不同产地和采收期的中药材电子鼻鉴别研究  

Discrimination of Chinese Herbal Medicines from Different Growing Areas and Harvesting Dates Based on E-Nose

作　　者：伍世元[1] 骆德汉[1] 邓炳荣[1] 赵庆辉[1] 

机构地区：[1]广东工业大学信息工程学院,广州510006

出　　处：《传感技术学报》2011年第1期10-13,共4页Chinese Journal of Sensors and Actuators

基　　金：2009年国家自然科学基金资助"基于仿生嗅觉的辛味中药材气味指纹图谱研究"(60971105)

摘　　要：不同产地和采收期的同种中药材在感官上很难区分。提出一种在自然态下采用PEN3电子鼻鉴别不同产地和采收期中药材的方法。首先通过电子鼻获取样本的气味信息,综合气味信息各方面的特征组成一个特征集合,采用逆向反馈方法提取特征,获得最能区别样品的特征子集,利用PCA+LDA算法对样本进行分类,最后运用欧式距离、马氏距离对未知样本进行鉴别。对未知样本的识别正确率达100%,证明采用电子鼻对中药材质量进行评判是可行的。为中药材质量控制提供了一种新的手段。It is difficult to distinguish the same kind of Chinese herbal medicines（CHMs）with different growing areas and harvesting dates.An electronic nose（E-nose）PEN3 was used to discriminate the CHMs with different growing areas and harvesting dates under natural state.Firstly,odor information of samples was obtained by E-nose,and feature set was constituted by all aspects of the representative characteristics of odor information.Then,negative feedback was applied to extract features,and the most effective feature subset was determined.PCA＋LDA was used to classify samples,finally,unknown samples were identified by using Euclidean distance,Mahalanobis distance.Identification of unknown samples was up to 100% accuracy,showing that it is feasible to evaluate the quality of the CHMs used e-nose.The paper provides a new method for quality control of CHMs.

关 键 词：电子鼻 中药材 特征提取与选择 PCA+LDA算法 质量控制 

分 类 号：TP212[自动化与计算机技术—检测技术与自动化装置] R282.5[自动化与计算机技术—控制科学与工程]