Prediction of human assessments of odor using electronic nose and neural networks

Fangle Chang, Paul Heinz Heinemann

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Use of instruments instead of human panels to assess odors can save money and make the collection process more efficient. In this work, an electronic nose comprising of an array of 32 internal polymer sensors was applied to collect measurements from dairy farm odor sources. Artificial neural networks using the Levenberg-Maerquardt Back-propagation algorithm were used to build prediction models to predict human response to odor pleasantness on a generic hedonic scale that ranged from -11 (extremely unpleasant) to +11 (extremely pleasant). Forward selection (FS), Gamma Test (GT), and Principal Component Analysis (PCA) were used to reduce the noise of the measurements. For 28 input candidates, eight variables were selected using GT, and nine variables were selected using FS and PCA, respectively. GT-LMBNN was considered as the highest accurate model based on the probability of separate validation results falling within the human assessments range.

Original languageEnglish (US)
Title of host publicationAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2015
PublisherAmerican Society of Agricultural and Biological Engineers
Pages899-911
Number of pages13
Volume2
ISBN (Electronic)9781510810501
StatePublished - Jan 1 2015
EventAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2015 - New Orleans, United States
Duration: Jul 26 2015Jul 29 2015

Other

OtherAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2015
CountryUnited States
CityNew Orleans
Period7/26/157/29/15

Fingerprint

electronic nose
Odors
neural networks
odors
Neural networks
Principal component analysis
prediction
principal component analysis
Dairies
Backpropagation algorithms
testing
dairy farming
Farms
sensors (equipment)
polymers
Polymers
Sensors
Electronic nose

All Science Journal Classification (ASJC) codes

  • Bioengineering
  • Agronomy and Crop Science

Cite this

Chang, F., & Heinemann, P. H. (2015). Prediction of human assessments of odor using electronic nose and neural networks. In American Society of Agricultural and Biological Engineers Annual International Meeting 2015 (Vol. 2, pp. 899-911). American Society of Agricultural and Biological Engineers.
Chang, Fangle ; Heinemann, Paul Heinz. / Prediction of human assessments of odor using electronic nose and neural networks. American Society of Agricultural and Biological Engineers Annual International Meeting 2015. Vol. 2 American Society of Agricultural and Biological Engineers, 2015. pp. 899-911
@inproceedings{e9e1e19ea5c04a5fa21d104d2ecd186e,
title = "Prediction of human assessments of odor using electronic nose and neural networks",
abstract = "Use of instruments instead of human panels to assess odors can save money and make the collection process more efficient. In this work, an electronic nose comprising of an array of 32 internal polymer sensors was applied to collect measurements from dairy farm odor sources. Artificial neural networks using the Levenberg-Maerquardt Back-propagation algorithm were used to build prediction models to predict human response to odor pleasantness on a generic hedonic scale that ranged from -11 (extremely unpleasant) to +11 (extremely pleasant). Forward selection (FS), Gamma Test (GT), and Principal Component Analysis (PCA) were used to reduce the noise of the measurements. For 28 input candidates, eight variables were selected using GT, and nine variables were selected using FS and PCA, respectively. GT-LMBNN was considered as the highest accurate model based on the probability of separate validation results falling within the human assessments range.",
author = "Fangle Chang and Heinemann, {Paul Heinz}",
year = "2015",
month = "1",
day = "1",
language = "English (US)",
volume = "2",
pages = "899--911",
booktitle = "American Society of Agricultural and Biological Engineers Annual International Meeting 2015",
publisher = "American Society of Agricultural and Biological Engineers",
address = "United States",

}

Chang, F & Heinemann, PH 2015, Prediction of human assessments of odor using electronic nose and neural networks. in American Society of Agricultural and Biological Engineers Annual International Meeting 2015. vol. 2, American Society of Agricultural and Biological Engineers, pp. 899-911, American Society of Agricultural and Biological Engineers Annual International Meeting 2015, New Orleans, United States, 7/26/15.

Prediction of human assessments of odor using electronic nose and neural networks. / Chang, Fangle; Heinemann, Paul Heinz.

American Society of Agricultural and Biological Engineers Annual International Meeting 2015. Vol. 2 American Society of Agricultural and Biological Engineers, 2015. p. 899-911.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Prediction of human assessments of odor using electronic nose and neural networks

AU - Chang, Fangle

AU - Heinemann, Paul Heinz

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Use of instruments instead of human panels to assess odors can save money and make the collection process more efficient. In this work, an electronic nose comprising of an array of 32 internal polymer sensors was applied to collect measurements from dairy farm odor sources. Artificial neural networks using the Levenberg-Maerquardt Back-propagation algorithm were used to build prediction models to predict human response to odor pleasantness on a generic hedonic scale that ranged from -11 (extremely unpleasant) to +11 (extremely pleasant). Forward selection (FS), Gamma Test (GT), and Principal Component Analysis (PCA) were used to reduce the noise of the measurements. For 28 input candidates, eight variables were selected using GT, and nine variables were selected using FS and PCA, respectively. GT-LMBNN was considered as the highest accurate model based on the probability of separate validation results falling within the human assessments range.

AB - Use of instruments instead of human panels to assess odors can save money and make the collection process more efficient. In this work, an electronic nose comprising of an array of 32 internal polymer sensors was applied to collect measurements from dairy farm odor sources. Artificial neural networks using the Levenberg-Maerquardt Back-propagation algorithm were used to build prediction models to predict human response to odor pleasantness on a generic hedonic scale that ranged from -11 (extremely unpleasant) to +11 (extremely pleasant). Forward selection (FS), Gamma Test (GT), and Principal Component Analysis (PCA) were used to reduce the noise of the measurements. For 28 input candidates, eight variables were selected using GT, and nine variables were selected using FS and PCA, respectively. GT-LMBNN was considered as the highest accurate model based on the probability of separate validation results falling within the human assessments range.

UR - http://www.scopus.com/inward/record.url?scp=84951807094&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84951807094&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84951807094

VL - 2

SP - 899

EP - 911

BT - American Society of Agricultural and Biological Engineers Annual International Meeting 2015

PB - American Society of Agricultural and Biological Engineers

ER -

Chang F, Heinemann PH. Prediction of human assessments of odor using electronic nose and neural networks. In American Society of Agricultural and Biological Engineers Annual International Meeting 2015. Vol. 2. American Society of Agricultural and Biological Engineers. 2015. p. 899-911