应用独立组分分析解析红外光谱  

Resolution of IR Spectra by Using Independent Component Analysis

作　　者：刘广军[1] 

机构地区：[1]济宁师专化学系,山东济宁272025

出　　处：《琼州大学学报》2005年第2期14-18,共5页Journal of Qiongzhou University

摘　　要：独立组分分析(Independent Component Analysis,ICA)应用于混合红外光谱定性分析。其主要优点在于可从未知混合光谱中分离出独立组分的光谱,且这种分离是盲源分离,混合物的组成事先是未知的.对ICA在正已醇、丙酮和正丁醇的混合中红外光谱分离中的应用进行了研究,验证了体系的独立性,并对ICA算法做了一定的改进,讨论了各种预处理方法对其分离结果的误差.A new method is presented to separate the IR spectrum based on the independent component analysis (ICA) .The main advantage of this method is that it is able to separate the spectra of the constitute components from the mixed spectra. The separation is a blind source separation, since the constitute components of mixtures was unknown. ICA was used to process the mixed system of alcohol, acetone and n - butyl alcohol in this paper. The author also discussed the effect of various preprocess methods to the result of ICA and developed the ICA algorithm by adding PCA in front of ICA.

关 键 词：独立组分分析 红外光谱 应用 Analysis 解析 光谱定性分析 ICA算法 预处理方法 混合光谱 盲源分离 光谱分离 混合物 正已醇 中红外 正丁醇 独立性 

分 类 号：TN911.7[电子电信—通信与信息系统] O657.33[电子电信—信息与通信工程]