Electronic Nose Based on Independent Component Analysis Combined with Partial Least Squares and Artificial Neural Networks for Wine Prediction

Teodoro Aguilera; Jesús Lozano; José A. Paredes; Francisco J. Alvarez; José I. Suárez

doi:103390/s120608055

Electronic Nose Based on Independent Component Analysis Combined with Partial Least Squares and Artificial Neural Networks for Wine Prediction

Teodoro Aguilera, Jesús Lozano, José A. Paredes, Francisco J. Alvarez, José I. Suárez

Wright State University

Research output: Contribution to journal › Article › peer-review

Abstract

<p> The aim of this work is to propose an alternative way for wine classi&filig;cation and prediction based on an electronic nose (e-nose) combined with Independent Component Analysis (ICA) as a dimensionality reduction technique, Partial Least Squares (PLS) to predict sensorial descriptors and Arti&filig;cial Neural Networks (ANNs) for classi&filig;cation purpose. A total of 26 wines from different regions, varieties and elaboration processes have been analyzed with an e-nose and tasted by a sensory panel. Successful results have been obtained in most cases for prediction and classi&filig;cation.</p>

Original language	American English
Journal	Sensors
Volume	12
DOIs	https://doi.org/103390/s120608055
State	Published - Jan 1 2012

Keywords

artiﬁcial neural networks
electronic nose
independent component analysis
partial least squares
wine classiﬁcation

Disciplines

Medical Cell Biology
Medical Neurobiology
Medical Physiology
Medical Sciences
Medicine and Health Sciences
Neurosciences
Physiological Processes

Access to Document

103390/s120608055License: Unspecified

Electronic Nose Based on Independent Component Analysis CombinedFinal published version, 2.41 MBLicense: Unspecified

Cite this

@article{efb1c4e8758745f88034db5ac3cb458a,

title = "Electronic Nose Based on Independent Component Analysis Combined with Partial Least Squares and Artificial Neural Networks for Wine Prediction",

abstract = " The aim of this work is to propose an alternative way for wine classi&filig;cation and prediction based on an electronic nose (e-nose) combined with Independent Component Analysis (ICA) as a dimensionality reduction technique, Partial Least Squares (PLS) to predict sensorial descriptors and Arti&filig;cial Neural Networks (ANNs) for classi&filig;cation purpose. A total of 26 wines from different regions, varieties and elaboration processes have been analyzed with an e-nose and tasted by a sensory panel. Successful results have been obtained in most cases for prediction and classi&filig;cation.",

keywords = "artiﬁcial neural networks, electronic nose, independent component analysis, partial least squares, wine classiﬁcation",

author = "Teodoro Aguilera and Jes{\'u}s Lozano and Paredes, {Jos{\'e} A.} and Alvarez, {Francisco J.} and Su{\'a}rez, {Jos{\'e} I.}",

year = "2012",

month = jan,

day = "1",

doi = "103390/s120608055",

language = "American English",

volume = "12",

journal = "Sensors",

}

TY - JOUR

T1 - Electronic Nose Based on Independent Component Analysis Combined with Partial Least Squares and Artificial Neural Networks for Wine Prediction

AU - Aguilera, Teodoro

AU - Lozano, Jesús

AU - Paredes, José A.

AU - Alvarez, Francisco J.

AU - Suárez, José I.

PY - 2012/1/1

Y1 - 2012/1/1

N2 - The aim of this work is to propose an alternative way for wine classi&filig;cation and prediction based on an electronic nose (e-nose) combined with Independent Component Analysis (ICA) as a dimensionality reduction technique, Partial Least Squares (PLS) to predict sensorial descriptors and Arti&filig;cial Neural Networks (ANNs) for classi&filig;cation purpose. A total of 26 wines from different regions, varieties and elaboration processes have been analyzed with an e-nose and tasted by a sensory panel. Successful results have been obtained in most cases for prediction and classi&filig;cation.

AB - The aim of this work is to propose an alternative way for wine classi&filig;cation and prediction based on an electronic nose (e-nose) combined with Independent Component Analysis (ICA) as a dimensionality reduction technique, Partial Least Squares (PLS) to predict sensorial descriptors and Arti&filig;cial Neural Networks (ANNs) for classi&filig;cation purpose. A total of 26 wines from different regions, varieties and elaboration processes have been analyzed with an e-nose and tasted by a sensory panel. Successful results have been obtained in most cases for prediction and classi&filig;cation.

KW - artiﬁcial neural networks

KW - electronic nose

KW - independent component analysis

KW - partial least squares

KW - wine classiﬁcation

UR - https://corescholar.libraries.wright.edu/ncbp/530

U2 - 103390/s120608055

DO - 103390/s120608055

M3 - Article

VL - 12

JO - Sensors

JF - Sensors

ER -

Electronic Nose Based on Independent Component Analysis Combined with Partial Least Squares and Artificial Neural Networks for Wine Prediction

Abstract

Keywords

Disciplines

Access to Document

Other files and links

Cite this