吉林大学学报(信息科学版)

• 论文 • 上一篇    下一篇

用于中药人参品类鉴别的算法研究及硬件实现

王 萌, 赵培陆, 田丽媛, 王 莲, 卢革宇   

  1. 吉林大学 电子科学与工程学院, 长春 130012
  • 收稿日期:2016-12-21 出版日期:2017-05-25 发布日期:2017-06-07
  • 通讯作者: 卢革宇(1963— ), 男, 黑龙江海伦人, 吉林大学教授, 博士生导师, 主要从事 先进传感技术研究, (Tel)86-13578629546(E-mail)lugy@ jlu. edu. cn。
  • 作者简介:萌(1988— ), 女, 山东枣庄人, 吉林大学硕士研究生, 主要从事先进传感器应用研究, (Tel)86-18744017085(E-mail) wangmeng_jlu2016@163. com。
  • 基金资助:
     国家自然科学基金资助项目(61374218; 61134010; 61327804); 教育部“长江学者和创新团队发展计划冶创新团队基金资助
    项目(IRT13018); 国家高技术研究发展计划基金资助项目(863 计划, 2013AA030902; 2014AA06A505); 吉林大学研究生
    创新基金资助项目(2016087)

Research of Algorithm and Implementation of Hardware System for Identification of Traditional Chinese Medicine Ginseng

WANG Meng, ZHAO Peilu, TIAN Liyuan, WANG Lian, LU Geyu   

  1. College of Electronic Science and Engineering, Jilin University, Changchun 130012, China
  • Received:2016-12-21 Online:2017-05-25 Published:2017-06-07

摘要: 提高人参品类的鉴别效果, 研制了一套智能化自动检测系统。 该系统硬件主要包括气体传感器阵列的
驱动电路、 信号调理和数据采集电路、 信息处理单元电路、 进气部分电路控制电路、 外部接口电路。 该系统使
用主成分分析(PCA: Principal Component Analysis)与支持向量机(SVM: Support Vector Machine)相结合的算法
实现对人参品类的鉴别, 同时利用 PID(Proportion Integral Differential)算法实现对气室温度的智能控制, 提高了
气体传感器的稳定性和精确度。 使用该系统对红参、 白参、 西洋参、 太子参、 三七(小人参)以及外形与气味相
似的天花粉进行了多组测试。 实验结果表明, 该系统对人参品类的鉴别具有较高的准确度, 并且操作简单、
成本低廉, 具有良好的应用前景。

关键词: PCA 算法, 智能化系统, SVM 算法, 模式识别算法, 人参鉴别

Abstract: In order to realize the identification of panax ginseng, an intelligent automatic detection system is
developed. The hardware of the system mainly includes the driving circuit of the gas sensor array, signal
collecting and conditioning circuit, information processing circuit, air inlet part control circuit and external
interface circuit. The system uses PCA (Principal Component Analysis) and SVM (Support Vector Machine)
algorithm to realize the identification of ginseng category. The intelligent control of the temperature of the gas
chamber is realized by PID (Proportion Integral Differential) algorithm. And the stability and Accuracy of the
gas sensor is improved. The results showed that the system had high accuracy in the identification of Panax
ginseng. The red ginseng, white ginseng, American ginseng, heterophylla, Panax notoginseng and the
trichosanthin of similar shape and odor are used to test by the system. The experimental results show that the
system has a high accuracy in the identification of ginseng, and it is simple in operation and the cost is low, and
has good application prospect.

Key words: support vector machine (SVM), the pattern recognition algorithm, principal component analysis (PCA), ginseng identification, the intelligent system

中图分类号: 

  •