Building an Ensemble from a Single Naive Bayes Classifier in the Analysis of Key Risk Factors for Polish State Fire Service
In this paper, we describe our solution in a competition that required performing data mining to identify key risk factors for the State Fire Service of Poland. The goal was to create an ensemble of Naive Bayes classifiers that could predict incidents involving firefighters, rescuers, children, or civilians. To this end, we first created a single Naive Bayes classifier and then partitioned the set of attributes used in that classifier. The attribute subsets were used to create new Naive Bayes classifiers that would form an ensemble, which generally performs better than both the single classifier and ensemble obtained by searching over all attributes considered when creating the single classifier. The application of our approach yielded a solution that ranked third in the competition.(original abstract)
- AAIA'14 Data Mining Competition. Available: https://fedcsis.org/2014/dm_competition
- AAIA'14 Data Mining Competition: Key risk factors for Polish State Fire Service. Available: http://challenge.mimuw.edu.pl/contest/view.php?id=83
- Ballard J. E., Koepsell T. D., and Rivara F., "Association of smoking and alcohol drinking with residential fire injuries," American journal of epidemiology, vol. 135, pp. 26-34, 1992.
- Beckage B. and Platt W. J., "Predicting severe wildfire years in the Florida Everglades," Frontiers in Ecology and the Environment, vol. 1, pp. 235-239, 2003, http://dx.doi.org/10.1890/1540-9295(2003)001[0235:PSWYIT]2.0.CO;2
- Burgess J. L., Duncan M., Mallett J., LaFleur B., Littau S., and Shiwaku K., "International comparison of fire department injuries," Fire Technology, pp. 1-17, 2013, http://dx.doi.org/10.1007/s10694-013-0340-y
- Cantu-Paz E., Newsam S., and Kamath C., "Feature Selection in Scientific Applications," in Proc. ACM International Conference on Knowledge Discovery and Data Mining, 2004, pp. 788-793, http://dx.doi.org/10.1145/1014052.1016915
- Freund Y. and Schapire R. E., "A desicion-theoretic generalization of on-line learning and an application to boosting," in Computational learning theory, 1995, pp. 23-37, http://dx.doi.org/10.1007/3-540-59119-2
- Romanski P., "FSelector: Selecting Attributes," Vienna: R Foundation for Statistical Computing, 2009.
- Shai D., "Income, housing, and fire injuries: a census tract analysis," Public health reports, vol. 121, 2006.
- Tsymbal A., Pechenizkiy M., and Cunningham P., "Diversity in search strategies for ensemble feature selection," Information fusion, vol. 6, pp. 83-98, 2005, http://dx.doi.org/10.1016/j.inffus.2004.04.003
- Warda L., Tenenbein M., and Moffatt M. E., "House fire injury prevention update. Part I. A review of risk factors for fatal and non-fatal house fire injury," Injury Prevention, vol. 5, pp. 145-150, 1999, http://dx.doi.org/10.1136/ip.5.2.145
- Yue X., Mickley L. J., Logan J. A., and Kaplan J. O., "Ensemble projections of wildfire activity and carbonaceous aerosol concentrations over the western United States in the mid-21st century," Atmospheric Environment, vol. 77, pp. 767-780, 2013, http://dx.doi.org/10.1016/j.atmosenv.2013.06.003