Predicting the Risk of Freshwater Disease Emergence in UK

Authors: Silva, E.S., Hassani, H., Andreou, D. and Gozlan, R.

Conference: 6th Annual BU Postgraduate Conference

Dates: 22-23 January 2014

Abstract:

Freshwater disease emergence continues to have increasingly negative impacts on the earth’s eco-systems. We developed a new model based on Support Vector Machines (SVM) for predicting the risk of freshwater disease emergence in the United Kingdom (UK). Following a rigorous training process and simulations, the proposed SVM model was validated and reported high accuracy rates for predicting the risk of freshwater disease emergence in UK. Our findings suggest that the disease monitoring strategy employed in the UK could be successful at preventing disease emergence in certain parts of UK, as areas in which there is high fish movement were not correlated with high disease emergence (which was to be expected from the literature). We further test our model’s predictions with actual disease emergence data using chi-square tests and test of mutual information. These results enable us to pinpoint the Environmental Agencies to cities which require further attention and resource allocations to successfully curb future freshwater disease emergence.

Source: Manual

Preferred by: Emmanuel Sirimal Silva

The data on this page was last updated at 16:03 on May 5, 2021.