Prediction of CO2 emissions using an artificial neural network: The case of the sugar industry

Chairul Saleh, Raden Achmad Chairdino Leuveano, Mohd Nizam Ab Rahman, Baba Md Deros, Nur Rachman Dzakiyullah

Research output: Contribution to journalArticle

Abstract

In this paper, the back-propagation artificial neural networks (ANN) model is presented to predict expenditure of carbon (CO2) emission. The model was built based on the input variables that affect to expenditure of CO2 include the amount of bagasse, wood and marine fuel oil used in boiler machine. The objective of this paper is to monitor the CO2 emission based on the fuel used for operating the boiler machine. The data used for testing the models were obtained from Sugar Industry. It splits up into 90% of training data and 10% of testing data. The model experiment was conducted using trial and error approach to find the optimal parameters of ANN model. The result shows that the architecture of ANN model have optimal parameter on training cycle 50, learning rate 0.1, momentum 0.1, and 19 hidden nodes. The validity of the trained ANN is evaluated by using Root Mean Square Error (RMSE) with error value as 0.055. It indicates that the smallest error provides more accurate results on prediction and even can contribute to the industrial practice, especially helping the executive manager to make an effective decision for business operation by considering the expenditure of CO2 monitoring.

Original languageEnglish
Pages (from-to)3079-3083
Number of pages5
JournalAdvanced Science Letters
Volume21
Issue number10
DOIs
Publication statusPublished - 1 Oct 2015
Externally publishedYes

Fingerprint

Sugar industry
Neural Networks (Computer)
food and luxury products industry
Sugars
Health Expenditures
neural network
artificial neural network
Artificial Neural Network
Industry
Neural Network Model
Neural networks
Prediction
Optimal Parameter
prediction
Fuel Oils
expenditures
expenditure
Testing
Learning Rate
Boilers

Keywords

  • Artificial neural network
  • Carbon emission
  • Prediction
  • RMSE

ASJC Scopus subject areas

  • Engineering(all)
  • Environmental Science(all)
  • Computer Science(all)
  • Energy(all)
  • Mathematics(all)
  • Health(social science)
  • Education

Cite this

Prediction of CO2 emissions using an artificial neural network : The case of the sugar industry. / Saleh, Chairul; Leuveano, Raden Achmad Chairdino; Ab Rahman, Mohd Nizam; Md Deros, Baba; Dzakiyullah, Nur Rachman.

In: Advanced Science Letters, Vol. 21, No. 10, 01.10.2015, p. 3079-3083.

Research output: Contribution to journalArticle

Saleh, Chairul ; Leuveano, Raden Achmad Chairdino ; Ab Rahman, Mohd Nizam ; Md Deros, Baba ; Dzakiyullah, Nur Rachman. / Prediction of CO2 emissions using an artificial neural network : The case of the sugar industry. In: Advanced Science Letters. 2015 ; Vol. 21, No. 10. pp. 3079-3083.
@article{065040a2e99449b6ae28e6f532608350,
title = "Prediction of CO2 emissions using an artificial neural network: The case of the sugar industry",
abstract = "In this paper, the back-propagation artificial neural networks (ANN) model is presented to predict expenditure of carbon (CO2) emission. The model was built based on the input variables that affect to expenditure of CO2 include the amount of bagasse, wood and marine fuel oil used in boiler machine. The objective of this paper is to monitor the CO2 emission based on the fuel used for operating the boiler machine. The data used for testing the models were obtained from Sugar Industry. It splits up into 90{\%} of training data and 10{\%} of testing data. The model experiment was conducted using trial and error approach to find the optimal parameters of ANN model. The result shows that the architecture of ANN model have optimal parameter on training cycle 50, learning rate 0.1, momentum 0.1, and 19 hidden nodes. The validity of the trained ANN is evaluated by using Root Mean Square Error (RMSE) with error value as 0.055. It indicates that the smallest error provides more accurate results on prediction and even can contribute to the industrial practice, especially helping the executive manager to make an effective decision for business operation by considering the expenditure of CO2 monitoring.",
keywords = "Artificial neural network, Carbon emission, Prediction, RMSE",
author = "Chairul Saleh and Leuveano, {Raden Achmad Chairdino} and {Ab Rahman}, {Mohd Nizam} and {Md Deros}, Baba and Dzakiyullah, {Nur Rachman}",
year = "2015",
month = "10",
day = "1",
doi = "10.1166/asl.2015.6488",
language = "English",
volume = "21",
pages = "3079--3083",
journal = "Advanced Science Letters",
issn = "1936-6612",
publisher = "American Scientific Publishers",
number = "10",

}

TY - JOUR

T1 - Prediction of CO2 emissions using an artificial neural network

T2 - The case of the sugar industry

AU - Saleh, Chairul

AU - Leuveano, Raden Achmad Chairdino

AU - Ab Rahman, Mohd Nizam

AU - Md Deros, Baba

AU - Dzakiyullah, Nur Rachman

PY - 2015/10/1

Y1 - 2015/10/1

N2 - In this paper, the back-propagation artificial neural networks (ANN) model is presented to predict expenditure of carbon (CO2) emission. The model was built based on the input variables that affect to expenditure of CO2 include the amount of bagasse, wood and marine fuel oil used in boiler machine. The objective of this paper is to monitor the CO2 emission based on the fuel used for operating the boiler machine. The data used for testing the models were obtained from Sugar Industry. It splits up into 90% of training data and 10% of testing data. The model experiment was conducted using trial and error approach to find the optimal parameters of ANN model. The result shows that the architecture of ANN model have optimal parameter on training cycle 50, learning rate 0.1, momentum 0.1, and 19 hidden nodes. The validity of the trained ANN is evaluated by using Root Mean Square Error (RMSE) with error value as 0.055. It indicates that the smallest error provides more accurate results on prediction and even can contribute to the industrial practice, especially helping the executive manager to make an effective decision for business operation by considering the expenditure of CO2 monitoring.

AB - In this paper, the back-propagation artificial neural networks (ANN) model is presented to predict expenditure of carbon (CO2) emission. The model was built based on the input variables that affect to expenditure of CO2 include the amount of bagasse, wood and marine fuel oil used in boiler machine. The objective of this paper is to monitor the CO2 emission based on the fuel used for operating the boiler machine. The data used for testing the models were obtained from Sugar Industry. It splits up into 90% of training data and 10% of testing data. The model experiment was conducted using trial and error approach to find the optimal parameters of ANN model. The result shows that the architecture of ANN model have optimal parameter on training cycle 50, learning rate 0.1, momentum 0.1, and 19 hidden nodes. The validity of the trained ANN is evaluated by using Root Mean Square Error (RMSE) with error value as 0.055. It indicates that the smallest error provides more accurate results on prediction and even can contribute to the industrial practice, especially helping the executive manager to make an effective decision for business operation by considering the expenditure of CO2 monitoring.

KW - Artificial neural network

KW - Carbon emission

KW - Prediction

KW - RMSE

UR - http://www.scopus.com/inward/record.url?scp=84960335313&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960335313&partnerID=8YFLogxK

U2 - 10.1166/asl.2015.6488

DO - 10.1166/asl.2015.6488

M3 - Article

AN - SCOPUS:84960335313

VL - 21

SP - 3079

EP - 3083

JO - Advanced Science Letters

JF - Advanced Science Letters

SN - 1936-6612

IS - 10

ER -