A Bayesian Network Threat Model for Anti-abalone Poaching Operations

Abstract

The work will be part of a post-graduate student research project. The work will consist of the following work packages.User requirement statement and system requirement specifications. There will be interaction with the end users and domain experts to understand the problem. This interaction is required to determine the structure and parameters of the threat model. Literature review and assessment of the current state of the art for the problem.The current body of knowledge will be evaluated and assessed to determine how the proposed solution can be compared to methods in the literature. This is necessary to determine how the proposed method will compare to existing methods in terms of performance. Also, the literature will inform which methods should be used to evaluate and validate the threat model. Model structure and parameter design using domain expert knowledge and historical data.Domain experts will again be consulted to parameterize the threat model, after initial design which will take into account the user requirements. Historical data will be incorporated to inform the parameters of the model where relevant. Model validation and verificationThe model will be validated using training and test data sets and using n-fold cross validation methods. Further evaluations will be performed using Monte Carlo simulations where relevant. Dissemination of resultsResults will be disseminated by writing a report and by submitting an article to a journal

Document Details

Document Type
DoD Grant Award
Publication Date
Feb 03, 2017
Source ID
N62909151N080

Entities

People

  • Pieter De Villkiers

Organizations

  • Office of Naval Research
  • United States Navy
  • University of Pretoria

Tags

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Library and Information Science
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference