Search

Fuzzy geographically weighted clustering has been proposed as an approach for improving fuzzy c-means algorithm when applied to geodemographic analysis. This clustering method allows a spatial entity to belong to more than one cluster with varying degrees, namely, membership values. Although fuzzy geographically weighted clustering attempts to create geographically aware clusters, it partially fails to trace spatial dependence and heterogeneity because, as a global metric, the membership values are calculated across the entire set of spatial entities. Here we introduce the first local version of fuzzy geographically weighted clustering, 'local fuzzy geographically weighted clustering.' In local fuzzy geographically weighted clustering, the membership values of a spatial entity are updated only according to the membership values of the spatial entities within its neighborhood and not across the entire set of entities, as originally proposed by the global metric. Additionally, we apply particle swarm optimization meta-heuristic to overcome the random initialization problem regarding the fuzzy c-means algorithm. To evaluate our method we compare local fuzzy geographically weighted clustering to global fuzzy geographically weighted clustering using a cancer incident benchmark dataset for Manhattan, New York. The results show that local fuzzy geographically weighted clustering outperforms the global version in all experimental settings. [ABSTRACT FROM AUTHOR]

Any analysis of health service problems facing the world today must consider that these problems exist in a geographic context. This fact has led to an increased need for accurate and current information to support emergency planning and decision making. In this article we combine geographic information systems (GIS) and neural networks for performing health emergency assessments and generating hazard maps that show areas that are potentially at high risk for emergencies. Through the use of neural networks we predict the location of future emergency events. On these events we use a kernel density estimator to create maps of areas that have a high risk for future emergencies. As a result, emergency services will know in advance where there is a high possibility of an emergency event occurring and can formulate a response, thus improving incident management and health planning. For example, the service can locate ambulances in places near the expected emergency cases, minimizing response time. The approach was tested in stroke-event analysis in the city of Athens, Greece. [ABSTRACT FROM PUBLISHER]