Electronic nose and tongue for pet food classification

Viktória Éles, István Hullár, R. Romvári

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Commercial canned dog and cat foods (four type of each) were classified by electronic nose (EN) and tongue (ET) methods. The classification was performed by canonical discriminant analysis (DA) followed by cross-validation, using the ET and EN sensory values separately (7 and 18 sensors) and also jointly. The number of entered variables corresponding to the total number of sensors (n=25) were decreased by using a stepwise procedure during DA. First the dog and cat samples were classified than the discrimination were performed on the canned foods (eight type). Thereafter two groups were formed depending on the compositional characteristics of the foods (pure animal vs animal and plant origin), and finally these groups were divided into four subgroups according to the concerning species (dog vs cat). In general, the lowest discriminating results were achieved by the single application of ET method (58.3- 81.7 %). The highest classification power (85-98.3%, CV% 83.3-95.8) derived from the joint application of the two sensory methods. According to the results achieved, the common application of EN and ET technology seems to be a promising tool for the aroma classification of pet foods.

Original languageEnglish
Pages (from-to)225-228
Number of pages4
JournalAgriculturae Conspectus Scientificus
Volume78
Issue number3
Publication statusPublished - Sep 2013

Fingerprint

electronic tongue
Electronic Nose
pet foods
electronic nose
tongue
Pets
food
dogs
cats
taxonomy
Food
discriminant analysis
sensors (equipment)
electronics
Cats
canned foods
animals
Discriminant Analysis
Dogs
Tongue

Keywords

  • Cat
  • Classification
  • Dog
  • Electronic nose
  • Electronic tongue
  • Pet food

ASJC Scopus subject areas

  • Geophysics
  • Earth and Planetary Sciences(all)

Cite this

Electronic nose and tongue for pet food classification. / Éles, Viktória; Hullár, István; Romvári, R.

In: Agriculturae Conspectus Scientificus, Vol. 78, No. 3, 09.2013, p. 225-228.

Research output: Contribution to journalArticle

Éles, Viktória ; Hullár, István ; Romvári, R. / Electronic nose and tongue for pet food classification. In: Agriculturae Conspectus Scientificus. 2013 ; Vol. 78, No. 3. pp. 225-228.
@article{2c4bd7c1d7ae4482ab27350b8b36b3f7,
title = "Electronic nose and tongue for pet food classification",
abstract = "Commercial canned dog and cat foods (four type of each) were classified by electronic nose (EN) and tongue (ET) methods. The classification was performed by canonical discriminant analysis (DA) followed by cross-validation, using the ET and EN sensory values separately (7 and 18 sensors) and also jointly. The number of entered variables corresponding to the total number of sensors (n=25) were decreased by using a stepwise procedure during DA. First the dog and cat samples were classified than the discrimination were performed on the canned foods (eight type). Thereafter two groups were formed depending on the compositional characteristics of the foods (pure animal vs animal and plant origin), and finally these groups were divided into four subgroups according to the concerning species (dog vs cat). In general, the lowest discriminating results were achieved by the single application of ET method (58.3- 81.7 {\%}). The highest classification power (85-98.3{\%}, CV{\%} 83.3-95.8) derived from the joint application of the two sensory methods. According to the results achieved, the common application of EN and ET technology seems to be a promising tool for the aroma classification of pet foods.",
keywords = "Cat, Classification, Dog, Electronic nose, Electronic tongue, Pet food",
author = "Vikt{\'o}ria {\'E}les and Istv{\'a}n Hull{\'a}r and R. Romv{\'a}ri",
year = "2013",
month = "9",
language = "English",
volume = "78",
pages = "225--228",
journal = "Agriculturae Conspectus Scientificus",
issn = "1331-7768",
publisher = "University of Zagreb",
number = "3",

}

TY - JOUR

T1 - Electronic nose and tongue for pet food classification

AU - Éles, Viktória

AU - Hullár, István

AU - Romvári, R.

PY - 2013/9

Y1 - 2013/9

N2 - Commercial canned dog and cat foods (four type of each) were classified by electronic nose (EN) and tongue (ET) methods. The classification was performed by canonical discriminant analysis (DA) followed by cross-validation, using the ET and EN sensory values separately (7 and 18 sensors) and also jointly. The number of entered variables corresponding to the total number of sensors (n=25) were decreased by using a stepwise procedure during DA. First the dog and cat samples were classified than the discrimination were performed on the canned foods (eight type). Thereafter two groups were formed depending on the compositional characteristics of the foods (pure animal vs animal and plant origin), and finally these groups were divided into four subgroups according to the concerning species (dog vs cat). In general, the lowest discriminating results were achieved by the single application of ET method (58.3- 81.7 %). The highest classification power (85-98.3%, CV% 83.3-95.8) derived from the joint application of the two sensory methods. According to the results achieved, the common application of EN and ET technology seems to be a promising tool for the aroma classification of pet foods.

AB - Commercial canned dog and cat foods (four type of each) were classified by electronic nose (EN) and tongue (ET) methods. The classification was performed by canonical discriminant analysis (DA) followed by cross-validation, using the ET and EN sensory values separately (7 and 18 sensors) and also jointly. The number of entered variables corresponding to the total number of sensors (n=25) were decreased by using a stepwise procedure during DA. First the dog and cat samples were classified than the discrimination were performed on the canned foods (eight type). Thereafter two groups were formed depending on the compositional characteristics of the foods (pure animal vs animal and plant origin), and finally these groups were divided into four subgroups according to the concerning species (dog vs cat). In general, the lowest discriminating results were achieved by the single application of ET method (58.3- 81.7 %). The highest classification power (85-98.3%, CV% 83.3-95.8) derived from the joint application of the two sensory methods. According to the results achieved, the common application of EN and ET technology seems to be a promising tool for the aroma classification of pet foods.

KW - Cat

KW - Classification

KW - Dog

KW - Electronic nose

KW - Electronic tongue

KW - Pet food

UR - http://www.scopus.com/inward/record.url?scp=84883503582&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883503582&partnerID=8YFLogxK

M3 - Article

VL - 78

SP - 225

EP - 228

JO - Agriculturae Conspectus Scientificus

JF - Agriculturae Conspectus Scientificus

SN - 1331-7768

IS - 3

ER -