Meshing Capability and Threat-based Science and Technology (S&T) Resource Allocation
Systems Engineering and Systems Management Transformation
Report Number: SERC-2019-TR-010
Publication Date: 2019-06-30
Project: Meshing Capability and Threat-based Science and Technology (S&T) Resource Allocation
Dr. Carlo Lipizzi
Dr. Dinesh Verma
Dr. George Korfiatis
The purpose of this research is to provide a computational model to support the planning cycle that will inject relevant threat-based intelligence and operational scenarios into the more traditional capabilities-based model. This approach will better inform the technical communities charged with developing future weapons systems and has been piloted in late 2016 at the U.S. CCDCAC in the armament-systems domain.
Using a data or text-driven approach, this research focused on a proxy-domain “Artificial Intelligence (AI)/ Machine Learning (ML) in a connected environment”. In specific, the private security industry marketplace was used as an example for this project. In the U.S., the private security industry is chosen because it is a technology-driven marketplace that has close semantic proximity to the needs at the U.S. CCDCAC. According to the Security Industry Association, cybersecurity impact on physical security, internet of things and the big data effect, cloud computing, workforce development, and AI are the top 5 forecasted security megatrends in 2019.
In this research, two core systems, Technology Monitoring and Risk Panel systems, were designed and developed as agile, iterative prototypes with modular components (refer to Section 5). The modular components are vital building blocks that were designed to be used as components for the overall system and the data collection process for the proxy domain (refer to Section 4). Most of the components are developed separately for better reusability.
The objectives of the computational model are as follows:
- Replicate the aforementioned process developed at the U.S. CCDCAC in 2016 to validate this notional computational architecture
- Enhance the visualization and analytic capability to allow rapid, high fidelity decision making
- Introduce additional parameters and variables to refine the decision-making framework further. Real-world scenarios will be modeled to project evolving threats, doctrine, partner force interoperability, and other operational environmental conditions (political, military, socio-economic, information, infrastructure, physical environment)
- Deliver the results with an agile approach, developing prototypes/proofs of concepts with increasing capabilities, using a partially automatic learning approach.