Robust principal component analysis in water quality index development

Zalina Mohd Ali, Noor Akma Ibrahim, Kerrie Mengersen, Mahendran Shitan, Hafizan Juahir

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Some statistical procedures already available in literature are employed in developing the water quality index, WQI. The nature of complexity and interdependency that occur in physical and chemical processes of water could be easier explained if statistical approaches were applied to water quality indexing. The most popular statistical method used in developing WQI is the principal component analysis (PCA). In literature, the WQI development based on the classical PCA mostly used water quality data that have been transformed and normalized. Outliers may be considered in or eliminated from the analysis. However, the classical mean and sample covariance matrix used in classical PCA methodology is not reliable if the outliers exist in the data. Since the presence of outliers may affect the computation of the principal component, robust principal component analysis, RPCA should be used. Focusing in Langat River, the RPCA-WQI was introduced for the first time in this study to re-calculate the DOE-WQI. Results show that the RPCA-WQI is capable to capture similar distribution in the existing DOE-WQI.

Original languageEnglish
Title of host publicationAIP Conference Proceedings
PublisherAmerican Institute of Physics Inc.
Pages1091-1097
Number of pages7
Volume1602
ISBN (Print)9780735412361
DOIs
Publication statusPublished - 2014
Event3rd International Conference on Mathematical Sciences, ICMS 2013 - Kuala Lumpur, Malaysia
Duration: 17 Dec 201319 Dec 2013

Other

Other3rd International Conference on Mathematical Sciences, ICMS 2013
CountryMalaysia
CityKuala Lumpur
Period17/12/1319/12/13

Fingerprint

water quality
principal components analysis
rivers
methodology
water

Keywords

  • Robust Principal Component Analysis
  • Water Quality Index and Langat River

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Mohd Ali, Z., Ibrahim, N. A., Mengersen, K., Shitan, M., & Juahir, H. (2014). Robust principal component analysis in water quality index development. In AIP Conference Proceedings (Vol. 1602, pp. 1091-1097). American Institute of Physics Inc.. https://doi.org/10.1063/1.4882620

Robust principal component analysis in water quality index development. / Mohd Ali, Zalina; Ibrahim, Noor Akma; Mengersen, Kerrie; Shitan, Mahendran; Juahir, Hafizan.

AIP Conference Proceedings. Vol. 1602 American Institute of Physics Inc., 2014. p. 1091-1097.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mohd Ali, Z, Ibrahim, NA, Mengersen, K, Shitan, M & Juahir, H 2014, Robust principal component analysis in water quality index development. in AIP Conference Proceedings. vol. 1602, American Institute of Physics Inc., pp. 1091-1097, 3rd International Conference on Mathematical Sciences, ICMS 2013, Kuala Lumpur, Malaysia, 17/12/13. https://doi.org/10.1063/1.4882620
Mohd Ali Z, Ibrahim NA, Mengersen K, Shitan M, Juahir H. Robust principal component analysis in water quality index development. In AIP Conference Proceedings. Vol. 1602. American Institute of Physics Inc. 2014. p. 1091-1097 https://doi.org/10.1063/1.4882620
Mohd Ali, Zalina ; Ibrahim, Noor Akma ; Mengersen, Kerrie ; Shitan, Mahendran ; Juahir, Hafizan. / Robust principal component analysis in water quality index development. AIP Conference Proceedings. Vol. 1602 American Institute of Physics Inc., 2014. pp. 1091-1097
@inproceedings{c861c2372ee741f6940fa3eb7e35e5df,
title = "Robust principal component analysis in water quality index development",
abstract = "Some statistical procedures already available in literature are employed in developing the water quality index, WQI. The nature of complexity and interdependency that occur in physical and chemical processes of water could be easier explained if statistical approaches were applied to water quality indexing. The most popular statistical method used in developing WQI is the principal component analysis (PCA). In literature, the WQI development based on the classical PCA mostly used water quality data that have been transformed and normalized. Outliers may be considered in or eliminated from the analysis. However, the classical mean and sample covariance matrix used in classical PCA methodology is not reliable if the outliers exist in the data. Since the presence of outliers may affect the computation of the principal component, robust principal component analysis, RPCA should be used. Focusing in Langat River, the RPCA-WQI was introduced for the first time in this study to re-calculate the DOE-WQI. Results show that the RPCA-WQI is capable to capture similar distribution in the existing DOE-WQI.",
keywords = "Robust Principal Component Analysis, Water Quality Index and Langat River",
author = "{Mohd Ali}, Zalina and Ibrahim, {Noor Akma} and Kerrie Mengersen and Mahendran Shitan and Hafizan Juahir",
year = "2014",
doi = "10.1063/1.4882620",
language = "English",
isbn = "9780735412361",
volume = "1602",
pages = "1091--1097",
booktitle = "AIP Conference Proceedings",
publisher = "American Institute of Physics Inc.",

}

TY - GEN

T1 - Robust principal component analysis in water quality index development

AU - Mohd Ali, Zalina

AU - Ibrahim, Noor Akma

AU - Mengersen, Kerrie

AU - Shitan, Mahendran

AU - Juahir, Hafizan

PY - 2014

Y1 - 2014

N2 - Some statistical procedures already available in literature are employed in developing the water quality index, WQI. The nature of complexity and interdependency that occur in physical and chemical processes of water could be easier explained if statistical approaches were applied to water quality indexing. The most popular statistical method used in developing WQI is the principal component analysis (PCA). In literature, the WQI development based on the classical PCA mostly used water quality data that have been transformed and normalized. Outliers may be considered in or eliminated from the analysis. However, the classical mean and sample covariance matrix used in classical PCA methodology is not reliable if the outliers exist in the data. Since the presence of outliers may affect the computation of the principal component, robust principal component analysis, RPCA should be used. Focusing in Langat River, the RPCA-WQI was introduced for the first time in this study to re-calculate the DOE-WQI. Results show that the RPCA-WQI is capable to capture similar distribution in the existing DOE-WQI.

AB - Some statistical procedures already available in literature are employed in developing the water quality index, WQI. The nature of complexity and interdependency that occur in physical and chemical processes of water could be easier explained if statistical approaches were applied to water quality indexing. The most popular statistical method used in developing WQI is the principal component analysis (PCA). In literature, the WQI development based on the classical PCA mostly used water quality data that have been transformed and normalized. Outliers may be considered in or eliminated from the analysis. However, the classical mean and sample covariance matrix used in classical PCA methodology is not reliable if the outliers exist in the data. Since the presence of outliers may affect the computation of the principal component, robust principal component analysis, RPCA should be used. Focusing in Langat River, the RPCA-WQI was introduced for the first time in this study to re-calculate the DOE-WQI. Results show that the RPCA-WQI is capable to capture similar distribution in the existing DOE-WQI.

KW - Robust Principal Component Analysis

KW - Water Quality Index and Langat River

UR - http://www.scopus.com/inward/record.url?scp=84904114419&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904114419&partnerID=8YFLogxK

U2 - 10.1063/1.4882620

DO - 10.1063/1.4882620

M3 - Conference contribution

SN - 9780735412361

VL - 1602

SP - 1091

EP - 1097

BT - AIP Conference Proceedings

PB - American Institute of Physics Inc.

ER -