Ann-integrated electronic nose and zNose™ system for apple quality evaluation

Changying Li, Paul H. Heinemann

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The fresh produce industry generates more than one billion dollars each year in the U.S. market. However, fresh produce departments in grocery stores experience as much as 10% loss because the apples contain undetected defects and deteriorate in quality before they can be sold. Apple defects can create sites for pathogen development, which can cause foodborne illness. It is important to develop a non-destructive system for rapid detection and classification of defective fresh produce. In this study, an artificial neural network (ANN) based electronic nose and zNose™ system was developed to detect physically damaged apples. Principal component analysis was used for clustering plot and feature extraction. The first five principal components were selected for the electronic nose data input, and the first ten principal components were selected for the zNose™ spectrum data. Different ANN models, back-propagation networks (BP), probabilistic neural networks (PNN), and learning vector quantification networks (LVQ), were built and compared based on their classification accuracy, sensitivity and specificity, generalization, and incremental learning performance. For the Enose data, the BP and PNN classification rate of 85.3% and 85.1%, respectively, was better than the LVQ classification rate of 73.7%; for the zNose™ data, the three ANN models had similar performances, which were less favorable than the Enose, with classification rates of 77%, 76.8% and 74.3%. The three ANN models' performances were also measured by their sensitivity, specificity, generalization, and incremental learning.

Original languageEnglish (US)
Pages (from-to)2285-2294
Number of pages10
JournalTransactions of the ASABE
Volume50
Issue number6
StatePublished - Nov 1 2007

Fingerprint

Electronic Nose
electronic nose
Malus
neural networks
apples
artificial neural network
Neural Networks (Computer)
Neural networks
learning
fresh produce
Learning
back propagation
defect
Backpropagation
Sensitivity and Specificity
Foodborne Diseases
grocery stores
Defects
Principal Component Analysis
Pathogens

All Science Journal Classification (ASJC) codes

  • Forestry
  • Food Science
  • Biomedical Engineering
  • Agronomy and Crop Science
  • Soil Science

Cite this

@article{3e0135807db54be9aa9493da43de05b1,
title = "Ann-integrated electronic nose and zNose™ system for apple quality evaluation",
abstract = "The fresh produce industry generates more than one billion dollars each year in the U.S. market. However, fresh produce departments in grocery stores experience as much as 10{\%} loss because the apples contain undetected defects and deteriorate in quality before they can be sold. Apple defects can create sites for pathogen development, which can cause foodborne illness. It is important to develop a non-destructive system for rapid detection and classification of defective fresh produce. In this study, an artificial neural network (ANN) based electronic nose and zNose™ system was developed to detect physically damaged apples. Principal component analysis was used for clustering plot and feature extraction. The first five principal components were selected for the electronic nose data input, and the first ten principal components were selected for the zNose™ spectrum data. Different ANN models, back-propagation networks (BP), probabilistic neural networks (PNN), and learning vector quantification networks (LVQ), were built and compared based on their classification accuracy, sensitivity and specificity, generalization, and incremental learning performance. For the Enose data, the BP and PNN classification rate of 85.3{\%} and 85.1{\%}, respectively, was better than the LVQ classification rate of 73.7{\%}; for the zNose™ data, the three ANN models had similar performances, which were less favorable than the Enose, with classification rates of 77{\%}, 76.8{\%} and 74.3{\%}. The three ANN models' performances were also measured by their sensitivity, specificity, generalization, and incremental learning.",
author = "Changying Li and Heinemann, {Paul H.}",
year = "2007",
month = "11",
day = "1",
language = "English (US)",
volume = "50",
pages = "2285--2294",
journal = "Transactions of the ASABE",
issn = "2151-0032",
publisher = "American Society of Agricultural and Biological Engineers",
number = "6",

}

Ann-integrated electronic nose and zNose™ system for apple quality evaluation. / Li, Changying; Heinemann, Paul H.

In: Transactions of the ASABE, Vol. 50, No. 6, 01.11.2007, p. 2285-2294.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Ann-integrated electronic nose and zNose™ system for apple quality evaluation

AU - Li, Changying

AU - Heinemann, Paul H.

PY - 2007/11/1

Y1 - 2007/11/1

N2 - The fresh produce industry generates more than one billion dollars each year in the U.S. market. However, fresh produce departments in grocery stores experience as much as 10% loss because the apples contain undetected defects and deteriorate in quality before they can be sold. Apple defects can create sites for pathogen development, which can cause foodborne illness. It is important to develop a non-destructive system for rapid detection and classification of defective fresh produce. In this study, an artificial neural network (ANN) based electronic nose and zNose™ system was developed to detect physically damaged apples. Principal component analysis was used for clustering plot and feature extraction. The first five principal components were selected for the electronic nose data input, and the first ten principal components were selected for the zNose™ spectrum data. Different ANN models, back-propagation networks (BP), probabilistic neural networks (PNN), and learning vector quantification networks (LVQ), were built and compared based on their classification accuracy, sensitivity and specificity, generalization, and incremental learning performance. For the Enose data, the BP and PNN classification rate of 85.3% and 85.1%, respectively, was better than the LVQ classification rate of 73.7%; for the zNose™ data, the three ANN models had similar performances, which were less favorable than the Enose, with classification rates of 77%, 76.8% and 74.3%. The three ANN models' performances were also measured by their sensitivity, specificity, generalization, and incremental learning.

AB - The fresh produce industry generates more than one billion dollars each year in the U.S. market. However, fresh produce departments in grocery stores experience as much as 10% loss because the apples contain undetected defects and deteriorate in quality before they can be sold. Apple defects can create sites for pathogen development, which can cause foodborne illness. It is important to develop a non-destructive system for rapid detection and classification of defective fresh produce. In this study, an artificial neural network (ANN) based electronic nose and zNose™ system was developed to detect physically damaged apples. Principal component analysis was used for clustering plot and feature extraction. The first five principal components were selected for the electronic nose data input, and the first ten principal components were selected for the zNose™ spectrum data. Different ANN models, back-propagation networks (BP), probabilistic neural networks (PNN), and learning vector quantification networks (LVQ), were built and compared based on their classification accuracy, sensitivity and specificity, generalization, and incremental learning performance. For the Enose data, the BP and PNN classification rate of 85.3% and 85.1%, respectively, was better than the LVQ classification rate of 73.7%; for the zNose™ data, the three ANN models had similar performances, which were less favorable than the Enose, with classification rates of 77%, 76.8% and 74.3%. The three ANN models' performances were also measured by their sensitivity, specificity, generalization, and incremental learning.

UR - http://www.scopus.com/inward/record.url?scp=38549141695&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38549141695&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:38549141695

VL - 50

SP - 2285

EP - 2294

JO - Transactions of the ASABE

JF - Transactions of the ASABE

SN - 2151-0032

IS - 6

ER -