期刊文献+

基于主成分分析与近红外光谱技术的窖泥聚类研究 被引量:1

Cluster Analysis of Pit Mud Based on Main Components Analysis and Near Infrared Spectroscopy
下载PDF
导出
摘要 采用近红外光谱技术和主成分分析法相结合的检测手段,从60年、90年、200年窖龄的窖池和封窖泥中取样,每个窖池样本为12个,测量其近红外漫反射红外光谱,在4000~10000 cm-1区间选取不同范围内的光谱数据,对48个样本进行主成分分析,作二维线性投影图和三维线性投影图,比较了48个样品在红外光谱上的差异程度,发现基于傅里叶变换近红外光谱的主成分分析投影图能够较好地表征48个样品的类别关系,不同窖龄的样本在空间分布中能够得到较好的区分。结果表明,应用近红外漫反射光谱法能够鉴别窖泥的使用年份。作为一种窖泥质量检测手段,该方法具有一定的应用价值。 48 pit mud samples in total were obtained fxom three pits (pit of 60 years age, pit of 90 years age, and pit of 200 years age) and pit mud for pit-sealing (12 samples for each pit). Then main components analysis of those pit mud samples was carried out by near infrared spectroscopy with diffuse reflection method (the spectra data between 4000 and 10000 wave-numbers).Through the analysis of two dimensional and three di- mensional projection figures, it was found that the figures could clearly reflect the difference of different pit mud samples and pit mud of different age could be differentiated in space distribution. As a method of controlling and detecting the quality of pit mud, near infrared spectroscopy and main components analysis was valuable in practice.
出处 《酿酒科技》 2011年第8期36-38,共3页 Liquor-Making Science & Technology
基金 四川省科技支撑计划项目 编号2010SZ0228
关键词 主成分分析(PCA) 近红外光谱 窖泥 聚类 principal component analysis(PCA) near infrared spectroscopy (NIR) pit mud cluster
  • 相关文献

参考文献8

二级参考文献20

  • 1Woo Y-A, Kim H-J, Cho J, et al. Discrimination of herbal mecidines according to geographical origin with near infrared reflectance spectroscopy and pattern recognition techniques. Journal of Pharmacceutical and Biomedical Analysis, 1999, 21:407~413
  • 2Woo Y-A, Cho C-H, Kim H-J, et al. Classification of cultivation years of Ginseng using near-infrared (NIR) reflectance spectroscopy. Near Infrared Analysis, 2000,1:19~22
  • 3Vapnik V. The Nature of Statistical Learning Theory. NY: Springer-Verlag, 1995
  • 4Guyon I, Weston J, Barnhill S, et al. Gene selection for cancer classfication using support vector machines. Machine Learning, 2002, 46(1): 389~422
  • 5Zhang X, Ke H. ALL/AML cancer classification by gene expression data using SVM and CSVM approach. Genome Informatics, 2000, 237~239
  • 6Ramaswamy S, Tamayo P, Riflin R, et al. Multiclass cancer diagnosis using tumor gene expression signatures. PNAS, 2001, 98(26): 15149~15154
  • 7Zhang X, Wong WH. Sample classification and gene selection based on SVM: method and software description, Technical Report, Department of Biostatistics, Harvard School of Public Health, 2001 (http://www.biostat.harvard.edu/~xzhang/R-SVM/R-SVM. html)
  • 8Collobert R, Bengio S. SVMTorch: support vector machines for large-scale regression problems. Journal of Machine Learning Research, 2001, 1:143~160 (http://www.idiap.ch/learning/SVMTorch. html)
  • 9Duda RO, Hart PE, Stork DG. Pattern Classification (2nd edition). NY: John Wiley & Sons, 2001
  • 10刘大江.窖泥中氨基酸含量对其曲酒质量的影响(第一报)窖泥成分对酒质影响的研究[J].酿酒科技,1987,(4):2-5.

共引文献43

同被引文献16

引证文献1

二级引证文献25

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部