Spatio-Temporal Point Pattern Analysis Using Genetic Algorithms

The effectiveness of emergency service systems is measured in terms of their ability to deploy units and personnel in a timely, and efficient manner upon an event’s occurrence. A typical methodology to deal with such a task is through the application of an appropriate location - allocation model. In such a case, however, the spatial distribution of demand although stochastic in nature and layout, when aggregated to a specific spatial reference unit, appears to be spatially structured or semi – structured. Aiming to exploit the above incentive, the spatial tracing and analysis of emergency incidents is achieved through the utilisation of Artificial Intelligence. More specifically, in the proposed approach, each location problem is dealt with at two interacting levels. Firstly, spatio-temporal point pattern of demand is analysed over time by a new genetic algorithm. The proposed genetic algorithm interrelates sequential events formulating moving objects and as a result, every demand point pattern is correlated both to previous and following events. Secondly, the approach provides the ability to predict, by means of an artificial neural network, how the pattern of demand will evolve and thus the location of supplying centres and/or vehicles can be optimally defined. The proposed neural network is also optimised through genetic algorithms. The approach is applied to Athens Metropolitan Area and the data come from Fire Department’s records for the years 2003-2004.