Selection of the most significant variables of air pollutants using sensitivity analysis

Azman Azid, Hafizan Juahir, Mohd. Ekhwan Toriman, Azizah Endut, Mohd Nordin Abdul Rahman, Mohd Khairul Amri Kamarudin, Mohd Talib Latif, Ahmad Shakir Mohd Saudi, Che Noraini Che Hasnam, Kamaruzzaman Yunus

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This study was conducted to determine the most significant parameters for the air-pollutant index (API) prediction in Malaysia using data covering a 7-year period (2006-2012) obtained from the Malaysian Department of Environment (DOE). The sensitivity analysis method coupled with the artificial neural network (ANN) was applied. Nine models (ANN-API-AP, ANN-API-LCO, ANN-API-LO3, ANN-API-LPM10, ANN-API-LSO2, ANN-API-LNO2, ANN-API-LCH4, ANN-APILNmHC and ANN-API-LTHC) were carried out in the sensitivity analysis test. From the findings, PM10 and CO were identified as the most significant parameters in Malaysia. Three artificial neural network models (ANN-API-AP, ANN-API-LO, and ANN-API-DOE) were compared based on the performance criterion [R2, root-mean-square error (RMSE), and squared sum of all errors (SSE)] for the best prediction model selection. The ANN-API-AP, ANN-API-LO, and ANN-APIDOE models have R2 values of 0.733, 0.578, and 0.742, respectively; RMSE values of 8.689, 10.858, and 8.357, respectively; SSE values of 762,767.22, 1,191,280.60, and 705,600.05, respectively. The findings exhibit the ANN-API-LO model has a lower value in R2 and higher values in RMSE and SSE than others. ANN-API-LO model was considered as the best model of prediction because of fewer variables was utilized as input and far less complex than others. Hence, the use of fewer parameters of the API prediction has been highly practicable for air resource management because of its time and cost efficiency.

Original languageEnglish
Pages (from-to)376-384
Number of pages9
JournalJournal of Testing and Evaluation
Volume44
Issue number1
DOIs
Publication statusPublished - 1 Jan 2016

Fingerprint

Air Pollutants
Sensitivity analysis
Neural networks
Air
Mean square error

Keywords

  • Air-pollutant index
  • Artificial neural network
  • Sensitivity analysis

ASJC Scopus subject areas

  • Mechanical Engineering
  • Mechanics of Materials
  • Materials Science(all)

Cite this

Selection of the most significant variables of air pollutants using sensitivity analysis. / Azid, Azman; Juahir, Hafizan; Toriman, Mohd. Ekhwan; Endut, Azizah; Rahman, Mohd Nordin Abdul; Kamarudin, Mohd Khairul Amri; Latif, Mohd Talib; Saudi, Ahmad Shakir Mohd; Hasnam, Che Noraini Che; Yunus, Kamaruzzaman.

In: Journal of Testing and Evaluation, Vol. 44, No. 1, 01.01.2016, p. 376-384.

Research output: Contribution to journalArticle

Azid, A, Juahir, H, Toriman, ME, Endut, A, Rahman, MNA, Kamarudin, MKA, Latif, MT, Saudi, ASM, Hasnam, CNC & Yunus, K 2016, 'Selection of the most significant variables of air pollutants using sensitivity analysis', Journal of Testing and Evaluation, vol. 44, no. 1, pp. 376-384. https://doi.org/10.1520/JTE20140325
Azid, Azman ; Juahir, Hafizan ; Toriman, Mohd. Ekhwan ; Endut, Azizah ; Rahman, Mohd Nordin Abdul ; Kamarudin, Mohd Khairul Amri ; Latif, Mohd Talib ; Saudi, Ahmad Shakir Mohd ; Hasnam, Che Noraini Che ; Yunus, Kamaruzzaman. / Selection of the most significant variables of air pollutants using sensitivity analysis. In: Journal of Testing and Evaluation. 2016 ; Vol. 44, No. 1. pp. 376-384.
@article{a2907bd0ce2a4fc994e97dfa8cdbe632,
title = "Selection of the most significant variables of air pollutants using sensitivity analysis",
abstract = "This study was conducted to determine the most significant parameters for the air-pollutant index (API) prediction in Malaysia using data covering a 7-year period (2006-2012) obtained from the Malaysian Department of Environment (DOE). The sensitivity analysis method coupled with the artificial neural network (ANN) was applied. Nine models (ANN-API-AP, ANN-API-LCO, ANN-API-LO3, ANN-API-LPM10, ANN-API-LSO2, ANN-API-LNO2, ANN-API-LCH4, ANN-APILNmHC and ANN-API-LTHC) were carried out in the sensitivity analysis test. From the findings, PM10 and CO were identified as the most significant parameters in Malaysia. Three artificial neural network models (ANN-API-AP, ANN-API-LO, and ANN-API-DOE) were compared based on the performance criterion [R2, root-mean-square error (RMSE), and squared sum of all errors (SSE)] for the best prediction model selection. The ANN-API-AP, ANN-API-LO, and ANN-APIDOE models have R2 values of 0.733, 0.578, and 0.742, respectively; RMSE values of 8.689, 10.858, and 8.357, respectively; SSE values of 762,767.22, 1,191,280.60, and 705,600.05, respectively. The findings exhibit the ANN-API-LO model has a lower value in R2 and higher values in RMSE and SSE than others. ANN-API-LO model was considered as the best model of prediction because of fewer variables was utilized as input and far less complex than others. Hence, the use of fewer parameters of the API prediction has been highly practicable for air resource management because of its time and cost efficiency.",
keywords = "Air-pollutant index, Artificial neural network, Sensitivity analysis",
author = "Azman Azid and Hafizan Juahir and Toriman, {Mohd. Ekhwan} and Azizah Endut and Rahman, {Mohd Nordin Abdul} and Kamarudin, {Mohd Khairul Amri} and Latif, {Mohd Talib} and Saudi, {Ahmad Shakir Mohd} and Hasnam, {Che Noraini Che} and Kamaruzzaman Yunus",
year = "2016",
month = "1",
day = "1",
doi = "10.1520/JTE20140325",
language = "English",
volume = "44",
pages = "376--384",
journal = "Journal of Testing and Evaluation",
issn = "0090-3973",
publisher = "American Society for Testing and Materials",
number = "1",

