Hava Kalite İndeksinin Tahmin Başarısının Artırılması için Topluluk Regresyon Algoritmalarının Kullanılması
Abstract
Şehirlerdeki hava kalitesi
seviyesinin düzenli aralıklarla ölçülmesi ve ölçüm sonuçlarının incelenerek
gerekli önlemlerin alınması bu şehirlerde yaşayan insanların ve diğer canlıların
sağlıkları için oldukça önemlidir. Ülkemizde bu amaçla ilgili bakanlık
tarafından pek çok şehre hava kalitesi ölçüm istasyonları kurulmuştur. Bu
çalışmada bu istasyonlardan biri olan Adana ili valilik istasyonuna ait ölçüm
verileri kullanıldı. Kullanılan veriler kükürt dioksit (SO2), azot
dioksit (NO2), ozon (O3), karbon monoksit (CO) ve toz
parçacıkları (PM10) gibi hava kirletici gazların ölçüm değerlerdir. Bu verilere
farklı makine öğrenme algoritmaları uygulanarak hava kalite indeksi tespit edildi.
Kullanılan makine öğrenmesi regresyon algoritmaları; rastgele orman, karar
ağacı, destek vektör, k-en yakın komşu, doğrusal, yapay sinir ağı, yığın, uyumlu artırıcı, eğimli artırıcı ve örneklemeli
toplam regresyonudur. Bu algoritmaların hata oranları ve çalışma süreleri
bakımından başarı değerleri kıyaslanarak elde edilen sonuçlar
değerlendirilmiştir.
References
- [1] L.H. Tecer, Hava Kirliliği ve Sağlığımız. Bilim ve Aklın Aydınlığında Eğitim. S. 135, ss. 15-29., Mayıs 2011.[2] K. Veljanovska and A. Dimoski, Air Quality Index Prediction Using Simple Machine Learning Algorithms. International Journal of Emerging Trends & Technology in Computer Science (IJETTCS). Volume 7. Issue 1. January - February 2018. pp. 025-030. ISSN 2278-6856. 2018.[3] E.A. Dragomir, Air Quality Index Prediction using K-Nearest Neighbor Technique. BULETINUL Universităţii Petrol – Gaze din Ploieşti. Volume 62. No 1. pp. 103 – 108, 2010.[4] M.D. Adams et al., Air Quality Health Index Mapping: A Data Driven Modelling Approach. Proceedings of the 13th International Conference on Environmental Science and Technology Athens, Greece, 5-7 September 2013.[5] R. Raturi and J.R. Prasad, Recognition of Future Air Quality Index Using Artificial Neural Network. International Research Journal of Engineering and Technology (IRJET). Volume: 05 Issue: 03 e-ISSN: 2395-0056, 2018.[6] B. Zhai and J. Chen, Research on the forecasting of Air Quality Index (AQI) based on FS-GABPNN: A case study of Beijing, China. Proceedings of the 14th ISCRAM Conference – Albi, France, May 2017.[7] H. Wang et al, Air Quality Index Forecast Based on Fuzzy Time Series Models. Journal of Residuals Science & Technology, Vol. 13, No. 5. doi:10.12783/issn.1544-8053/13/5/161, 2016.[8] http://www.havaizleme.gov.tr (Nisan 2018’de erişildi)[9] https://www3.epa.gov/airnow/aqi_brochure_02_14.pdf (Ekim 2018’de erişildi)[10] http://www.havaizleme.gov.tr/home/HKI (Nisan 2018’de erişildi)[11] https://www.spyder-ide.org (Nisan 2018’de erişildi)[12] J.M. Stanton ,” Galton, Pearson, and the Peas: A Brief History of Linear Regression for Statistics Instructors”, Journal of Statistics Education, 9:3, DOI: 10.1080/10691898.2001.11910537, 2017.[13] J.R. QUINLAN, Machine Learning 1: 81-106, 1986[14] K. Alkhatib et al., Stock Price Prediction Using K-Nearest Neighbor (k-NN) Algorithm. Int. J. Bus. Humanit. Technol., vol. 3, no. 3, pp. 32–44, March., 2013.[15] V. Vapnik, The nature of statistical learning theory, Springer-Verlag, New York, 2000.[16] A.J. Smola and B. Schölkopf, A tutorial on support vector regression, Statistics and Computing, 14 (3), 199-222, 2004.[17] F. Murtagh, Multilayer perceptron for classification and regression. Neurocomputing. Volume 2, Issues 5-6, Pages 183-197, doi.org/10.1016/0925-2312(91)90023-5, 1991.[18] L. Breiman, ”Random forests”. Machine Learning, 45 (1): s.5-32., 2001.[19] L. Breiman, "Stacked regressions." Machine learning 24.1. 49-64, 1996.[20] Y. Freund and R. Schapire, “A Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting”, 1995.[21] J.H. Friedman, "Greedy Function Approximation: A Gradient Boosting Machine", 1999.[22] L. Breiman, “Bagging predictors”, Machine Learning, 24(2), 123-140, 1996.
