Volume 6, Issue 1 (5-2013)
ijhe 2013, 6(1): 1-10 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Noori R, Hoshyaripour G, Ashrafi K, Rasti O. Introducing an Appropriate Model using Support Vector Machine for Predicting Carbon Monoxide Daily Concentration in Tehran Atmosphere . ijhe 2013; 6 (1) :1-10
URL: http://ijhe.tums.ac.ir/article-1-5133-en.html
URL: http://ijhe.tums.ac.ir/article-1-5133-en.html
1- Department of Civil Engineering, Islamic Azad University, Malard Branch, Tehran, Iran , roohollahnoori@gmail.com
2- Department of Geophysics, Institute of Geophysics, University of Hamburg, Hamburg, Germany
3- Department of Civil Engineering, Islamic Azad University, Malard Branch, Tehran, Iran
4- Department of Politic Geography, Faculty of Geography, University of Birjand, Khorasan Jonoubi, Iran
2- Department of Geophysics, Institute of Geophysics, University of Hamburg, Hamburg, Germany
3- Department of Civil Engineering, Islamic Azad University, Malard Branch, Tehran, Iran
4- Department of Politic Geography, Faculty of Geography, University of Birjand, Khorasan Jonoubi, Iran
Abstract: (15717 Views)
Backgrounds and Objectives: Precise air pollutants prediction, as the first step in facing air pollution problem, could provide helpful information for authorities in order to have appropriate actions toward this challenge. Regarding the importance of carbon monoxide (CO) in Tehran atmosphere, this study aims to introduce a suitable model for predicting this pollutant.
Materials and Method: We used the air pollutants and meteorological data of Gholhak station located in the north of Tehran these data provided 12 variables as inputs for predicting the average CO concentration of the next day. First, support vector machine (SVM) model was used for forecasting CO daily average concentration. Then, we reduced the SVM inputs to seven variables using forward selection (FS) method. Finally, the hybrid model, FS-SVM, was developed for CO daily average concentration forecasting.
Result: In the research, we used correlation coefficient to evaluate the accuracy of both SVM and FS-SVM models. Findings indicated that correlation coefficient for both models in testing step was equal (R~0.88). It means that both models have proper accuracy for predicting CO concentration. However, it is noteworthy that FS-SVM model charged fewer amounts of computational and economical costs due to fewer inputs than SVM model.
Conclusion: Results showed that although both models have relatively equal accuracy in predicting CO concentration, FS-SVM model is the superior model due to its less number of inputs and therefore, less computational burden.
Materials and Method: We used the air pollutants and meteorological data of Gholhak station located in the north of Tehran these data provided 12 variables as inputs for predicting the average CO concentration of the next day. First, support vector machine (SVM) model was used for forecasting CO daily average concentration. Then, we reduced the SVM inputs to seven variables using forward selection (FS) method. Finally, the hybrid model, FS-SVM, was developed for CO daily average concentration forecasting.
Result: In the research, we used correlation coefficient to evaluate the accuracy of both SVM and FS-SVM models. Findings indicated that correlation coefficient for both models in testing step was equal (R~0.88). It means that both models have proper accuracy for predicting CO concentration. However, it is noteworthy that FS-SVM model charged fewer amounts of computational and economical costs due to fewer inputs than SVM model.
Conclusion: Results showed that although both models have relatively equal accuracy in predicting CO concentration, FS-SVM model is the superior model due to its less number of inputs and therefore, less computational burden.
Type of Study: Research |
Subject:
Air
Received: 2012/02/8 | Accepted: 2012/05/6 | Published: 2013/12/28
Received: 2012/02/8 | Accepted: 2012/05/6 | Published: 2013/12/28
Send email to the article author
| Rights and Permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
