Ground-level ozone prediction by support vector machine approach with a cost-sensitive classification scheme

Science of the Total Environment

Volumn 395, Issue 2-3, 2008, Pages 109-116

  Lu, Wei Zhen ^a   Wang, Dong ^a  

^a CITY UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

Class imbalance problem; Cost sensitive classification; Ozone; Support vector classification; Support vector regression

Indexed keywords

AIR QUALITY; CLASSIFICATION (OF INFORMATION); HEALTH CARE; PROBLEM SOLVING; SUPPORT VECTOR MACHINES;

CLASS IMBALANCE PROBLEM; COST-SENSITIVE CLASSIFICATION; SUPPORT VECTOR CLASSIFICATION; SUPPORT VECTOR REGRESSION;

OZONE;

OZONE;

AIR QUALITY; COST-BENEFIT ANALYSIS; EMISSION; OZONE; POLLUTION MONITORING; PREDICTION; SENSITIVITY ANALYSIS;

AIR MONITORING; AIR QUALITY; ARTICLE; HONG KONG; PREDICTION; PRIORITY JOURNAL; PUBLIC HEALTH; SUPPORT VECTOR MACHINE;

AIR; AIR POLLUTANTS; ALGORITHMS; ENVIRONMENTAL MONITORING; HONG KONG; MODELS, THEORETICAL; OZONE; PREDICTIVE VALUE OF TESTS; REGRESSION ANALYSIS;

ASIA; CHINA; EURASIA; FAR EAST; HONG KONG;

SPRING VIREMIA OF CARP VIRUS;

EID: 41549103711     PISSN: 00489697     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.scitotenv.2008.01.035     Document Type: Article

References (26)

1. Ambroise C., and Grandvalet Y. Prediction of ozone peaks by mixture models. Ecol Model 145 (2001) 275-289
2. Bennett K.P., and Campbell C. Support vector machines: hype or hallelujah?. SIGKDD Explor 2 (2000) 1-13
3. Bradley A. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30 (1997) 1145-1159
4. Cawley G.C., Dorling S.R., Foxall R.J., and Mandic D.P. Estimating the costs associated with worthwhile predictions of poor air quality. Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithms. New York (2001) 485-488 [April]
5. Chan L.Y., Chan C.Y., and Qin Y. Surface ozone pattern in Hong Kong. J Appl Meteorol 37 (1998) 1153-1165
6. Dorling S.R., Foxall R.J., Mandic D.P., and Cawley G.C. Maximum likelihood cost functions for neural network models of air quality data. Atmos Environ 37 (2003) 3435-3443
7. Fortuna L., Rizzotto G., Lavorgna M., Nunnari G., Xibilia M.G., and Caponetto R. Soft computing: new trends and applications (2001), Springer, London
8. Gardner M.W., and Dorling S.R. Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London. Atmos Environ 33 (1999) 709-719
9. Guyon I., and Elisseeff A. An introduction to variable and feature selection. J Mach Learn Res 3 (2003) 1157-1182
10. Hong Kong Environmental Protection Department. Air quality in Hong Kong (2004)
11. Japkowicz N., and Stephen S. The class imbalance problem: a systematic study. Intell Data Anal 6 (2002) 429-449
12. Larsen R.I., McDonnell W.F., and Horstman D.H. An air quality data analysis system for interrelating effects standards, and needed source reductions: part 11, A lognormal model relating human lung function decrease to ozone exposure. J Air Waste Manage Assoc 41 (1991) 455-459
13. Lee Y.C., Calori G., Hills P., and Carmichael G.R. Ozone episodes in urban Hong Kong 1994-1999. Atmos Environ 36 (2002) 1957-1968
14. Lefohn A.S., and Foley J.K. Establishing relevant ozone standards to protect vegetation and human health: expose/dose response considerations. J Air Waste Manage Assoc 43 (1993) 106-112
15. Lin Y., Lee Y., and Wahba G. Support vector machines for classification in nonstandard situations. Technical Report 1016 (2000), Department of Statistics, University of Wisconsin, Madison
16. Lu W.Z., and Wang W.J. Potential assessment of the "support vector machine" method in forecasting ambient air pollutant trends. Chemosphere 59 (2005) 693-701
17. Margineantu O.S. Methods for cost-sensitive learning. PhD thesis 2002; Oregon State University.
18. National Ambient Air Quality Standards for Ozone. Final Rule. Fed Regist 62 138 (1997) 38855-38896
19. Niska H., Rantamaki M., Hiltunen T., Karppinen A., Kukkonen J., Ruuskanen J., et al. Evaluation of an integrated modelling system containing a multi-layer perceptron model and the numerical weather prediction model HIRLAM for the forecasting of urban airborne pollutant concentrations. Atmos Environ 39 (2005) 6524-6536
20. Schlinka U., Dorling S., Pelikan E., Nunnari G., Cawley G., Junninen H., et al. A rigorous inter-comparison of ground-level ozone predictions. Atmos Environ 37 (2003) 3237-3253
21. So K.L., and Wang T. On the local and regional influence on ground-level ozone concentrations in Hong Kong. Environ Pollut 123 (2003) 307-317
22. Spektor D.M., Thurston G.D., Mao J., He D., Hayes C., and Lippmann M. Effects of single and multiday ozone exposures on respiratory function in active normal children. Environ Res 55 (1991) 107-122
23. 3 and related photochemical oxidants. EPA/600/P-93/004a-cF (1996)
24. Vapnik V. The nature of statistical learning theory (1995), Wiley, New York, USA
25. Wang D., and Lu W.Z. Forecasting of ozone level in time series using MLP model with a novel hybrid training algorithm. Atmos Environ 40 (2006) 913-924
26. Wang W.J., Xu Z.B., Lu W.Z., and Zhang X.Y. Determination of the spread parameter in the Gaussian kernel for classification and regression. Neurocomputing 55 (2003) 643-663