Kajian awal penggunaan jaringan neural tiruan (ANN) bagi menentukan nilai peroksida tiga minyak sawit komersil berdasarkan spektrum FTIR

Translated title of the contribution: Preliminary study on application of artificial neural networks (ANN) for determining the peroxide value of three commercial palm oil based FTIR spectrum

Mohamad Azwani Shah Mat Lazim, Musa Ahmad, Zuriati Zakaria, Mohd. Suzeren Md. Jamil, Suria Ramli, Faiz Zainuddin, Mohd Nasir Taib, M. Nasir Mat Arip

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Peroxide value is one of the measurements that being used to determine the peroxide in oil samples produce from the peroxide compund and hydroperoxide group at the primary level of lipid oxidation. In this study, 3 commercial palm cooking oils were selected and labeled as A, B and C. Two different conditions were applied to the samples. First, the oil sample was exposed to the air for three months (labeled as A) while samples B and C were used for frying for many times. Two inputs from FTIR spectra (3444 cm-1 and 3450 cm-1) were chosen for the ANN training. The suitable architecture for this training is 2:20:1. The prediction made by ANN was very accurate and compatible to the result which obtained from the standard method. A low average error (0.48) was obtained when the hidden neuron (20) and the epochs (300) were used.

Original languageUndefined/Unknown
Pages (from-to)376-386
Number of pages11
JournalMalaysian Journal of Analytical Sciences
Volume17
Issue number3
Publication statusPublished - 2013

Fingerprint

Peroxides
Neural networks
Oils
Cooking
Hydrogen Peroxide
Neurons
Lipids
Oxidation
Air
palm oil

Keywords

  • ANN
  • FTIR
  • Palm oil
  • Peroxide value

ASJC Scopus subject areas

  • Analytical Chemistry

Cite this

Kajian awal penggunaan jaringan neural tiruan (ANN) bagi menentukan nilai peroksida tiga minyak sawit komersil berdasarkan spektrum FTIR. / Mat Lazim, Mohamad Azwani Shah; Ahmad, Musa; Zakaria, Zuriati; Md. Jamil, Mohd. Suzeren; Ramli, Suria; Zainuddin, Faiz; Taib, Mohd Nasir; Nasir Mat Arip, M.

In: Malaysian Journal of Analytical Sciences, Vol. 17, No. 3, 2013, p. 376-386.

Research output: Contribution to journalArticle

@article{638eb276782b4e1c951f6cb589081a6b,
title = "Kajian awal penggunaan jaringan neural tiruan (ANN) bagi menentukan nilai peroksida tiga minyak sawit komersil berdasarkan spektrum FTIR",
abstract = "Peroxide value is one of the measurements that being used to determine the peroxide in oil samples produce from the peroxide compund and hydroperoxide group at the primary level of lipid oxidation. In this study, 3 commercial palm cooking oils were selected and labeled as A, B and C. Two different conditions were applied to the samples. First, the oil sample was exposed to the air for three months (labeled as A) while samples B and C were used for frying for many times. Two inputs from FTIR spectra (3444 cm-1 and 3450 cm-1) were chosen for the ANN training. The suitable architecture for this training is 2:20:1. The prediction made by ANN was very accurate and compatible to the result which obtained from the standard method. A low average error (0.48) was obtained when the hidden neuron (20) and the epochs (300) were used.",
keywords = "ANN, FTIR, Palm oil, Peroxide value",
author = "{Mat Lazim}, {Mohamad Azwani Shah} and Musa Ahmad and Zuriati Zakaria and {Md. Jamil}, {Mohd. Suzeren} and Suria Ramli and Faiz Zainuddin and Taib, {Mohd Nasir} and {Nasir Mat Arip}, M.",
year = "2013",
language = "Undefined/Unknown",
volume = "17",
pages = "376--386",
journal = "Malaysian Journal of Analytical Sciences",
issn = "1394-2506",
publisher = "Faculty of Science and Technology, Universiti Kebangsaan Malaysia",
number = "3",

}

TY - JOUR

T1 - Kajian awal penggunaan jaringan neural tiruan (ANN) bagi menentukan nilai peroksida tiga minyak sawit komersil berdasarkan spektrum FTIR

AU - Mat Lazim, Mohamad Azwani Shah

AU - Ahmad, Musa

AU - Zakaria, Zuriati

AU - Md. Jamil, Mohd. Suzeren

AU - Ramli, Suria

AU - Zainuddin, Faiz

AU - Taib, Mohd Nasir

AU - Nasir Mat Arip, M.

PY - 2013

Y1 - 2013

N2 - Peroxide value is one of the measurements that being used to determine the peroxide in oil samples produce from the peroxide compund and hydroperoxide group at the primary level of lipid oxidation. In this study, 3 commercial palm cooking oils were selected and labeled as A, B and C. Two different conditions were applied to the samples. First, the oil sample was exposed to the air for three months (labeled as A) while samples B and C were used for frying for many times. Two inputs from FTIR spectra (3444 cm-1 and 3450 cm-1) were chosen for the ANN training. The suitable architecture for this training is 2:20:1. The prediction made by ANN was very accurate and compatible to the result which obtained from the standard method. A low average error (0.48) was obtained when the hidden neuron (20) and the epochs (300) were used.

AB - Peroxide value is one of the measurements that being used to determine the peroxide in oil samples produce from the peroxide compund and hydroperoxide group at the primary level of lipid oxidation. In this study, 3 commercial palm cooking oils were selected and labeled as A, B and C. Two different conditions were applied to the samples. First, the oil sample was exposed to the air for three months (labeled as A) while samples B and C were used for frying for many times. Two inputs from FTIR spectra (3444 cm-1 and 3450 cm-1) were chosen for the ANN training. The suitable architecture for this training is 2:20:1. The prediction made by ANN was very accurate and compatible to the result which obtained from the standard method. A low average error (0.48) was obtained when the hidden neuron (20) and the epochs (300) were used.

KW - ANN

KW - FTIR

KW - Palm oil

KW - Peroxide value

UR - http://www.scopus.com/inward/record.url?scp=84888861213&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888861213&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84888861213

VL - 17

SP - 376

EP - 386

JO - Malaysian Journal of Analytical Sciences

JF - Malaysian Journal of Analytical Sciences

SN - 1394-2506

IS - 3

ER -