Spatial Influence Index Effects in the Analysis of Epidemic Data

Abstract

In the context of epidemic analysis, the aim of this paper is to present the development of a spatial influence index that considers the spatial neighborhood relation, expressed by distance and direction bands in the analysis of non-spatial attribute values in order to predict an epidemic evolution. The studied case is the evolution of aids propagation in the city of Rio de Janeiro, Southeastern of Brazil. The prediction of this epidemic data, using the spatial influence index has shown an improved performance when compared to the traditional approaches without this information. Despite some instability of the model, it is able to forecast the epidemic evolution. We conclude that aids evolution analysis should take into account object proximity and socio economic indicators to obtain useful knowledge.