Intelligent Exit-Selection Behaviors during a Room Evacuation
Zarita Zainuddin1, Lim Eng Aik2**
1School of Mathematical Sciences, Universiti Sains Malaysia, 11800 Minden, Penang, Malaysia 2Institut Matematik Kejuruteraan, Universiti Malaysia Perlis, 02000 Kuala Perlis, Perlis, Malaysia
Intelligent Exit-Selection Behaviors during a Room Evacuation
Zarita Zainuddin1, Lim Eng Aik2**
1School of Mathematical Sciences, Universiti Sains Malaysia, 11800 Minden, Penang, Malaysia 2Institut Matematik Kejuruteraan, Universiti Malaysia Perlis, 02000 Kuala Perlis, Perlis, Malaysia
摘要A modified version of the existing cellular automata (CA) model is proposed to simulate an evacuation procedure in a classroom with and without obstacles. Based on the numerous literature on the implementation of CA in modeling evacuation motions, it is notable that most of the published studies do not take into account the pedestrian's ability to select the exit route in their models. To resolve these issues, we develop a CA model incorporating a probabilistic neural network for determining the decision-making ability of the pedestrians, and simulate an exit-selection phenomenon in the simulation. Intelligent exit-selection behavior is observed in our model. From the simulation results, it is observed that occupants tend to select the exit closest to them when the density is low, but if the density is high they will go to an alternative exit so as to avoid a long wait. This reflects the fact that occupants may not fully utilize multiple exits during evacuation. The improvement in our proposed model is valuable for further study and for upgrading the safety aspects of building designs.
Abstract：A modified version of the existing cellular automata (CA) model is proposed to simulate an evacuation procedure in a classroom with and without obstacles. Based on the numerous literature on the implementation of CA in modeling evacuation motions, it is notable that most of the published studies do not take into account the pedestrian's ability to select the exit route in their models. To resolve these issues, we develop a CA model incorporating a probabilistic neural network for determining the decision-making ability of the pedestrians, and simulate an exit-selection phenomenon in the simulation. Intelligent exit-selection behavior is observed in our model. From the simulation results, it is observed that occupants tend to select the exit closest to them when the density is low, but if the density is high they will go to an alternative exit so as to avoid a long wait. This reflects the fact that occupants may not fully utilize multiple exits during evacuation. The improvement in our proposed model is valuable for further study and for upgrading the safety aspects of building designs.
[1] Song W G, Xu X, Wang B H and Ni S J 2006 Physica A 363 492
[2] Schadschneider A, Kirchner A and Nishinari K 2002 5th Proc. Int. Conf. on Cellular Automata for Research and Industry 239
[3] Kirchner A, Nishinari K and Schadschneider A 2003 Phys. Rev. E 74 036102
[4] Varas A, Cornejo M D, Mainemer D, Toledo B, Rogan J, Munoz V and Valdivia J A 2007 Physica A 382 631
[5] Fang Z M, Song W G, Zhang J and Wu H 2010 Physica A 389 815
[6] Peng Y C and Chou C I 2011 Comput. Phys. Comm. 182 205
[7] Ishii H and Morishita S 2010 Lecture Notes in Computer Science 6350 465
[8] Sarmady S, Haron F, Talib A Z 2011 Sim. Modeling Pract. Theory 19 969
[9] Alizadeh R 2011 Safety Sci. 49 315
[10] Guo R Y, Huang H J, Wong S C 2011 Trans. Research B 45 490
[11] Huang H J, Guo R Y 2008 Phys. Rev. E 78 021131
[12] Guo R Y, Huang H J 2010 Chin. Phys. B 19 030501
[13] Guo R Y, Huang H J 2011 J. Stat. Mech.: Theory and Experiment 4 P04018
[14] Specht D F 1990 IEEE Trans. Neural Networks 1 111
[15] Zarita Z and Lim E A 2010 Eur. J. Sci. Res. 42 522
[16] Muniz A M S, Liu H, Lyons K E, Pahwa R, Liu W, Nobre F F and Nadal J 2010 J. Biomechan. 43 720
[17] Mckenzie J S, Jurado J M and Pablos F 2010 Food Chem. 123 859
2012, Vol. 29 
