Identification of Key Risk Factors for the Polish State Fire Service with Cascade Step Forward Feature Selection

• Autorzy: Piotr Płoński
• Języki publikacji: EN

Abstrakty

EN

The Polish State Fire Service gathers information about incidents which require their intervention. This information is stored to document the events. However, it can be very useful for new officers training, better identification of threats and planning of more effective procedures. The identification of key risk factors for casualties among firefighters, children or other involved people was a topic of data mining competition organized as a part of 1st Complex Events and Information Modelling workshop devoted to the fire protection engineering. The task of the competition was to find ten subsets of features for ten Naive Bayes classifiers. The ensemble output was used to predict occurence of casualities. Herein, the solution description that took 5th place is presented. The proposed method used cascade step forward feature selection procedure to find features subsets.(original abstract)

Słowa kluczowe

EN

Firefighters; Bayesian inference; Algorithms

PL

Straż pożarna; Wnioskowanie bayesowskie; Algorytmy

• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2014
• Tom: 2
• Strony: 369--373

Twórcy

autor

Piotr Płoński

• Warsaw University of Technology, Poland

Bibliografia

• Bąk K., Krasuski A., Szczuka M., "Searching for Concepts in Natural Language Part of Fire Service Reports," In: Proceedings of Concurrency, Specification and Programming; XXIII-th International Workshop, CS&P 2013, Warsaw, Poland, September 25-27, 2013.
• Collective Work (2001) Ewidencja zdarzen% EWID99. Technical report, Abacus. http://www.ewid.pl/?set=rozw_ewid&gr=roz. Accessed date 23 April 2007
• Hastie T., Friedman J., Tibshirani R., "The elements of statistical learning," Springer, 2009, DOI: 10.1007/978-0-387-84858-7
• Janusz A., Krasuski A., Szczuka M., "Improving Semantic Clustering of EWID Reports by Using Heterogeneous Data Types," Lecture Notes in Artificial Intelligence, vol. 8170, 2013, pp. 304-314, DOI: 10.1007/978-3-642-41218-9_33
• Krasuski A., Janusz A., "Semantic Tagging of Heterogeneous Data: Labeling Fire & Rescue Incidents with Threats," 8th International Symposium Advances in Artificial Intelligence and Applications, 2013, pp 77-82
• Krasuski A., Jankowski A., Skowron A., Ślęzak D., "From Sensory Data to Decision Making: A Perspective on Supporting a Fire Commander," Web Intelligence/IAT Workshops, 2013, pp 229-236, DOI: 10.1109/WIIAT. 2013.188
• Krasuski A., Kreński K., Łazowy S., "A Method for Estimating the Efficiency of Commanding in the State Fire Service of Poland," Fire Technology vol.48, 2012, pp 795-805, DOI: 10.1007/s10694-011-0244-7
• Krasuski A., Wasilewski P., "The Detection of Outlying Fire Service's Reports. The FCA Driven Analytics," In Processings of the 11-th International Conferene on Formal Concept Analysis, 2013, pp 35-50
• Krawczyk B., Schaefer G., "A hybrid classifier committee for analyzing asymmetry features in breast thermograms," Applied Soft Computing, vol. 20, 2014, pp 112-118, DOI: 10.1016/j.asoc.2013.11.011
• Płoński P., Gradkowski W., Jednoróg K., Marchewka A., Bogorodzki P., "Dealing with heterogeneous multi-site neuroimaging data sets: a study on discrimination of children dyslexia," In: ´Sl˛eak, D., et al. (Eds.) Brain Informatics and Health, 2014, Lecture Notes in Artificial Intelligence, vol. 8609, 2014, pp 471-480