No Detail Found!

Air Quality Pattern in Central Region of Malaysia using Multivariate Technique: A New Approach

Author(s)
Nurul Alia Azizan School of Biomedical Science, Faculty of Health Sciences, Universiti Sultan Zainal Abidin,Gong Badak Campus, 21300 Kuala Nerus, Terengganu,Malaysia
Azman Azid School of Animal Science, Aquatic Science and Environment, Faculty of Bioresources and Food Industry, Universiti Sultan Zainal Abidin,Kampus Besut, 22200 Besut, Terengganu,Malaysia
Asheila AK Meramat School of Biomedical Science, Faculty of Health Sciences, Universiti Sultan Zainal Abidin,Gong Badak Campus, 21300 Kuala Nerus, Terengganu,Malaysia
Ahmad Syibli Othman School of Biomedical Science, Faculty of Health Sciences, Universiti Sultan Zainal Abidin,Gong Badak Campus, 21300 Kuala Nerus, Terengganu,Malaysia
Siti Noor Syuhada Muhammad Amin Universiti Sultan Zainal Abidin Science and Medicine Foundation Centre,Gong Badak Campus, 21300 Kuala Nerus, Terengganu,Malaysia
Abstract
Assessment of air quality patterns require multiple variables to be analysed. It becomes a multivariate problem that requires novel methodologies as agglomerative hierarchical cluster analysis (AHC) is used primarily to determine cluster patterns. Therefore, this study aimed to demonstrate a new approach to cluster analysis in air quality monitoring stations in the central region of Peninsular Malaysia to provide a better spatial cluster distribution. The data sets was obtained by the Department of Environment (DOE) for the years 2018 to 2019. Six air quality pollutants were involved in this study. Before clustering the data, multivariate techniques such as principal component analysis (PCA) were used to summarize the information to better understand of the variables by reducing dimensionality. The AHC was then created using the PCA factor scores. The factor scores were employed in a discriminant analysis (DA) to verify the clusters. PCA factor scores revealed that 10 of 11 stations needed to be further investigated using AHC. High Polluted Region (HPR=five stations) and Low Polluted Region (LPR=five stations) were established from AHC. Each class was distinguished using discriminant analysis (DA). The researchers discovered that each class has its own set of variables. According to the DA, confusion matrix for the clusters is 94.58 %. The framework provided here offers a new approach for identifying and classifying stations based on air quality variables. This demonstrates that the hybrid cluster analysis technique utilized in this study is capable of producing more precise pollutant distributions.
Publication Details
Page(s) 126-134
DOI DOI not available
Published Journal: Bioscience Research, Volume: 19, Issue: SI-1, Year: 2022

Request the full text from PASTIC

Keywords
Air quality, a new approach, multivariate technique
0

Citations

0

Downloads

69

Views