Home > Research > Publications & Outputs > Classification and calibration of organic matte...

Research

Associated organisational unit

Links

Text available via DOI:

Keywords

View graph of relations

Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks: an operational tool for improved drinking water treatment

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks: an operational tool for improved drinking water treatment. / Bieroza, Magdalena; Baker, Andy; Bridgeman, John.
In: Environmetrics, Vol. 22, No. 3, 05.2011, p. 256-270.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Bieroza, M, Baker, A & Bridgeman, J 2011, 'Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks: an operational tool for improved drinking water treatment', Environmetrics, vol. 22, no. 3, pp. 256-270. https://doi.org/10.1002/env.1045

APA

Bieroza, M., Baker, A., & Bridgeman, J. (2011). Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks: an operational tool for improved drinking water treatment. Environmetrics, 22(3), 256-270. https://doi.org/10.1002/env.1045

Vancouver

Bieroza M, Baker A, Bridgeman J. Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks: an operational tool for improved drinking water treatment. Environmetrics. 2011 May;22(3):256-270. doi: 10.1002/env.1045

Author

Bieroza, Magdalena ; Baker, Andy ; Bridgeman, John. / Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks : an operational tool for improved drinking water treatment. In: Environmetrics. 2011 ; Vol. 22, No. 3. pp. 256-270.

Bibtex

@article{835fe128b0814c048670e2a9d8997f77,
title = "Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks: an operational tool for improved drinking water treatment",
abstract = "Fluorescence spectroscopy enables fast and sensitive analysis of environmental samples containing various organic matter constituents. However, to retrieve valuable information from fluorescence spectra, robust techniques for data analysis should be employed. Here, different multivariate analysis methods and artificial neural networks (ANNs) were applied for decomposition and calibration of fluorescence excitation-emission matrices (EEMs). This is the first paper summarizing the application of different data mining methods, from multiway analysis to ANNs, for fluorescence EEMs technique employed to characterize organic matter properties and removal in the field of drinking water treatment. Fluorescence analysis was carried out on municipal water treatment samples of raw and partially-treated water. Parallel factor analysis (PARAFAC) method and self-organizing maps were used to analyse EEMs, extract information on the organic matter constituents and reduce the dimensionality of the data to enhance the efficiency of calibration methods. Partial least squares (PLS), multiple linear regression (MLR) and neural network with back-propagation were employed for calibration of fluorescence data with actual total organic carbon (TOC) concentrations. All models except PARAFAC-MLR produced consistent results with correlation coefficient R-2 = 0.93 for validation dataset. This is the first such comparative analysis of fluorescence data modelling that clarifies fundamental fluorescence data analysis questions regarding the suitability of different decomposition and calibration methods. Copyright (C) 2010 John Wiley & Sons, Ltd.",
keywords = "data mining, multivariate statistics, neural networks, fluorescence spectroscopy, organic matter removal, EMISSION MATRIX FLUORESCENCE, MULTIVARIATE CURVE RESOLUTION, SOLVING CHEMICAL PROBLEMS, PARTIAL LEAST-SQUARES, 3-WAY METHODS, EXCITATION, SPECTRA, SPECTROSCOPY, IDENTIFICATION, SIGNATURES",
author = "Magdalena Bieroza and Andy Baker and John Bridgeman",
year = "2011",
month = may,
doi = "10.1002/env.1045",
language = "English",
volume = "22",
pages = "256--270",
journal = "Environmetrics",
issn = "1099-095X",
publisher = "John Wiley and Sons Ltd",
number = "3",

}

RIS

TY - JOUR

T1 - Classification and calibration of organic matter fluorescence data with multiway analysis methods and artificial neural networks

T2 - an operational tool for improved drinking water treatment

AU - Bieroza, Magdalena

AU - Baker, Andy

AU - Bridgeman, John

PY - 2011/5

Y1 - 2011/5

N2 - Fluorescence spectroscopy enables fast and sensitive analysis of environmental samples containing various organic matter constituents. However, to retrieve valuable information from fluorescence spectra, robust techniques for data analysis should be employed. Here, different multivariate analysis methods and artificial neural networks (ANNs) were applied for decomposition and calibration of fluorescence excitation-emission matrices (EEMs). This is the first paper summarizing the application of different data mining methods, from multiway analysis to ANNs, for fluorescence EEMs technique employed to characterize organic matter properties and removal in the field of drinking water treatment. Fluorescence analysis was carried out on municipal water treatment samples of raw and partially-treated water. Parallel factor analysis (PARAFAC) method and self-organizing maps were used to analyse EEMs, extract information on the organic matter constituents and reduce the dimensionality of the data to enhance the efficiency of calibration methods. Partial least squares (PLS), multiple linear regression (MLR) and neural network with back-propagation were employed for calibration of fluorescence data with actual total organic carbon (TOC) concentrations. All models except PARAFAC-MLR produced consistent results with correlation coefficient R-2 = 0.93 for validation dataset. This is the first such comparative analysis of fluorescence data modelling that clarifies fundamental fluorescence data analysis questions regarding the suitability of different decomposition and calibration methods. Copyright (C) 2010 John Wiley & Sons, Ltd.

AB - Fluorescence spectroscopy enables fast and sensitive analysis of environmental samples containing various organic matter constituents. However, to retrieve valuable information from fluorescence spectra, robust techniques for data analysis should be employed. Here, different multivariate analysis methods and artificial neural networks (ANNs) were applied for decomposition and calibration of fluorescence excitation-emission matrices (EEMs). This is the first paper summarizing the application of different data mining methods, from multiway analysis to ANNs, for fluorescence EEMs technique employed to characterize organic matter properties and removal in the field of drinking water treatment. Fluorescence analysis was carried out on municipal water treatment samples of raw and partially-treated water. Parallel factor analysis (PARAFAC) method and self-organizing maps were used to analyse EEMs, extract information on the organic matter constituents and reduce the dimensionality of the data to enhance the efficiency of calibration methods. Partial least squares (PLS), multiple linear regression (MLR) and neural network with back-propagation were employed for calibration of fluorescence data with actual total organic carbon (TOC) concentrations. All models except PARAFAC-MLR produced consistent results with correlation coefficient R-2 = 0.93 for validation dataset. This is the first such comparative analysis of fluorescence data modelling that clarifies fundamental fluorescence data analysis questions regarding the suitability of different decomposition and calibration methods. Copyright (C) 2010 John Wiley & Sons, Ltd.

KW - data mining

KW - multivariate statistics

KW - neural networks

KW - fluorescence spectroscopy

KW - organic matter removal

KW - EMISSION MATRIX FLUORESCENCE

KW - MULTIVARIATE CURVE RESOLUTION

KW - SOLVING CHEMICAL PROBLEMS

KW - PARTIAL LEAST-SQUARES

KW - 3-WAY METHODS

KW - EXCITATION

KW - SPECTRA

KW - SPECTROSCOPY

KW - IDENTIFICATION

KW - SIGNATURES

U2 - 10.1002/env.1045

DO - 10.1002/env.1045

M3 - Journal article

VL - 22

SP - 256

EP - 270

JO - Environmetrics

JF - Environmetrics

SN - 1099-095X

IS - 3

ER -