Fire Situation Forecasting Based on Support Vector Machine Optimized by Genetic Algorithm

Yue Liang; Hong Xia Guo

doi:10.4028/www.scientific.net/AMR.1073-1076.1562

Paper Titles

Some Application Researches on the Performance Evaluation of Manufacturing Supply Chain Collaboration
p.1538

Research on the Connotation of Life Cycle of Ship
p.1544

Modeling and Rationing Evacuation in Russia
p.1551

Seismic Mortality Estimation in China: A Comparison of Three Empirical Models
p.1557

Fire Situation Forecasting Based on Support Vector Machine Optimized by Genetic Algorithm
p.1562

Study of the Dynamic Characteristics of Landslides Based on the DAN-W Model
p.1567

A Study on Oxygen Leak-Diffusion Process and Environmental Influence of High-Pressure Liquid of Spherical Tank
p.1574

A Study on Disastrous Law of Flood in Hubei Province
p.1581

Cleaner Production Potential of Industries in Liao River Basin
p.1587

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 1073-1076Fire Situation Forecasting Based on Support Vector...

Fire Situation Forecasting Based on Support Vector Machine Optimized by Genetic Algorithm

Abstract:

Improve the prediction accuracy of fire situation reasonably has great significance for fire prevention and fire deployment. Firstly, build a fire situation prediction model by using support vector regression; followed adopt genetic algorithm to select the optimal combination of parameters; finally provide empirical analysis by taking Chinese Zhejiang Province, test reliability and practicality of model. The results showed that: the fire prediction model based on support vector machine has ideal learning ability and generalization ability; the predicted results possess a high precision, thus providing the new idea and method for predicting fire situation.

You might also be interested in these eBooks

Environmental Protection and Resource Utilization IV

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 1073-1076)

Pages:

1562-1566

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.1073-1076.1562

Citation:

Cite this paper

Online since:

December 2014

Authors:

Yue Liang*, Hong Xia Guo

Keywords:

Fire Situation Prediction, Genetic Algorithm (GA), Support Vector Regression

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Li Yin-qing. Fire Protection Engineering. Beijing: Chemical Industry Press, 2004: 25-27.

Google Scholar

[2] Wu Qi-hong. Fire in the form of seriousness and urgency of disciplines. Fire Science and Technology, 24(2), pp.145-152, (2005).

Google Scholar

[3] Jiang Xue-peng, Xu Zhi-sheng. Time trend analysis of fire loss and dynamic Forecast. Fire Science and Technology, 24(4), pp.412-414, (2005).

Google Scholar

[4] Zhen Shuang-zhong. City Fire predictive analysis based on gray system theory. Mathematics in Practice and Theory, 35(1), pp.72-76, (2005).

Google Scholar

[5] Shi Shi-liang, Tang Guang-fa, He Li-wen. Building fire prediction model and its application based on wavelet neural network. Journal of Railway Science and Engineering, 2(2), pp.34-37, (2005).

Google Scholar

[6] Wu Lu-rong. The best combination of gray regression model and its application in China Fire Prediction. Mathematics in Practice and Theory, 38(6), pp.80-84, (2008).

Google Scholar

[7] Lou Wei, Liu Xing-gao. Polypropylene melt index prediction model PcCA-GA-RBF Network. Journal of Petrochemical Universities, 20(3), pp.82-85, (2007).

Google Scholar

[8] Li He-Cheng, Wang Yu-Ping, An interpolation based genetic algorithm for sloving nonlinear bilevel programming problems. Chinese Journal of Computers, 31(6), pp.910-918, June (2008).

DOI: 10.3724/sp.j.1016.2008.00910

Google Scholar

[9] Vanajakshi L, Rilett L R. A comparison of the performance of artifical neural networks and support vector machines for the prediction of traffic speed, IEEE Intelligent Vehieles Symposium, p.194 – 199, (2004).

DOI: 10.1109/ivs.2004.1336380

Google Scholar