Abstract
- The Department of Defense (DoD) continues to invest significant amounts of time, effort, and resources in analyzing massive amounts of data via traditional human-based approaches. Legacy methodologies may leave leadership susceptible to vulnerabilities and decisions based on incorrect, incomplete, or misleading data. Furthermore, with the widespread DoD adoption of smart devices interconnected within the Internet of Battlefield Things (IoBT), the DoD has exponentially increased its data collection capabilities. The resulting large volumes of unsorted and unfiltered data is too time-consuming and expensive for humans to process. To properly leverage big data, the DoD must implement artificial intelligence and machine learning (AI/ML) in place of traditional human analysis. This paper presents some concepts to help extrapolate patterns from data within the future knowledgebase system of systems (FKSS) to increase reliability and availability. AI engines will ultimately use machine learning algorithms to find decision-worthy data that is potentially overlooked through current manual analysis processes. Additionally, this paper provides an empirical approach to measuring the system of systems (SoS) or IoBT reliability and availability while considering DoD specific needs and limitations.