An Intelligible Illustration of an Epidemic Spatio – Temporal Statistics on GIS

Abstract

Innovations in the sector of information technology have enabled the collection and processing of enormous amounts of spatial data. The goal of data mining is to determine nuggets. Spatial data mining identifies the collocation rules. Spatial data are considered from the spatial objects. The considered spatial data is preprocessed by using the data mining tool. To the preprocessed data, collocation rule is applied for detecting the frequent item sets. Disaster impacted areas were predicted by applying the collocation rule. In particular to spatial data mining, when spatial data are comparatively represented in time series, a spatio-temporal significance is concluded. In this perspective, the collocation rule that is an epitome for the spatial data acquires changes with temporal impact. Therefore, the changes that arise to the spatial knowledge are the spatio-temporal transactions. Extracting the spatio-temporal transactions and finding the various behavioral aspects of collocation is one of the considerable activities of GIS. By implementing the collocation rule with “nearby” as the predicate, disaster affected areas are identified follows the representation of the spatial data on Geographical Information Systems (GIS) by various colored pinpoints for all the quarters of a year. From that, the regions at risk zone of disaster were predicted, then the analyzed spatial data will be redirected to the health organizations for supervising campaigns. Our focus is to forecast the disaster, design the spatio-temporal trees for all the quarters of a year and to represent the spatial nuggets on GIS. Therefore, a spatio-temporal disaster management system is designed and implemented. A novel data structure for the spatio-temporal data is proposed.