您好，欢迎访问北京市农林科学院 机构知识库！
北京市农林科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Electronic Nose-Based Technique for Rapid Detection and Recognition of Moldy Apples

文献类型： 外文期刊

作者： Jia, Wenshen 1 ; Liang, Gang 1 ; Tian, Hui 1 ; Sun, Jing 5 ; Wan, Cihui 1 ;

作者机构： 1.Beijing Acad Agr & Forestry Sci, Beijing Res Ctr Agr Stand & Testing, Beijing 100097, Peoples R China

2.Minist Agr, Risk Assessment Lab Agroprod Beijing, Beijing 100097, Peoples R China

3.Beijing Municipal Key Lab Agr Environm Monitoring, Beijing 100197, Peoples R China

4.Minist Agr & Rural Affairs, Key Lab Urban Agr North China, Beijing 100097, Peoples R China

5.Chinese Acad Agr Engn, Beijing 100121, Peoples R China

6.Minist Agr, Key Lab Agroprod Postharvest Handling, Beijing 100121, Peoples R China

关键词： electronic nose; apple; mildew; pattern recognition; artificial neural network; nondestructive examination

期刊名称：SENSORS （ 影响因子：3.576； 五年影响因子：3.735 ）

ISSN： 1424-8220

年卷期： 2019 年 19 卷 7 期

页码：

收录情况： SCI

摘要： In this study, the PEN3 electronic nose was used to detect and recognize fresh and moldy apples inoculated with Penicillium expansum and Aspergillus niger, taking Golden Delicious apples as the model subject. Firstly, the apples were divided into two groups: individual apple inoculated only with/without different molds (Group A) and mixed apples of inoculated apples with fresh apples (Group B). Then, the characteristic gas sensors of the PEN3 electronic nose that were most closely correlated with the flavor information of the moldy apples were optimized and determined to simplify the analysis process and improve the accuracy of the results. Four pattern recognition methods, including linear discriminant analysis (LDA), backpropagation neural network (BPNN), support vector machines (SVM), and radial basis function neural network (RBFNN), were applied to analyze the data obtained from the characteristic sensors, aiming at establishing the prediction model of the flavor information and fresh/moldy apples. The results showed that only the gas sensors of W1S, W2S, W5S, W1W, and W2W in the PEN3 electronic nose exhibited a strong signal response to the flavor information, indicating most were closely correlated with the characteristic flavor of apples and thus the data obtained from these characteristic sensors were used for modeling. The results of the four pattern recognition methods showed that BPNN had the best prediction performance for the training and testing sets for both Groups A and B, with prediction accuracies of 96.3% and 90.0% (Group A), 77.7% and 72.0% (Group B), respectively. Therefore, we demonstrate that the PEN3 electronic nose not only effectively detects and recognizes fresh and moldy apples, but also can distinguish apples inoculated with different molds.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：北京市农林科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台