Improved ozone pollution prediction using extreme learning machine with tribas regularization activation function

Noraini Ismail, Zulaiha Ali Othman

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Nowadays, increasing ozone (O3) pollution is becoming a global issue. The increasing of these pollutions has a huge negative impact on human health and also to the ecosystem. In order to reduce the risk of high O3 pollution, an accurate O3 forecasting model should be developed, so that a preventive measure can be taken earlier. Therefore, this study proposed an accurate O3 prediction model using improvement Extreme Learning Machine algorithm based on Regularization Activation Function (RAF-ELM). The experiment conducted by investigating RAF-ELM performance use four types of activation function, i.e., sigmoid, sine, tribas, and hardlim. In this study, RAF-ELM uses single hidden layer feedforward neural networks to predict the air quality index for O3 pollutant based on meteorological variables (Temperature and Wind Speed) and other pollutants (NOx, NO, NO2, CO, PM10, SO2, CH4, NMHC, and THC) in Malaysia using O3 hourly time series data collected at Shah Alam station. It has 107,329 instances recorded from the year 1998 to 2010. The input weight and bias for hidden layers are randomly selected, whereas the best neurons’ number of hidden layer is determined from 5 to 20. The number of neurons (11) with regularization (0.8) using tribas activation function showed the best model. The proposed model has obtained better accuracy performance (0.007999 MSE) and better processing time (2.699 s) compared with conventional MPE. It can be concluded that the proposed algorithm can be used as a good prediction technique for time series data.

Original languageEnglish
Title of host publicationLecture Notes in Networks and Systems
PublisherSpringer
Pages151-165
Number of pages15
DOIs
Publication statusPublished - 1 Jan 2019

Publication series

NameLecture Notes in Networks and Systems
Volume67
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Fingerprint

Ozone
Learning systems
Pollution
Chemical activation
Neurons
Time series
Feedforward neural networks
Air quality
Ecosystems
Health
Processing
Experiments
Temperature

Keywords

  • Data mining
  • Extreme learning machine
  • Neural networks
  • Ozone
  • Prediction

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications

Cite this

Ismail, N., & Ali Othman, Z. (2019). Improved ozone pollution prediction using extreme learning machine with tribas regularization activation function. In Lecture Notes in Networks and Systems (pp. 151-165). (Lecture Notes in Networks and Systems; Vol. 67). Springer. https://doi.org/10.1007/978-981-13-6031-2_9

Improved ozone pollution prediction using extreme learning machine with tribas regularization activation function. / Ismail, Noraini; Ali Othman, Zulaiha.

Lecture Notes in Networks and Systems. Springer, 2019. p. 151-165 (Lecture Notes in Networks and Systems; Vol. 67).

Research output: Chapter in Book/Report/Conference proceedingChapter

Ismail, N & Ali Othman, Z 2019, Improved ozone pollution prediction using extreme learning machine with tribas regularization activation function. in Lecture Notes in Networks and Systems. Lecture Notes in Networks and Systems, vol. 67, Springer, pp. 151-165. https://doi.org/10.1007/978-981-13-6031-2_9
Ismail N, Ali Othman Z. Improved ozone pollution prediction using extreme learning machine with tribas regularization activation function. In Lecture Notes in Networks and Systems. Springer. 2019. p. 151-165. (Lecture Notes in Networks and Systems). https://doi.org/10.1007/978-981-13-6031-2_9
Ismail, Noraini ; Ali Othman, Zulaiha. / Improved ozone pollution prediction using extreme learning machine with tribas regularization activation function. Lecture Notes in Networks and Systems. Springer, 2019. pp. 151-165 (Lecture Notes in Networks and Systems).
@inbook{0ec8723805db454589bb9dd6cb8ba542,
title = "Improved ozone pollution prediction using extreme learning machine with tribas regularization activation function",
abstract = "Nowadays, increasing ozone (O3) pollution is becoming a global issue. The increasing of these pollutions has a huge negative impact on human health and also to the ecosystem. In order to reduce the risk of high O3 pollution, an accurate O3 forecasting model should be developed, so that a preventive measure can be taken earlier. Therefore, this study proposed an accurate O3 prediction model using improvement Extreme Learning Machine algorithm based on Regularization Activation Function (RAF-ELM). The experiment conducted by investigating RAF-ELM performance use four types of activation function, i.e., sigmoid, sine, tribas, and hardlim. In this study, RAF-ELM uses single hidden layer feedforward neural networks to predict the air quality index for O3 pollutant based on meteorological variables (Temperature and Wind Speed) and other pollutants (NOx, NO, NO2, CO, PM10, SO2, CH4, NMHC, and THC) in Malaysia using O3 hourly time series data collected at Shah Alam station. It has 107,329 instances recorded from the year 1998 to 2010. The input weight and bias for hidden layers are randomly selected, whereas the best neurons’ number of hidden layer is determined from 5 to 20. The number of neurons (11) with regularization (0.8) using tribas activation function showed the best model. The proposed model has obtained better accuracy performance (0.007999 MSE) and better processing time (2.699 s) compared with conventional MPE. It can be concluded that the proposed algorithm can be used as a good prediction technique for time series data.",
keywords = "Data mining, Extreme learning machine, Neural networks, Ozone, Prediction",
author = "Noraini Ismail and {Ali Othman}, Zulaiha",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-981-13-6031-2_9",
language = "English",
series = "Lecture Notes in Networks and Systems",
publisher = "Springer",
pages = "151--165",
booktitle = "Lecture Notes in Networks and Systems",

