Artificial neural network to predict the growth of the indigenous Acidthiobacillus thiooxidans

Hsuan Liang Liu, Fu Chiang Yang, Hsin Yi Lin, Chih Hung Huang, Hsu Wei Fang, Wei Bor Tsai, Yung Chu Cheng

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

In this study, the growth of the indigenous Acidithiobacillus thiooxidans was predicted using artificial neural network (ANN). Four important variables of the growth medium: KH 2 PO 4 , (NH 4 ) 2 SO 4 , MgSO 4 , and elemental sulfur (S 0 ) were fed as input into the ANN model, while the dry cell weight (DCW) was the output. The ANN model adopted in this study, consisting of an input layer, a hidden layer, and an output layer, was found to give satisfactory results. Among different combinations of 10 mostly used transfer functions, Gaussian and Sigmoid transfer functions were selected for the hidden and the output layers, respectively, to minimize the error between the experimental results and the estimated outputs. Experimental data were randomly separated into a training set and a test set with 22 and 8 experimental runs, respectively. The resulting ANN shows satisfactory prediction of the DCW with R 2 = 0.991 and mean relative deviation (RD) = 0.026. The optimal medium composition of the indigenous A. thiooxidans was further predicted to be KH 2 PO 4 = 1.0 g/l, (NH 4 ) 2 SO 4 = 3.5 g/l, MgSO 4 = 0.65 g/l, and S 0 = 23 g/l with the optimal DCW being 0.722 g/l. The results of this study suggest that ANN provides a powerful tool in studying the nonlinear and time-variant biological processes.

Original languageEnglish
Pages (from-to)231-237
Number of pages7
JournalChemical Engineering Journal
Volume137
Issue number2
DOIs
Publication statusPublished - Apr 1 2008
Externally publishedYes

Fingerprint

artificial neural network
Neural networks
transfer function
Transfer functions
Sulfur
biological processes
sulfur
prediction
Chemical analysis
PO-2

Keywords

  • Acidithiobacillus thiooxidans
  • Artificial neural network (ANN)
  • Elemental sulfur
  • Gaussian
  • Sigmoid
  • Transfer function

ASJC Scopus subject areas

  • Chemistry(all)
  • Environmental Chemistry
  • Chemical Engineering(all)
  • Industrial and Manufacturing Engineering

Cite this

Artificial neural network to predict the growth of the indigenous Acidthiobacillus thiooxidans. / Liu, Hsuan Liang; Yang, Fu Chiang; Lin, Hsin Yi; Huang, Chih Hung; Fang, Hsu Wei; Tsai, Wei Bor; Cheng, Yung Chu.

In: Chemical Engineering Journal, Vol. 137, No. 2, 01.04.2008, p. 231-237.

Research output: Contribution to journalArticle

Liu, Hsuan Liang ; Yang, Fu Chiang ; Lin, Hsin Yi ; Huang, Chih Hung ; Fang, Hsu Wei ; Tsai, Wei Bor ; Cheng, Yung Chu. / Artificial neural network to predict the growth of the indigenous Acidthiobacillus thiooxidans. In: Chemical Engineering Journal. 2008 ; Vol. 137, No. 2. pp. 231-237.
@article{d71f68253cb74565919166316189229a,
title = "Artificial neural network to predict the growth of the indigenous Acidthiobacillus thiooxidans",
abstract = "In this study, the growth of the indigenous Acidithiobacillus thiooxidans was predicted using artificial neural network (ANN). Four important variables of the growth medium: KH 2 PO 4 , (NH 4 ) 2 SO 4 , MgSO 4 , and elemental sulfur (S 0 ) were fed as input into the ANN model, while the dry cell weight (DCW) was the output. The ANN model adopted in this study, consisting of an input layer, a hidden layer, and an output layer, was found to give satisfactory results. Among different combinations of 10 mostly used transfer functions, Gaussian and Sigmoid transfer functions were selected for the hidden and the output layers, respectively, to minimize the error between the experimental results and the estimated outputs. Experimental data were randomly separated into a training set and a test set with 22 and 8 experimental runs, respectively. The resulting ANN shows satisfactory prediction of the DCW with R 2 = 0.991 and mean relative deviation (RD) = 0.026. The optimal medium composition of the indigenous A. thiooxidans was further predicted to be KH 2 PO 4 = 1.0 g/l, (NH 4 ) 2 SO 4 = 3.5 g/l, MgSO 4 = 0.65 g/l, and S 0 = 23 g/l with the optimal DCW being 0.722 g/l. The results of this study suggest that ANN provides a powerful tool in studying the nonlinear and time-variant biological processes.",
keywords = "Acidithiobacillus thiooxidans, Artificial neural network (ANN), Elemental sulfur, Gaussian, Sigmoid, Transfer function",
author = "Liu, {Hsuan Liang} and Yang, {Fu Chiang} and Lin, {Hsin Yi} and Huang, {Chih Hung} and Fang, {Hsu Wei} and Tsai, {Wei Bor} and Cheng, {Yung Chu}",
year = "2008",
month = "4",
day = "1",
doi = "10.1016/j.cej.2007.04.024",
language = "English",
volume = "137",
pages = "231--237",
journal = "Chemical Engineering Journal",
issn = "1385-8947",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - Artificial neural network to predict the growth of the indigenous Acidthiobacillus thiooxidans

