Cluster Computing

, Volume 22, Supplement 3, pp 6417–6424 | Cite as

The radial basis function analysis of fire evacuation model based on RBF neural network

  • Lijie ZhangEmail author
  • Jianchang Liu
  • Shubin Tan


After the occurrence of major accidents, the people in the buildings should be evacuated to safe areas within the shortest time. It is the important part of safe evacuation and reduction of mass mortality accidents. Therefore, the research of fire evacuation problem has highly theoretical and practical values. In the fire evacuation scene, the individual attributes are affected by psychology and behavior among individuals. Based on radial basis function neural network, we used the principal component analysis to determine six main factors affecting evacuation time. These factors are taken as the input of neural network; the evacuation time as the output of neural network. The network was trained by 125 sets of survey data. The quadratic sum error of the model was similar to 0, thus better achieving simulation of actual situation.


Fire evacuation Radial basis function Neural network Model establishment 



National Natural Science Foundation of China (NSFC) (Nos. 61374137, 61773106, 61703086), the IAPI Fundamental Research Funds (2013ZCX02-03).


  1. 1.
    Helbing, D., Illes, J., Farkas, P.: Simulation of Pedestrian Crowds in Normal and Evacuation Situations. Pedestrain and Evacuation Dynamics, pp. 21–58. Springer, Berlin (2001)Google Scholar
  2. 2.
    Helbing, D.: Traffic and related self-driven many-particle systems. Rev. Mod. Phys. 73, 1067–1141 (2001)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Galea, E.R., Blake, S.: Collection and Analysis of Human Behaviour Data Appearing in the Mass Media Relating To The Evacuation of The World Trade Centre Towers of 11 September 2001, pp. 4–6. Office of the Deputy Prime Minister, London (2004)Google Scholar
  4. 4.
    Helbing, D., Farkas, I., Vicsek, T.: Simulating dynamical features of escape panic. Nature 407, 487–490 (2000)CrossRefGoogle Scholar
  5. 5.
    Helbing, D., Schonhof, M., Kern, D.: Volatile decision dynamics: experiments, stochastic description, intermittency control, and traffic optimization. New J. Phys. 4(33), 1–33 (2002)MathSciNetGoogle Scholar
  6. 6.
    Helbing, D., Platkowski, T.: Self-organization in space and induced by fluctuations. Int. J. Chaos Theory Appl. 5(2), 25–38 (2000)Google Scholar
  7. 7.
    Helbing, D.: A fluid dynamics model for movement of pedestrians. Complex Syst. 6(1), 391–415 (1992)MathSciNetzbMATHGoogle Scholar
  8. 8.
    Henderson, F.: The statistics of crowd fluids. Nature 229, 381–383 (1971)CrossRefGoogle Scholar
  9. 9.
    Henderson, F.: Sexual differences in human crowd notion. Nature 240(8), 353–355 (1972)CrossRefGoogle Scholar
  10. 10.
    Mitchell, H., MacGregor, J.: Topological network design of pedestrian networks. Transp. Res. B 35, 107–135 (2001)CrossRefGoogle Scholar
  11. 11.
    Lovas, G.: Modeling and simulation of pedestrian traffic flow. Transp. Res. B 28, 429–443 (1994)CrossRefGoogle Scholar
  12. 12.
    Murakami, Y., Minami, K., Kawasoe, T., et al.: Multi-agent simulation for crisis management. In: KMN’02 Proceedings of the IEEE Workshop on Knowledge Media Networking. Washington: IEEE Computer Society, pp. 135–139 (2002)Google Scholar
  13. 13.
    Society of Fire Protection Engineers. SFPE Handbook of Fire Protection Engineering (2002 Edition).Quincy, MA: National fire protection association (NFPA),2003-01Google Scholar
  14. 14.
    Smith, A.: Density velocity and flow relationships for closely packed crowds. Saf. Sci. 18, 321–327 (1995)CrossRefGoogle Scholar
  15. 15.
