Cellular Automata Based Evacuation Process Triggered by Indoors Wi-Fi and GPS Established Detection

This study presents the principles of an application that is designed to facilitate customized evacuation from indoor spaces. The proposed approach combines in-doors detection using existing wireless networks based on trilateration technique and proper evacuation estimation based on cellular automata (CA). An efficient application has been developed that can be installed in smartphones under Android operation system and technically fulfills the scopes of the aforementioned evacuation model. More specifically, it offers the user the option to view her/his location at any time and to find the closest possible route to an exit in case of an emergency. The efficiency of the application to provide reliable guidance towards an exit is also evaluated. Preliminary results are reasonably encouraging; provided that the application is properly customized then a reliable, real-time evacuation guidance could be realized.

[1]  Theofilos Chrysikos,et al.  Attenuation over distance for indoor propagation topologies at 2.4 GHz , 2011, 2011 IEEE Symposium on Computers and Communications (ISCC).

[2]  Georgios Ch. Sirakoulis,et al.  A Cellular Automaton Model for Crowd Evacuation and Its Auto-Defined Obstacle Avoidance Attribute , 2010, ACRI.

[3]  Stefania Bandini,et al.  Route choice in pedestrian simulation: Design and evaluation of a model based on empirical observations , 2016, Intelligenza Artificiale.

[4]  Kevin Curran,et al.  HABITS: a Bayesian filter approach to indoor tracking and location , 2011, Int. J. Bio Inspired Comput..

[5]  Kevin Curran,et al.  An evaluation of indoor location determination technologies , 2011, J. Locat. Based Serv..

[6]  Georgios Ch. Sirakoulis,et al.  Real Data Evaluation of a Crowd Supervising System for Stadium Evacuation and Its Hardware Implementation , 2016, IEEE Systems Journal.

[7]  Santiago Mazuelas,et al.  Robust Indoor Positioning Provided by Real-Time RSSI Values in Unmodified WLAN Networks , 2009, IEEE Journal of Selected Topics in Signal Processing.

[8]  Jaroslaw Was,et al.  Cellular Automata as the basis of effective and realistic agent-based models of crowd behavior , 2016, The Journal of Supercomputing.

[9]  Sascha Ossowski,et al.  A distributed architecture for real-time evacuation guidance in large smart buildings , 2017, Comput. Sci. Inf. Syst..

[10]  Tomislav Jagušt,et al.  Enhanced Weighted Centroid Localization Algorithm for Indoor Environments , 2014 .

[11]  Georgios Ch. Sirakoulis,et al.  An Anticipative Crowd Management System Preventing Clogging in Exits During Pedestrian Evacuation Processes , 2011, IEEE Systems Journal.

[12]  Michail-Antisthenis I. Tsompanas,et al.  Evolving Transport Networks With Cellular Automata Models Inspired by Slime Mould , 2015, IEEE Transactions on Cybernetics.

[13]  Gi-Wan Yoon,et al.  Building a Practical Wi-Fi-Based Indoor Navigation System , 2014, IEEE Pervasive Computing.

[14]  Theofilos Chrysikos,et al.  Empirical calculation of shadowing deviation for complex indoor propagation topologies at 2.4 GHz , 2009, 2009 International Conference on Ultra Modern Telecommunications & Workshops.

[15]  John Krumm,et al.  Accuracy characterization for metropolitan-scale Wi-Fi localization , 2005, MobiSys '05.

[16]  Stefania Bandini,et al.  Cellular automata: From a theoretical parallel computational model to its application to complex systems , 2001, Parallel Comput..

[17]  Naser El-Sheimy,et al.  Smartphone-based WiFi access point localisation and propagation parameter estimation using crowdsourcing , 2015 .