Predictive modelling for rhino anti-poaching operations

Dr Alte de Waal will present the Department of Computer Science colloquium  with a talk entitled, "Predictive modelling for rhino anti-poaching operations".

Rhino poaching in South Africa is leading to a catastrophic reduction in the rhino population. A Bayesian network causal model is proposed to model the underlying (causal) relationships that lead to rhino poaching events. The model may be used to fuse a collection of heterogeneous information sources. If a game reserve is partitioned into several geographical areas or cells, the model may perform inference for each of these cells separately, and give a relative predictive distribution of poaching events over the game reserve. Several data sources are used to construct the model. Expert knowledge is used to parameterise the model as well as data based on historical poaching events. In this presentation we discuss the outcomes of the two models and present an evaluation framework for the model.

Alta de Waal holds a PhD in Engineering Science from the North West University, South Africa. She is a senior lecturer at the Statistics Department, University of Pretoria. Alta has 16 years’ experience in the field of decision support model development. Of special focus is the development of Bayesian networks in order to model multidisciplinary scenarios. This involves the facilitation of experts from these disciplines in order to develop the qualitative and quantitative aspects of these models. Furthermore Alta also specialises in the field of text analytics and unsupervised modelling of natural language text.

Date: 
Wednesday, June 8, 2016 - 13:00
Venue: 

Computer Science Lecture Theatre 303, Upper Campus, UCT

TOP