}

TY - JOUR

T1 - Selection of the most significant variables of air pollutants using sensitivity analysis

AU - Azid, Azman

AU - Juahir, Hafizan

AU - Toriman, Mohd. Ekhwan

AU - Endut, Azizah

AU - Rahman, Mohd Nordin Abdul

AU - Kamarudin, Mohd Khairul Amri

AU - Latif, Mohd Talib

AU - Saudi, Ahmad Shakir Mohd

AU - Hasnam, Che Noraini Che

AU - Yunus, Kamaruzzaman

PY - 2016/1/1

Y1 - 2016/1/1

N2 - This study was conducted to determine the most significant parameters for the air-pollutant index (API) prediction in Malaysia using data covering a 7-year period (2006-2012) obtained from the Malaysian Department of Environment (DOE). The sensitivity analysis method coupled with the artificial neural network (ANN) was applied. Nine models (ANN-API-AP, ANN-API-LCO, ANN-API-LO3, ANN-API-LPM10, ANN-API-LSO2, ANN-API-LNO2, ANN-API-LCH4, ANN-APILNmHC and ANN-API-LTHC) were carried out in the sensitivity analysis test. From the findings, PM10 and CO were identified as the most significant parameters in Malaysia. Three artificial neural network models (ANN-API-AP, ANN-API-LO, and ANN-API-DOE) were compared based on the performance criterion [R2, root-mean-square error (RMSE), and squared sum of all errors (SSE)] for the best prediction model selection. The ANN-API-AP, ANN-API-LO, and ANN-APIDOE models have R2 values of 0.733, 0.578, and 0.742, respectively; RMSE values of 8.689, 10.858, and 8.357, respectively; SSE values of 762,767.22, 1,191,280.60, and 705,600.05, respectively. The findings exhibit the ANN-API-LO model has a lower value in R2 and higher values in RMSE and SSE than others. ANN-API-LO model was considered as the best model of prediction because of fewer variables was utilized as input and far less complex than others. Hence, the use of fewer parameters of the API prediction has been highly practicable for air resource management because of its time and cost efficiency.

AB - This study was conducted to determine the most significant parameters for the air-pollutant index (API) prediction in Malaysia using data covering a 7-year period (2006-2012) obtained from the Malaysian Department of Environment (DOE). The sensitivity analysis method coupled with the artificial neural network (ANN) was applied. Nine models (ANN-API-AP, ANN-API-LCO, ANN-API-LO3, ANN-API-LPM10, ANN-API-LSO2, ANN-API-LNO2, ANN-API-LCH4, ANN-APILNmHC and ANN-API-LTHC) were carried out in the sensitivity analysis test. From the findings, PM10 and CO were identified as the most significant parameters in Malaysia. Three artificial neural network models (ANN-API-AP, ANN-API-LO, and ANN-API-DOE) were compared based on the performance criterion [R2, root-mean-square error (RMSE), and squared sum of all errors (SSE)] for the best prediction model selection. The ANN-API-AP, ANN-API-LO, and ANN-APIDOE models have R2 values of 0.733, 0.578, and 0.742, respectively; RMSE values of 8.689, 10.858, and 8.357, respectively; SSE values of 762,767.22, 1,191,280.60, and 705,600.05, respectively. The findings exhibit the ANN-API-LO model has a lower value in R2 and higher values in RMSE and SSE than others. ANN-API-LO model was considered as the best model of prediction because of fewer variables was utilized as input and far less complex than others. Hence, the use of fewer parameters of the API prediction has been highly practicable for air resource management because of its time and cost efficiency.

KW - Air-pollutant index

KW - Artificial neural network

KW - Sensitivity analysis

UR - http://www.scopus.com/inward/record.url?scp=84959537323&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959537323&partnerID=8YFLogxK

U2 - 10.1520/JTE20140325

DO - 10.1520/JTE20140325

M3 - Article

AN - SCOPUS:84959537323

VL - 44

SP - 376

EP - 384

JO - Journal of Testing and Evaluation

JF - Journal of Testing and Evaluation

SN - 0090-3973

IS - 1

ER -