Artificial neural networks and fuzzy time series forecasting: an application to air quality

Nur Haizum Abd Rahman, Muhammad Hisyam Lee, Suhartono, Mohd Talib Latif

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

The arising air pollution has addressed much attention globally due to its detrimental effects on human health and environment. As an early warning system for air quality control and management, it is important to provide precise information about the future concentrations in pollutants. We present here a time series model in predicting the Air Pollution Index (API) from three different stations; industrial, residential, and sub-urban areas between 2000 and 2009. In this paper, the Box–Jenkins approach of seasonal autoregressive integrated moving average (ARIMA), artificial neural network (ANN), and three models of fuzzy time series (FTS) have been compared by using the mean absolute percentage error, mean absolute error, mean square error, and root mean square error. Although all the methods were used as operational tools, the ANN seemed more accurate in forecasting API. The results showed that FTS (i.e. Chen’s, Yu’s, and Cheng’s) performed inconsistent results since the conventional methods of ARIMA outperformed the performance of FTS. However, consistent results were achieved as the ANNs gave the smallest forecasting error compared to FTS and ARIMA.

Original languageEnglish
Pages (from-to)2633-2647
Number of pages15
JournalQuality and Quantity
Volume49
Issue number6
DOIs
Publication statusPublished - 5 Dec 2014

Fingerprint

Fuzzy Time Series
Time Series Forecasting
Air Quality
neural network
Artificial Neural Network
time series
Air Pollution
Moving Average
air
air pollution
Mean square error
Forecasting
Early Warning
Quality Management
Urban Areas
Time Series Models
early warning system
Pollutants
Quality Control
Inconsistent

Keywords

  • Air Pollution Index (API)
  • ARIMA
  • Artificial neural network
  • Forecasting
  • Fuzzy time series
  • Time series

ASJC Scopus subject areas

  • Statistics and Probability
  • Social Sciences(all)

Cite this

Artificial neural networks and fuzzy time series forecasting : an application to air quality. / Rahman, Nur Haizum Abd; Lee, Muhammad Hisyam; Suhartono, ; Latif, Mohd Talib.

In: Quality and Quantity, Vol. 49, No. 6, 05.12.2014, p. 2633-2647.

Research output: Contribution to journalArticle

Rahman, Nur Haizum Abd ; Lee, Muhammad Hisyam ; Suhartono, ; Latif, Mohd Talib. / Artificial neural networks and fuzzy time series forecasting : an application to air quality. In: Quality and Quantity. 2014 ; Vol. 49, No. 6. pp. 2633-2647.
@article{691b90ab0aa346598e9f6297f70d11f6,
title = "Artificial neural networks and fuzzy time series forecasting: an application to air quality",
abstract = "The arising air pollution has addressed much attention globally due to its detrimental effects on human health and environment. As an early warning system for air quality control and management, it is important to provide precise information about the future concentrations in pollutants. We present here a time series model in predicting the Air Pollution Index (API) from three different stations; industrial, residential, and sub-urban areas between 2000 and 2009. In this paper, the Box–Jenkins approach of seasonal autoregressive integrated moving average (ARIMA), artificial neural network (ANN), and three models of fuzzy time series (FTS) have been compared by using the mean absolute percentage error, mean absolute error, mean square error, and root mean square error. Although all the methods were used as operational tools, the ANN seemed more accurate in forecasting API. The results showed that FTS (i.e. Chen’s, Yu’s, and Cheng’s) performed inconsistent results since the conventional methods of ARIMA outperformed the performance of FTS. However, consistent results were achieved as the ANNs gave the smallest forecasting error compared to FTS and ARIMA.",
keywords = "Air Pollution Index (API), ARIMA, Artificial neural network, Forecasting, Fuzzy time series, Time series",
author = "Rahman, {Nur Haizum Abd} and Lee, {Muhammad Hisyam} and Suhartono and Latif, {Mohd Talib}",
year = "2014",
month = "12",
day = "5",
doi = "10.1007/s11135-014-0132-6",
language = "English",
volume = "49",
pages = "2633--2647",
journal = "Quality and Quantity",
issn = "0033-5177",
publisher = "Springer Netherlands",
number = "6",

}

TY - JOUR

T1 - Artificial neural networks and fuzzy time series forecasting

T2 - an application to air quality

AU - Rahman, Nur Haizum Abd

AU - Lee, Muhammad Hisyam

AU - Suhartono,

AU - Latif, Mohd Talib

PY - 2014/12/5

Y1 - 2014/12/5

N2 - The arising air pollution has addressed much attention globally due to its detrimental effects on human health and environment. As an early warning system for air quality control and management, it is important to provide precise information about the future concentrations in pollutants. We present here a time series model in predicting the Air Pollution Index (API) from three different stations; industrial, residential, and sub-urban areas between 2000 and 2009. In this paper, the Box–Jenkins approach of seasonal autoregressive integrated moving average (ARIMA), artificial neural network (ANN), and three models of fuzzy time series (FTS) have been compared by using the mean absolute percentage error, mean absolute error, mean square error, and root mean square error. Although all the methods were used as operational tools, the ANN seemed more accurate in forecasting API. The results showed that FTS (i.e. Chen’s, Yu’s, and Cheng’s) performed inconsistent results since the conventional methods of ARIMA outperformed the performance of FTS. However, consistent results were achieved as the ANNs gave the smallest forecasting error compared to FTS and ARIMA.

AB - The arising air pollution has addressed much attention globally due to its detrimental effects on human health and environment. As an early warning system for air quality control and management, it is important to provide precise information about the future concentrations in pollutants. We present here a time series model in predicting the Air Pollution Index (API) from three different stations; industrial, residential, and sub-urban areas between 2000 and 2009. In this paper, the Box–Jenkins approach of seasonal autoregressive integrated moving average (ARIMA), artificial neural network (ANN), and three models of fuzzy time series (FTS) have been compared by using the mean absolute percentage error, mean absolute error, mean square error, and root mean square error. Although all the methods were used as operational tools, the ANN seemed more accurate in forecasting API. The results showed that FTS (i.e. Chen’s, Yu’s, and Cheng’s) performed inconsistent results since the conventional methods of ARIMA outperformed the performance of FTS. However, consistent results were achieved as the ANNs gave the smallest forecasting error compared to FTS and ARIMA.

KW - Air Pollution Index (API)

KW - ARIMA

KW - Artificial neural network

KW - Forecasting

KW - Fuzzy time series

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=84942986317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84942986317&partnerID=8YFLogxK

U2 - 10.1007/s11135-014-0132-6

DO - 10.1007/s11135-014-0132-6

M3 - Article

AN - SCOPUS:84942986317

VL - 49

SP - 2633

EP - 2647

JO - Quality and Quantity

JF - Quality and Quantity

SN - 0033-5177

IS - 6

ER -