基于电子鼻传感器阵列优化的甜玉米种子活力检测

针对甜玉米种子活力传统检测方法操作繁琐、重复性差等不足,该研究利用电子鼻技术建立甜玉米种子活力快速检测方法.利用电子鼻获取不同活力甜玉米种子的气味信息,再结合主成分分析（PCA,principal component analysis）、线性判别分析（LDA,linear discriminant analysis）、载荷分析（loadings）和支持向量机（SVM,support vector machine）对气味信息进行提取分析,建立甜玉米种子活力的定性定量分析模型.结果显示：PCA和LDA分析均无法区分不同活力的甜玉米种子,而SVM的鉴别效果较好.全传感器阵列数据集SVM分类判别模型训...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 33; no. 21; pp. 275 - 281
Main Author 张婷婷 孙群 杨磊 杨丽明 王建华
Format Journal Article
LanguageChinese
Published 中国农业大学农学院作物遗传育种与种子科学系/北京市作物遗传改良重点实验室,北京,100193%中国农业大学理学院,北京,100083 2017
Subjects
优化
传感器
支持向量机
活力
甜玉米种子
电子鼻
支持向量机
电子鼻
support vector machine
sensors
sweet corn seed
optimization
甜玉米种子
优化
vigor
electronic nose
传感器
活力
Online AccessGet full text
ISSN1002-6819
DOI10.11975/j.issn.1002-6819.2017.21.034

Cover

More Information
Summary:针对甜玉米种子活力传统检测方法操作繁琐、重复性差等不足,该研究利用电子鼻技术建立甜玉米种子活力快速检测方法.利用电子鼻获取不同活力甜玉米种子的气味信息,再结合主成分分析（PCA,principal component analysis）、线性判别分析（LDA,linear discriminant analysis）、载荷分析（loadings）和支持向量机（SVM,support vector machine）对气味信息进行提取分析,建立甜玉米种子活力的定性定量分析模型.结果显示：PCA和LDA分析均无法区分不同活力的甜玉米种子,而SVM的鉴别效果较好.全传感器阵列数据集SVM分类判别模型训练集和预测集正确率分别为97.10%和96.67%,建模时间为30.75 s,回归预测模型训练集和预测集决定系数R2分别为0.993和0.913,均方差误差分别为2.23%和8.50%.经Loadings分析将10个传感器阵列优化为6个.优化后传感器阵列数据集SVM分类判别模型训练集和预测集正确率分别为98.55%和96.67%,建模时间为21.81 s,回归预测模型训练集和预测集决定系数R2分别为0.982和0.984,均方差误差分别为3.80%和3.01%.结果表明：基于SVM的电子鼻技术可以实现对不同活力甜玉米种子的高效判别和预测,将传感器阵列优化为6个,判别和预测效果均有所提升.该研究为电子鼻技术应用于甜玉米种子活力检测提供理论依据.
Bibliography:11-2047/S
Nondestructive testing equipment is important for the detection of seed vigor. However, there are few studies based on nondestructive testing equipment in sweet corn seed vigor. Therefore, developing an effective and reliable system for the detection of seed vigor has a certain practical significance. As a bionic electronic system, electronic nose （E-nose） detects the vigor of seed qualitatively and quantitatively through the analysis of sample volatile gas＆#39;s fingerprint information. So it is pretty suitable for sweet corn seed detection, though sweet corn seed＆#39;s odor is comprised of complicated compositions and small differences exist among seeds with different vigor, which makes the detection difficult. Given that, this paper proposed a monitoring method of sweet corn seed vigor based on E-nose. Five samples of sweet corn seeds with different vigor （germination percentages were 83.3%, 70.8%, 54.2%, 38.4% and 3.8%） were detected by E-nose. Principal component analysis （PCA） and linear discri
ISSN:1002-6819
DOI:10.11975/j.issn.1002-6819.2017.21.034