计算机技术与发展Issue(5)：192-195,4.DOI:10.3969/j.issn.1673-629X.2015.05.045
基于扩散映射和LDA的辛味中药材鉴别研究
Research on Classification of Pungent Chinese Herbal Medicines Based on Diffusion Maps and LDA
摘要
Abstract
An Electronic nose ( E-nose) was employed to collect the smell print of different kinds of pungent Chinese herbal medicines. For the high-dimensional and nonlinear of odor data,propose a method based on Diffusion Maps and LDA for the identification of pun-gent Chinese herbal medicines. Firstly,the collected odor data was reconstructed to the high-dimensional space,using the Diffusion Maps algorithm to extract the low-dimensional manifold features embedded in the high-dimensional odor data. Then the LDA algorithm was employed to implement a linear classifier. The results show that the combination of Diffusion Maps and LDA algorithm can well distin-guish four different kinds of pungent Chinese herbal medicines,which provides a new way for the classification and identification of Chi-nese herbal medicines.关键词
电子鼻/辛味中药材/扩散映射/线性判别分析/分类鉴别Key words
Electronic nose ( E-nose)/pungent Chinese herbal medicines/Diffusion Maps/LDA/classification and identification分类
信息技术与安全科学引用本文复制引用
陈惠勤,骆德汉..基于扩散映射和LDA的辛味中药材鉴别研究[J].计算机技术与发展,2015,(5):192-195,4.基金项目
广东省自然科学基金资助项目(S2011020002906) （S2011020002906）
