J4 ›› 2016, Vol. 33 ›› Issue (4): 392-398.

• 光谱 • 上一篇    下一篇

基于主成分分析和模糊识别方法的生物分子太赫兹光谱识别

陈涛   

  1. 桂林电子科技大学电子工程与自动化学院, 广西 桂林 541004
  • 收稿日期:2016-02-20 修回日期:2016-04-19 出版日期:2016-07-28 发布日期:2016-07-28
  • 通讯作者: 陈涛(1984-),广西桂林人,博士,讲师,研究生导师,主要从事太赫兹科学技术及应用的研究。 E-mail:tchen@mail.hzau.edu.cn

Terahertz Spectra Identification of Biomolecules Based on PCA and Fuzzy Recognition

Chen Tao   

  1. School of Electronic Engineering and Automation, Guilin University of Electronic Technology, Guilin 541004, China
  • Received:2016-02-20 Revised:2016-04-19 Published:2016-07-28 Online:2016-07-28

摘要: 提出了一种基于主成分分析(PCA)和模糊模式识别方法的生物分子太赫兹(THz)光谱识别方法,并采用多种典型糖类和氨基酸生物分子的太赫兹透射光谱作为实验介质证明所提方法的可行性和有效性。首先,运用PCA方法对生物分子太赫兹光谱数据做降维处理,提取样品太赫兹光谱特征信息;然后,用获得的主成分得分矩阵代替原始太赫兹光谱数据输入到模糊模式识别分析模型中,运用基于择近原则的模糊模式识别方法对待定样品进行分类识别。实验结果表明以生物分子的太赫兹光谱作为数据特征,采用PCA与模糊识别相结合的方法实现生物分子的检测和识别是可行的,该方法为太赫兹光谱技术用于生物分子的鉴定和识别提供了一种新的有效的分析方法。

关键词: 模糊模式识别

Abstract: A method to identify terahertz (THz) spectra of biomolecules is proposed based on principal component analysis (PCA) and fuzzy pattern recognition in this paper, and THz spectra of several typical saccharide and amino acid biomolecules are used to verify its effectiveness and feasibility. First, PCA is used to decrease the dimensionality of original THz spectra variables and extract data features. Second, instead of the initial THz spectra variables the selected principal component score matrix is input into the model of fuzzy pattern recognition, fuzzy recognition based on principle of fuzzy closeness optimization is employed successfully to identify these samples. The results show that the method to identify biomolecules is feasible which combines PCA and fuzzy pattern recognition based on their THz spectra. The presented method offers a new effective approach in the field of biomolecules detection by using THz spectroscopy.

Key words: Fuzzy pattern recognition

中图分类号: