Improved Ozone Pollution Prediction Using Extreme Learning Machine with Tribas Regularization Activation Function

  • Noraini IsmailEmail author
  • Zulaiha Ali Othman
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 67)


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.


Ozone Extreme learning machine Prediction Neural networks Data mining 



This research was supported by FRGS grant (FRGS/1/2016/ICT02/UKM/02/8), funded by the Ministry of Higher Education.


  1. 1.
    Rubin MB (2001) The history of ozone. The Schönbein period, 1839–1868. Bull Hist Chem 26(1):40–56Google Scholar
  2. 2.
    Austin E, Zanobetti A, Coull B, Schwartz J, Gold DR, Koutrakis P (2015) Ozone trends and their relationship to characteristic weather patterns. J Expo Sci Environ Epidemiol 25(5):535–542CrossRefGoogle Scholar
  3. 3.
    WHO (1991) Guidelines for the assessment of herbal medicines. World Health Organization, GenevaGoogle Scholar
  4. 4.
    Othman ZA, Ismail N, Latif MT (2017) Association pattern of NO2 and NMHC towards high ozone concentration in klang. In: 2017 6th international conference on electrical engineering and informatics (ICEEI), pp 1–6Google Scholar
  5. 5.
    Zhao W, Fan S, Guo H, Gao B, Sun J, Chen L (2016) Assessing the impact of local meteorological variables on surface ozone in Hong Kong during 2000–2015 using quantile and multiple line regression models. Atmos Environ 144:182–193CrossRefGoogle Scholar
  6. 6.
    Ahamad F, Latif MT, Tang R, Juneng L, Dominick D, Juahir H (2014) Variation of surface ozone exceedance around Klang Valley, Malaysia. Atmos Res 139:116–127CrossRefGoogle Scholar
  7. 7.
    Alvarez LJR, Lowe D, Badia A, Dorling SR, Lupascu A (2017) The source of ozone during an air pollution episode in the UK: a case study from the ICOZA campaignGoogle Scholar
  8. 8.
    Othman ZA, Ismail N, Latif MT (2017) Association rules of temperature towards high and low ozone in Putrajaya. In: 2017 6th international conference on electrical engineering and informatics (ICEEI), pp 1–5Google Scholar
  9. 9.
    Karlsson PE et al (2017) Past, present and future concentrations of ground-level ozone and potential impacts on ecosystems and human health in northern Europe. Sci Total Environ 576:22–35CrossRefGoogle Scholar
  10. 10.
    Sajjadi S et al (2016) Extreme learning machine for prediction of heat load in district heating systems. Energy Build 122:222–227CrossRefGoogle Scholar
  11. 11.
    Najah A, El-Shafie A, Karim OA, El-Shafie AH (2013) Application of artificial neural networks for water quality prediction. Neural Comput Appl 22(Suppl 1):187–201CrossRefGoogle Scholar
  12. 12.
    Ding S, Zhao H, Zhang Y, Xu X, Nie R (2015) Extreme learning machine: algorithm, theory and applications. Artif Intell Rev 44(1):103–115CrossRefGoogle Scholar
  13. 13.
    Deo RC, Şahin M (2015) Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia. Atmos Res 153:512–525CrossRefGoogle Scholar
  14. 14.
    Huang G, Bin Huang G, Song S, You K (2015) Trends in extreme learning machines: a review. Neural Netw 61:32–48CrossRefGoogle Scholar
  15. 15.
    Zaremba W, Sutskever I, Vinyals O (2014) Recurrent neural network regularization. Iclr, zenb. 2013, pp 1–8Google Scholar
  16. 16.
    Fakhr MW, Youssef ENS, El-Mahallawy MS (2015) L1-regularized least squares sparse extreme learning machine for classification. In: 2015 international conference on information and communication technology research, ICTRC 2015, pp 222–225Google Scholar
  17. 17.
    Martínez-Martínez JM, Escandell-Montero P, Soria-Olivas E, Martín-Guerrero JD, Magdalena-Benedito R, Gómez-Sanchis J (2011) Regularized extreme learning machine for regression problems. Neurocomputing 74(17):3716–3721CrossRefGoogle Scholar
  18. 18.
    Izhab Z (1992) Effective reading is the way to ensure success of science students. Surat kepada Editor, New Straits Times, p 9Google Scholar
  19. 19.
    Dick T (2017) The effect of a missing at random missing data mechanism on a single layer artificial neural network with a sigmoidal activation function and the use of multiple imputation as a correction. West Virginia UniversityGoogle Scholar
  20. 20.
    Yadav A, Sahu K (2017) Wind forecasting using artificial neural networks: a survey and taxonomy. Int J Res Sci 3:148–155Google Scholar
  21. 21.
    Venkitaraman A, Chatterjee S, Händel P (2018) Extreme learning machine for graph signal processing. arXiv Prepr. arXiv:1803.04193
  22. 22.
    Cao W, Gao J, Ming Z, Cai S (2017) Some tricks in parameter selection for extreme learning machine. In: IOP conference series: materials science and engineering, vol 261, p 1Google Scholar
  23. 23.
    Dobbin KK, Simon RM (2011) Optimally splitting cases for training and testing high dimensional classifiers. BMC Med Genomics 4:31CrossRefGoogle Scholar
  24. 24.
    Bisht M, Seeja KR (2018) Air pollution prediction using extreme learning machine: a case study on Delhi (India), vol 79Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Faculty of Information Science and Technology, Center for Artificial Intelligence and TechnologyUniversiti Kebangsaan MalaysiaBangiMalaysia

Personalised recommendations