANG You-Xiang, WANG Cheng-Hua. DISCRIMINATION OF VARIETY AND AUTHENTICITY FOR RICE BASED ON VISUAL/NEAR INFRARED REFLECTION SPECTRA[J]. Journal of Infrared and Millimeter Waves, 2009, 28(5): 353.

基于可见/近红外反射光谱的稻米品种与真伪鉴别

关于本站 Cookie 的使用提示

全站搜索

基于可见/近红外反射光谱的稻米品种与真伪鉴别

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索