AU - Liu, Hsuan Liang

AU - Yang, Fu Chiang

AU - Lin, Hsin Yi

AU - Huang, Chih Hung

AU - Fang, Hsu Wei

AU - Tsai, Wei Bor

AU - Cheng, Yung Chu

PY - 2008/4/1

Y1 - 2008/4/1

N2 - In this study, the growth of the indigenous Acidithiobacillus thiooxidans was predicted using artificial neural network (ANN). Four important variables of the growth medium: KH 2 PO 4 , (NH 4 ) 2 SO 4 , MgSO 4 , and elemental sulfur (S 0 ) were fed as input into the ANN model, while the dry cell weight (DCW) was the output. The ANN model adopted in this study, consisting of an input layer, a hidden layer, and an output layer, was found to give satisfactory results. Among different combinations of 10 mostly used transfer functions, Gaussian and Sigmoid transfer functions were selected for the hidden and the output layers, respectively, to minimize the error between the experimental results and the estimated outputs. Experimental data were randomly separated into a training set and a test set with 22 and 8 experimental runs, respectively. The resulting ANN shows satisfactory prediction of the DCW with R 2 = 0.991 and mean relative deviation (RD) = 0.026. The optimal medium composition of the indigenous A. thiooxidans was further predicted to be KH 2 PO 4 = 1.0 g/l, (NH 4 ) 2 SO 4 = 3.5 g/l, MgSO 4 = 0.65 g/l, and S 0 = 23 g/l with the optimal DCW being 0.722 g/l. The results of this study suggest that ANN provides a powerful tool in studying the nonlinear and time-variant biological processes.

AB - In this study, the growth of the indigenous Acidithiobacillus thiooxidans was predicted using artificial neural network (ANN). Four important variables of the growth medium: KH 2 PO 4 , (NH 4 ) 2 SO 4 , MgSO 4 , and elemental sulfur (S 0 ) were fed as input into the ANN model, while the dry cell weight (DCW) was the output. The ANN model adopted in this study, consisting of an input layer, a hidden layer, and an output layer, was found to give satisfactory results. Among different combinations of 10 mostly used transfer functions, Gaussian and Sigmoid transfer functions were selected for the hidden and the output layers, respectively, to minimize the error between the experimental results and the estimated outputs. Experimental data were randomly separated into a training set and a test set with 22 and 8 experimental runs, respectively. The resulting ANN shows satisfactory prediction of the DCW with R 2 = 0.991 and mean relative deviation (RD) = 0.026. The optimal medium composition of the indigenous A. thiooxidans was further predicted to be KH 2 PO 4 = 1.0 g/l, (NH 4 ) 2 SO 4 = 3.5 g/l, MgSO 4 = 0.65 g/l, and S 0 = 23 g/l with the optimal DCW being 0.722 g/l. The results of this study suggest that ANN provides a powerful tool in studying the nonlinear and time-variant biological processes.

KW - Acidithiobacillus thiooxidans

KW - Artificial neural network (ANN)

KW - Elemental sulfur

KW - Gaussian

KW - Sigmoid

KW - Transfer function

UR - http://www.scopus.com/inward/record.url?scp=38949174992&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38949174992&partnerID=8YFLogxK

U2 - 10.1016/j.cej.2007.04.024

DO - 10.1016/j.cej.2007.04.024

M3 - Article

VL - 137

SP - 231

EP - 237

JO - Chemical Engineering Journal

JF - Chemical Engineering Journal

SN - 1385-8947

IS - 2

ER -