Thermal conductivity prediction of foods by Neural Network and Fuzzy (ANFIS) modeling techniques

Mohammad Shafiur Rahman, M. M. Rashid, M. A. Hussain

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

A neuro-fuzzy modeling technique was used to predict the effective of thermal conductivity of various fruits and vegetables. A total of 676 data point was used to develop the neuro-fuzzy model considering the inputs as the fraction of water content, temperature and apparent porosity of food materials. The complexity of the data set which incorporates wide ranges of temperature (including those below freezing points) made it difficult for the data to be predicted by normal analytical and conventional models. However the adaptive neuro-fuzzy model (ANFIS) was able to predict conductivity values which closely matched the experimental values by providing lowest mean square error compared to multivariable regression and conventional artificial neural network (ANN) models. This method also alleviates the problem of determining the hidden structure of the neural network layer by trial and error.

Original languageEnglish
Pages (from-to)333-340
Number of pages8
JournalFood and Bioproducts Processing: Transactions of the Institution of of Chemical Engineers, Part C
Volume90
Issue number2
DOIs
Publication statusPublished - Apr 2012

Fingerprint

Thermal Conductivity
thermal conductivity
neural networks
Thermal conductivity
fuzzy logic
Neural networks
Food
Temperature
Neural Networks (Computer)
prediction
Porosity
Vegetables
Freezing
Fruit
freezing point
porosity
Water
Network layers
temperature
Fruits

Keywords

  • Artificial neural network
  • Fuzzy model
  • Neurofuzzy
  • Porosity
  • Thermal conductivity

ASJC Scopus subject areas

  • Food Science
  • Biochemistry
  • Biotechnology
  • Chemical Engineering(all)

Cite this

@article{1f72c9dd92c64229b7c83ea8e15aacf4,
title = "Thermal conductivity prediction of foods by Neural Network and Fuzzy (ANFIS) modeling techniques",
abstract = "A neuro-fuzzy modeling technique was used to predict the effective of thermal conductivity of various fruits and vegetables. A total of 676 data point was used to develop the neuro-fuzzy model considering the inputs as the fraction of water content, temperature and apparent porosity of food materials. The complexity of the data set which incorporates wide ranges of temperature (including those below freezing points) made it difficult for the data to be predicted by normal analytical and conventional models. However the adaptive neuro-fuzzy model (ANFIS) was able to predict conductivity values which closely matched the experimental values by providing lowest mean square error compared to multivariable regression and conventional artificial neural network (ANN) models. This method also alleviates the problem of determining the hidden structure of the neural network layer by trial and error.",
keywords = "Artificial neural network, Fuzzy model, Neurofuzzy, Porosity, Thermal conductivity",
author = "Rahman, {Mohammad Shafiur} and Rashid, {M. M.} and Hussain, {M. A.}",
year = "2012",
month = "4",
doi = "10.1016/j.fbp.2011.07.001",
language = "English",
volume = "90",
pages = "333--340",
journal = "Food and Bioproducts Processing",
issn = "0960-3085",
publisher = "Institution of Chemical Engineers",
number = "2",

}

TY - JOUR

T1 - Thermal conductivity prediction of foods by Neural Network and Fuzzy (ANFIS) modeling techniques

AU - Rahman, Mohammad Shafiur

AU - Rashid, M. M.

AU - Hussain, M. A.

PY - 2012/4

Y1 - 2012/4

N2 - A neuro-fuzzy modeling technique was used to predict the effective of thermal conductivity of various fruits and vegetables. A total of 676 data point was used to develop the neuro-fuzzy model considering the inputs as the fraction of water content, temperature and apparent porosity of food materials. The complexity of the data set which incorporates wide ranges of temperature (including those below freezing points) made it difficult for the data to be predicted by normal analytical and conventional models. However the adaptive neuro-fuzzy model (ANFIS) was able to predict conductivity values which closely matched the experimental values by providing lowest mean square error compared to multivariable regression and conventional artificial neural network (ANN) models. This method also alleviates the problem of determining the hidden structure of the neural network layer by trial and error.

AB - A neuro-fuzzy modeling technique was used to predict the effective of thermal conductivity of various fruits and vegetables. A total of 676 data point was used to develop the neuro-fuzzy model considering the inputs as the fraction of water content, temperature and apparent porosity of food materials. The complexity of the data set which incorporates wide ranges of temperature (including those below freezing points) made it difficult for the data to be predicted by normal analytical and conventional models. However the adaptive neuro-fuzzy model (ANFIS) was able to predict conductivity values which closely matched the experimental values by providing lowest mean square error compared to multivariable regression and conventional artificial neural network (ANN) models. This method also alleviates the problem of determining the hidden structure of the neural network layer by trial and error.

KW - Artificial neural network

KW - Fuzzy model

KW - Neurofuzzy

KW - Porosity

KW - Thermal conductivity

UR - http://www.scopus.com/inward/record.url?scp=84859005891&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859005891&partnerID=8YFLogxK

U2 - 10.1016/j.fbp.2011.07.001

DO - 10.1016/j.fbp.2011.07.001

M3 - Article

VL - 90

SP - 333

EP - 340

JO - Food and Bioproducts Processing

JF - Food and Bioproducts Processing

SN - 0960-3085

IS - 2

ER -