One of the most relevant problems for public places flooded with crowds of people such as airports, railway stations, and stadiums, is the detection of different biological, chemical or radioactive contaminations and threats related to individuals who are carrying drugs or explosives. To detect such threats in advance the place has to be equipped with a special monitoring infrastructure that includes a network of detectors covering the entire vicinity.
Having a real picture of pedestrian flows through the place makes it possible to optimize the placement of detectors and count to minimize the cost of the monitoring infrastructure, while satisfying time and precision requirements for detecting threats in advance. This task is solved with the help of a multi population genetic algorithm based on a pedestrian mobility model. This model takes into account motivations, age structure, social stratification of visitors and the specific schedule of the place itself.
As an illustration, this video gives an example of optimal detector network construction for the international terminal of Pulkovo airport (Saint-Petersburg). The network is designed by modelling passenger activities inside the terminal based on a real flight schedule.
Towards a Performance-realism Compromise in the Development of the Pedestrian Navigation Model // Procedia Computer Science. — 2015. — Vol. 51. — pp. 2799-2803.
The Multi-Agent Simulation-Based Framework for Optimization of Detectors Layout in Public Crowded Places // Procedia Computer Science. — 2015. — Vol. 51., Issue 1. — pp. 522-531.
Optimization-based Calibration for Micro-level Agent-based Simulation of Pedestrian Behavior in Public Spaces // Procedia Computer Science. — 2015. — Vol. 66. — pp. 372-381.