Abstract
Measuring the air quality level in the
city at regular intervals and taking the necessary measures by examining the
results of the measurement is very important for the health of the people and
other living things in these cities. For this purpose, air quality measurement
stations have been established in many cities by the relevant ministry. In this
study, one of these stations, Adana province provincial station measurement
data was used. The data used are the measured values of air pollutant gases
such as sulfur dioxide (SO2), nitrogen dioxide (NO2), ozone (O3), carbon
monoxide (CO) and dust particles (PM10). The air quality index was determined
by applying different machine learning algorithms to these data. Machine
learning regression algorithms used; random forest, decision tree, support
vector, k-nearest neighbor, linear, artificial neural network, stacking,
adaboost, gradient boosting and bagging regression. The results obtained by
comparing the success rates of these algorithms in terms of error rates and run
times were evaluated.
References
- [1] L.H. Tecer, Hava Kirliliği ve Sağlığımız. Bilim ve Aklın Aydınlığında Eğitim. S. 135, ss. 15-29., Mayıs 2011.[2] K. Veljanovska and A. Dimoski, Air Quality Index Prediction Using Simple Machine Learning Algorithms. International Journal of Emerging Trends & Technology in Computer Science (IJETTCS). Volume 7. Issue 1. January - February 2018. pp. 025-030. ISSN 2278-6856. 2018.[3] E.A. Dragomir, Air Quality Index Prediction using K-Nearest Neighbor Technique. BULETINUL Universităţii Petrol – Gaze din Ploieşti. Volume 62. No 1. pp. 103 – 108, 2010.[4] M.D. Adams et al., Air Quality Health Index Mapping: A Data Driven Modelling Approach. Proceedings of the 13th International Conference on Environmental Science and Technology Athens, Greece, 5-7 September 2013.[5] R. Raturi and J.R. Prasad, Recognition of Future Air Quality Index Using Artificial Neural Network. International Research Journal of Engineering and Technology (IRJET). Volume: 05 Issue: 03 e-ISSN: 2395-0056, 2018.[6] B. Zhai and J. Chen, Research on the forecasting of Air Quality Index (AQI) based on FS-GABPNN: A case study of Beijing, China. Proceedings of the 14th ISCRAM Conference – Albi, France, May 2017.[7] H. Wang et al, Air Quality Index Forecast Based on Fuzzy Time Series Models. Journal of Residuals Science & Technology, Vol. 13, No. 5. doi:10.12783/issn.1544-8053/13/5/161, 2016.[8] http://www.havaizleme.gov.tr (Nisan 2018’de erişildi)[9] https://www3.epa.gov/airnow/aqi_brochure_02_14.pdf (Ekim 2018’de erişildi)[10] http://www.havaizleme.gov.tr/home/HKI (Nisan 2018’de erişildi)[11] https://www.spyder-ide.org (Nisan 2018’de erişildi)[12] J.M. Stanton ,” Galton, Pearson, and the Peas: A Brief History of Linear Regression for Statistics Instructors”, Journal of Statistics Education, 9:3, DOI: 10.1080/10691898.2001.11910537, 2017.[13] J.R. QUINLAN, Machine Learning 1: 81-106, 1986[14] K. Alkhatib et al., Stock Price Prediction Using K-Nearest Neighbor (k-NN) Algorithm. Int. J. Bus. Humanit. Technol., vol. 3, no. 3, pp. 32–44, March., 2013.[15] V. Vapnik, The nature of statistical learning theory, Springer-Verlag, New York, 2000.[16] A.J. Smola and B. Schölkopf, A tutorial on support vector regression, Statistics and Computing, 14 (3), 199-222, 2004.[17] F. Murtagh, Multilayer perceptron for classification and regression. Neurocomputing. Volume 2, Issues 5-6, Pages 183-197, doi.org/10.1016/0925-2312(91)90023-5, 1991.[18] L. Breiman, ”Random forests”. Machine Learning, 45 (1): s.5-32., 2001.[19] L. Breiman, "Stacked regressions." Machine learning 24.1. 49-64, 1996.[20] Y. Freund and R. Schapire, “A Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting”, 1995.[21] J.H. Friedman, "Greedy Function Approximation: A Gradient Boosting Machine", 1999.[22] L. Breiman, “Bagging predictors”, Machine Learning, 24(2), 123-140, 1996.
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Engineering |
| Journal Section | Articles |
| Authors | |
| Publication Date | September 28, 2019 |
| Submission Date | November 2, 2018 |
| Published in Issue | Year 2019 Volume: 7 Issue: 3 |
