Intelligent security systems engineering for modeling fire critical incidents: Towards sustainable security

Abstract

An intelligent security systems engineering approach is used to analyze fire and explosive critical incidents, a growing concern in urban communities. A feed-forward back-propagation neural network models the damages arising from these critical incidents. The overall goal is to promote fire safety and sustainable security. The intelligent security systems engineering prediction model uses a fully connected multilayer neural network and considers a number of factors related to the fire or explosive incident including the type of property affected, the time of day, and the ignition source. The network was trained on a large number of critical incident records reported in Toronto, Canada between 2000 and 2006. Our intelligent security systems engineering approach can help emergency responders by improving critical incident analysis, sustainable security, and fire risk management.

Keywords

Intelligent security / systems engineering / fire / feed-forward neural networks / critical incidents

References

[1] Battiti, R. & Masulli, F. (1990). BFGS optimization for faster and automated supervised learning. In: Proceedings of the International Neural Network Conference, 757–760, Paris

[2] Chen K., Jacobson C., Blong R.. Artificial neural networks for risk decision support in natural hazards: a case study of assessing the probability of house survival from bushfires. Environmental Modeling and Assessment, 2004, 9(3): 189-199.

[3] Choudhury J.R., Banerjee T.P., Das S., Abraham A., Snášel V.. Fuzzy rule based intelligent security and fire detector system. Advances in Soft Computing, 2009, 63: 45-51.

[4] Council of Canadian Fire Marshals and Fire Commissioners (CCFM-FC). (2007). Fire losses in Canada. Annual Report 2002

[5] Critical Incident Analysis Group (CIAG). (2009). University of Virginia. Available via DIALOG. http://www.healthsystem.virginia.edu/internet/ciag/

[6] Gurney, K. (1997). An Introduction to Neural Networks. Routledge, London

[7] Hagan M.T., Menhaj M.B.. Training feed forward network with the Marquardt algorithm. IEEE Trans. on Neural Net., 1994, 5(6): 989-993.

[8] Haykin, S. (1999). Neural Networks: A Comprehensive Foundation. Prentice Hall

[9] Hornik K.. Approximation capabilities of multilayer feedforward networks. Neural Networks, 1991, 4(22): 251-257.

[10] Johansson M., Dowla F.U., Goodman D.M.. Backpropagation learning for multilayer feed-forward neural networks using the conjugate gradient method. Int. J. Neural Syst., 1991, 2(4): 291-301.

[11] Lo S.M., Liu M., Yuen R.K.K.. An artificial neural-network based predictive model for pre-evacuation human response in domestic building fire. Fire Technology, 2009, 45(4): 431-439.

[12] National Center for Critical Incident Analysis (NCCIA) (2009). National Defense University. Available via DIALOG. http://www.criticalincident.org/index.html

[13] Nelson M.M., Illingworth W.T.. A Practical Guide to Neural Nets, 1991, Reading, MA: Addison-Wesley

[14] Rose-Pehrsson S.L., Hart S.J., Street T.T., Williams F.W., Hammond M.H., Gottuk D.T., Wright M.T., Wong J.T.. Early warning fire detection system using a probabilistic neural network. Fire Technology, 2003, 39(2): 147-171.

[15] Rumelhart D.E., Hinton G.E., Williams R.J.. Learning internal representations by error propagation. Parallel Data Processing, 1986, 1(8): 318-362.

[16] Suratgar A.A., Tavakoli M.B., Hoseinabadi A.. Modified Levenberg-Marquardt method for neural networks training. Trans. Eng. Comput. Technol., 2005, 6: 46-48.

[17] Ung S.T., Williams V., Bonsall S.. Test case based risk predictions using artificial neural network. Journal of Safety Research, 2006, 37(3): 245-260.

[18] Xia, D. (2007). Fire risk evaluation model of high-rise buildings based on multilevel BP neural network. In: Fourth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), Haikou, Hainan, China, 2007

[19] Zurada J.. Introduction to Artificial Neural Systems, 1992, St. Paul, MN: West Publishing Co.