Gavin cholera risk prediction

Uploaded from authorPOINT
Views:
 
     
 

Presentation Description

No description available.

Comments

Presentation Transcript

Fuzzy Expert Systems and GIS for Cholera Health Risk Prediction in Southern Africa : 

Fuzzy Expert Systems and GIS for Cholera Health Risk Prediction in Southern Africa Gavin Fleming, Marna van der Merwe, Graeme McFerren, Kerry Murphy CSIR, South Africa

Vibrio cholerae: 

Vibrio cholerae Untreated: death within 24h from loss of fluid Transmission: ingest contaminated material Treatment: fluid replacement and antibiotics Origins in the Orient Now endemic in many places

Disaster: Cholera epidemics: 

Disaster: Cholera epidemics Frequent South Africa 2000-2002 andgt;115000 cases 260 deaths

Prevention and mitigation: 

Prevention and mitigation Interventions Water supply and sanitation Poverty reduction Education Treatment New Disaster Management Act Department of Health Department of Water Affairs

The problem…: 

The problem… Response is not well directed Scarce resources are wasted History of response, not mitigation Often too late Risk assessment and forecasting

Premise: 

Premise Integrate understanding of cholera biology human factors Improve accuracy and reduce uncertainly of predictions

The complex nature of cholera: 

The complex nature of cholera

Hierarchical approach: 

Hierarchical approach

Slide9: 


Simulation model - Stella: 

Simulation model - Stella

Expert systems: 

Expert systems Bayesian networks Facilitated expert workshop Erdas Imagine Knowledge Engineer Codify final set of rules from Bayesian networks and simulation model

Slide12: 


GIS and Fuzzy LogicArcInfo: raster, AML: 

GIS and Fuzzy Logic ArcInfo: raster, AML

Model variables: 

Model variables

Slide15: 


Conclusions: 

Conclusions An integrative approach is effective for modelling complex problems Non-linear simulation modelling Expert systems AI integration (fuzzy logic) We have established a framework and working model

Taking it further: 

Taking it further Funding to collect missing data Several proposals submitted Develop predictive capability – now mainly risk assessment Improve algal bloom (cholera) prediction Consider other factors Red tide events in Mozambique channel La niña, el nio Develop and integrate social model

Slide18: