不同产地国产烤烟近红外光谱的特征分析及其模式识别.pdfVIP

不同产地国产烤烟近红外光谱的特征 分析及其模式识别 1 2 2 1 , , , 1. 华东理工大学化学与制药学院, 上海市徐汇区梅陇路130 号425 信箱 200237; 2. 上海烟草( 集团) 技术中心, 上海市 昌路 1062 号 200082 T o b : 烤烟; 近红外光谱; 主成分分析; 光谱预处理; 模式识别 a c c o : 对2003年125 个不同产地的国产烤烟烟叶的原始近红外光谱SNV 光谱与一阶导数光 ic e 谱进行了主成分分析, 采用主成分空间下的马氏距离判别样本的产地归属, 提出根据仪器噪声 n c e 和误差水平确定最大主成分个数, 研究了主成分个数样本空间光谱区间对烟叶产地识别准 T e 确率的影响, 分析了烟叶产地的近红外特征区和产地特征信息在不同主成分上的体现结果 c h n lo 表明, 采用光滑处理的全光谱区间的一阶导数光谱, 在建模样本空间进行主成分分析时所建模 o g y 型对烟叶样品的识别准确率最高 :TS442 : B : 1002- 0861( 2006) 05- 0036- 05 NIR Characteristic Analysis and Pattern Recognition of Domestic Flue_cured Tobaccos WANG GUO_DONG( 1) , SHU RU_XIN( 2) , ZHANG JIAN_PING( 2) , and NI LI_JUN( 1) 1. Chemical and Pharmaceutical College, East China University of Science Technology, Shanghai 200237, China 2.Technology Center of Shanghai Tobacco Group Corporation, Shanghai 200082, China T o b Keywords:Flue_cured tobacco; Near infrared spectra; Principal component analysis; Spectral pretreat a c c o ment; Pattern recognition C h e Abstract:By studying the original, SNV and first derivative near infrared spectra (NIRS) of 125 domes m is t tic flue_cured tobacco samples from different areas in 2003, the principal components in these samples r y were analyzed. The grown areas of tobacco samples were discriminated by Mahalanobis distance under principal components space. It was proposed to determine the maximum number of principal component on the basis of instrument noise and error level. The effects of principal component number, specimen space and spectral region on the accuracy in discrimination of tobacco grown area were studied. The 2 0 0