Abstract:
This work presents a design framework based on a centralized scalable
architecture for effective simulated aerial threat perception. In this
framework Data Mining and pattern classification techniques are
incorporated. This work focuses on effective prediction by relying on the
knowledge base and finding patterns for building the decision trees. This
framework is flexibly designed to seamlessly integrate with other
applications.
The results show the effectiveness of selected algorithms and suggest that
the more the parameters are incorporated for the decision making for aerial
threats; the better is our confidence level on the results. To delve into
accurate target prediction we have to make decisions on multiple factors.
Multiple techniques used together help finding the accurate threat
classification and result in better confidence on our results.