}

TY - CHAP

T1 - Improved ozone pollution prediction using extreme learning machine with tribas regularization activation function

AU - Ismail, Noraini

AU - Ali Othman, Zulaiha

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Nowadays, increasing ozone (O3) pollution is becoming a global issue. The increasing of these pollutions has a huge negative impact on human health and also to the ecosystem. In order to reduce the risk of high O3 pollution, an accurate O3 forecasting model should be developed, so that a preventive measure can be taken earlier. Therefore, this study proposed an accurate O3 prediction model using improvement Extreme Learning Machine algorithm based on Regularization Activation Function (RAF-ELM). The experiment conducted by investigating RAF-ELM performance use four types of activation function, i.e., sigmoid, sine, tribas, and hardlim. In this study, RAF-ELM uses single hidden layer feedforward neural networks to predict the air quality index for O3 pollutant based on meteorological variables (Temperature and Wind Speed) and other pollutants (NOx, NO, NO2, CO, PM10, SO2, CH4, NMHC, and THC) in Malaysia using O3 hourly time series data collected at Shah Alam station. It has 107,329 instances recorded from the year 1998 to 2010. The input weight and bias for hidden layers are randomly selected, whereas the best neurons’ number of hidden layer is determined from 5 to 20. The number of neurons (11) with regularization (0.8) using tribas activation function showed the best model. The proposed model has obtained better accuracy performance (0.007999 MSE) and better processing time (2.699 s) compared with conventional MPE. It can be concluded that the proposed algorithm can be used as a good prediction technique for time series data.

AB - Nowadays, increasing ozone (O3) pollution is becoming a global issue. The increasing of these pollutions has a huge negative impact on human health and also to the ecosystem. In order to reduce the risk of high O3 pollution, an accurate O3 forecasting model should be developed, so that a preventive measure can be taken earlier. Therefore, this study proposed an accurate O3 prediction model using improvement Extreme Learning Machine algorithm based on Regularization Activation Function (RAF-ELM). The experiment conducted by investigating RAF-ELM performance use four types of activation function, i.e., sigmoid, sine, tribas, and hardlim. In this study, RAF-ELM uses single hidden layer feedforward neural networks to predict the air quality index for O3 pollutant based on meteorological variables (Temperature and Wind Speed) and other pollutants (NOx, NO, NO2, CO, PM10, SO2, CH4, NMHC, and THC) in Malaysia using O3 hourly time series data collected at Shah Alam station. It has 107,329 instances recorded from the year 1998 to 2010. The input weight and bias for hidden layers are randomly selected, whereas the best neurons’ number of hidden layer is determined from 5 to 20. The number of neurons (11) with regularization (0.8) using tribas activation function showed the best model. The proposed model has obtained better accuracy performance (0.007999 MSE) and better processing time (2.699 s) compared with conventional MPE. It can be concluded that the proposed algorithm can be used as a good prediction technique for time series data.

KW - Data mining

KW - Extreme learning machine

KW - Neural networks

KW - Ozone

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=85066159002&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066159002&partnerID=8YFLogxK

U2 - 10.1007/978-981-13-6031-2_9

DO - 10.1007/978-981-13-6031-2_9

M3 - Chapter

AN - SCOPUS:85066159002

T3 - Lecture Notes in Networks and Systems

SP - 151

EP - 165

BT - Lecture Notes in Networks and Systems

PB - Springer

ER -