Home > Research > Publications & Outputs > New data mining and calibration approaches to t...

Associated organisational unit

View graph of relations

New data mining and calibration approaches to the assessment of water treatment efficiency

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

New data mining and calibration approaches to the assessment of water treatment efficiency. / Bieroza, M.; Baker, A.; Bridgeman, J.

In: Advances in Engineering Software, Vol. 44, No. 1, 02.2012, p. 126-135.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Bieroza, M, Baker, A & Bridgeman, J 2012, 'New data mining and calibration approaches to the assessment of water treatment efficiency', Advances in Engineering Software, vol. 44, no. 1, pp. 126-135. https://doi.org/10.1016/j.advengsoft.2011.05.031

APA

Vancouver

Author

Bieroza, M. ; Baker, A. ; Bridgeman, J. / New data mining and calibration approaches to the assessment of water treatment efficiency. In: Advances in Engineering Software. 2012 ; Vol. 44, No. 1. pp. 126-135.

Bibtex

@article{b7630ef4b9964d128a6b6be11c64169a,
title = "New data mining and calibration approaches to the assessment of water treatment efficiency",
abstract = "For the first time, the application of different robust data mining techniques to the assessment of water treatment performance is considered. Principal components analysis (PCA), parallel factor analysis (PARAFAC), and a self-organizing map (SOM) were used in the analysis of multivariate data characterising organic matter (OM) removal at 16 water treatment works. Decomposed fluorescence data from PCA. PARAFAC and SOM were used as input to calibrate fluorescence data with OM concentrations using step-wise regression (SR), partial least squares (PLS), multiple linear regression (MLR), and neural network with back-propagation algorithm (BPNN). The best results were obtained with combined PARAFAC/PLS and SOM/BPNN. Both the numerical accuracy and feasibility of the adopted solutions were compared and recommendations on the use of the above techniques for fluorescence data analysis are presented. ",
keywords = "Data mining, Multivariate analysis, Pattern recognition, Artificial neural networks, Fluorescence spectroscopy, Organic matter removal, DISSOLVED ORGANIC-MATTER, ARTIFICIAL NEURAL-NETWORKS, FLUORESCENCE SPECTROSCOPY, BY-PRODUCTS, CLASSIFICATION, CARBON, SPECTRA, OILS",
author = "M. Bieroza and A. Baker and J. Bridgeman",
year = "2012",
month = feb,
doi = "10.1016/j.advengsoft.2011.05.031",
language = "English",
volume = "44",
pages = "126--135",
journal = "Advances in Engineering Software",
issn = "0965-9978",
publisher = "Elsevier Limited",
number = "1",

}

RIS

TY - JOUR

T1 - New data mining and calibration approaches to the assessment of water treatment efficiency

AU - Bieroza, M.

AU - Baker, A.

AU - Bridgeman, J.

PY - 2012/2

Y1 - 2012/2

N2 - For the first time, the application of different robust data mining techniques to the assessment of water treatment performance is considered. Principal components analysis (PCA), parallel factor analysis (PARAFAC), and a self-organizing map (SOM) were used in the analysis of multivariate data characterising organic matter (OM) removal at 16 water treatment works. Decomposed fluorescence data from PCA. PARAFAC and SOM were used as input to calibrate fluorescence data with OM concentrations using step-wise regression (SR), partial least squares (PLS), multiple linear regression (MLR), and neural network with back-propagation algorithm (BPNN). The best results were obtained with combined PARAFAC/PLS and SOM/BPNN. Both the numerical accuracy and feasibility of the adopted solutions were compared and recommendations on the use of the above techniques for fluorescence data analysis are presented. 

AB - For the first time, the application of different robust data mining techniques to the assessment of water treatment performance is considered. Principal components analysis (PCA), parallel factor analysis (PARAFAC), and a self-organizing map (SOM) were used in the analysis of multivariate data characterising organic matter (OM) removal at 16 water treatment works. Decomposed fluorescence data from PCA. PARAFAC and SOM were used as input to calibrate fluorescence data with OM concentrations using step-wise regression (SR), partial least squares (PLS), multiple linear regression (MLR), and neural network with back-propagation algorithm (BPNN). The best results were obtained with combined PARAFAC/PLS and SOM/BPNN. Both the numerical accuracy and feasibility of the adopted solutions were compared and recommendations on the use of the above techniques for fluorescence data analysis are presented. 

KW - Data mining

KW - Multivariate analysis

KW - Pattern recognition

KW - Artificial neural networks

KW - Fluorescence spectroscopy

KW - Organic matter removal

KW - DISSOLVED ORGANIC-MATTER

KW - ARTIFICIAL NEURAL-NETWORKS

KW - FLUORESCENCE SPECTROSCOPY

KW - BY-PRODUCTS

KW - CLASSIFICATION

KW - CARBON

KW - SPECTRA

KW - OILS

U2 - 10.1016/j.advengsoft.2011.05.031

DO - 10.1016/j.advengsoft.2011.05.031

M3 - Journal article

VL - 44

SP - 126

EP - 135

JO - Advances in Engineering Software

JF - Advances in Engineering Software

SN - 0965-9978

IS - 1

ER -