FUZZY EXPERT SYSTEMS AND GIS FOR CHOLERA HEALTH RISK PREDICTION IN SOUTHERN AFRICA Authors

The South African Council for Scientific and Industrial Research (CSIR) is investigating technologies to predict health risk in line with national priorities. Cholera cases are commonly reported in the region, despite the funnelling of extensive resources into ameliorating the problem. It is possible that this results from a lack of foresight as to the likely outbreak locations and times. CSIR has been designing an early warning GIS prototype tool using ArcGIS and Erdas Imagine, aimed at identifying favourable pre-conditions for cholera outbreaks. The model behind the tool is driven by boolean algebra and fuzzy logic approaches that interrogate data patterns of spatial layer attributes. These attribute values determine the kind of algorithm to utilise and to directly interpret the risks. This tool relies on the capture of expert knowledge and historic data that integrates climatic and biophysical parameters with socio-economic parameters to produce a fuzzy surface of cholera outbreak risk potential.