    Matthew, O.: The EXODUS evacuation model applied to building evacuation scenarios. Fire Eng. J. 20(7), 27–30 (1996)Google Scholar
  16. 16.
    Gwynne, S., Galea, E.R., Owen, M.: An investigation of the aspects of occupant behavior required for evacuation modeling. Appl. Fire Sci. 8(1), 19–59 (1988)Google Scholar
  17. 17.
    Wolfram, S.: Theory and Applications of Cellular Automata, pp. 41–44. World Scientific, Singapore (1986)Google Scholar
  18. 18.
    Helbing, D.: A mathematical model for behavioral changes by pair interactions and its relation to game theory. Angewandte Sozialforschung 18(3), 117–132 (1994)Google Scholar
  19. 19.
    Wang, X.H., Yan, M.: An emergency evacuation elgorithm in large building fire. Software 32(2), 112–114 (2011)MathSciNetGoogle Scholar
  20. 20.
    Cui, X.H., Li, Q., Chen, J., Chen, C.X.: Study on occupant evacuation model in large public place: to consider individual character and following behavior. J. Nat. Disasters 14(6), 133–140 (2005)Google Scholar
  21. 21.
    Nguyen, V.Q., Nguyen, M.T., Nguyen, V.N.: Sliding mode control of a three phase induction motor based on RBF neural network. System Science and Engineering (ICSSE), 2017, July: 21–23Google Scholar
  22. 22.
    Sandeep, K., Satchidananda, D., Alok, K.: ABC optimized RBF network for classification of EEG signal for epileptic seizure identification. Egypt. Inform. J. 18(1), 55–66 (2017)CrossRefGoogle Scholar
  23. 23.
    Zhou, Qingyuan, Luo, Jianjian: Artificial neural network based grid computing of E-government scheduling for emergency management. Comput. Syst. Sci. Eng. 30(5), 327–335 (2015)Google Scholar
  24. 24.
    Zhou, Q., Luo, J.: The study on evaluation method of urban network security in the big data era. Intell. Autom. Soft Comput. (2017). CrossRefGoogle Scholar
  25. 25.
    Zhou, Qingyuan, Luo, Jianjian: The risk management using limit theory of statistics on extremes on the big data era. J. Comput. Theor. Nanosci. 12, 6237–6243 (2015). CrossRefGoogle Scholar
  26. 26.
    Liu, R., Pan, T., Li, Z.: Multi-model recursive identification for nonlinear systems with non-uniformly sampling. Clust. Comput. 20(1), 25–32 (2017)CrossRefGoogle Scholar
  27. 27.
    Liu, R., Xu, H., Zheng, E., et al.: Adaptive filtering for intelligent sensing speech based on multi-rate LMS algorithm. Clust. Comput. 20(2), 1493–1509 (2017)CrossRefGoogle Scholar
  28. 28.
    Fathi, M., Mohebbi, M., Razavi, S.M.A.: Application of image analysis and artificial neural network to predict mass transfer kinetics and color changes of osmotically dehydrated kiwifruit. Food Bioprocess. Technol. 4(8), 1357–1366 (2011)CrossRefGoogle Scholar
  29. 29.
    Kashaninejad, M., Dehghani, A.A., Kashiri, M.: Modeling of wheat soaking using two artificial neural networks (MLP and RBF). J. Food Eng. 91(4), 602–607 (2009)CrossRefGoogle Scholar
  30. 30.
    Li, G., Song, Z.: RBF neural network prediction model based on particle swarm optimization for internet-based teleoperation. In: Proceedings of the 2014 Seventh International Symposium onComputational Intelligence and Design (ISCID), pp. 34–37 (2014)Google Scholar
  31. 31.
    Zhou, Q.: Multi-layer affective computing model based on emotional psychology. Electron. Commer. Res. (2017). CrossRefGoogle Scholar
  32. 32.
    Xie, J., Luo, J., Zhou, Q.: Data mining based quality analysis on informants involved applied research. Clust. Comput. 19(4), 1885–1893 (2016). CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Northeastern UniversityShenyangPeople’s Republic of China
  2. 2.Ningxia Institute of Science and TechnologyShizuishanPeople’s Republic of China

Personalised recommendations