Open Call for Innovative Defense-Related Dual-Purpose Technologies/Solutions with a Clear Air Force Stakeholder Need

AFWERX/VMX-1 has a national defense-related mission need to decrease time-to-production for S-Shops multi-flight-platform data and information flow. Vennli’s platform will integrate heterogeneous metadata from a large set of source systems. Using a combination of machine learning and Network Information Theory, the system will identify inefficient ‘hotspots’ in the Operational, Test and Evaluation (OT&E) mission and VMX-1 Operations data and information flow. Through a robust API Gateway, the solution will enable real time updates by continuously monitoring system utilization trends & anomalies (hotspots) without transmitting sensitive information. The solution will include an interactive analytics dashboard and provide tactical recommendations for improving operational efficiency. Leveraging the many benefits that Artificial Intelligence (AI) and Machine Learning (ML) offer can decrease this time-to-production. Like any supply chain, there is a complex network of inter-dependencies between the sources and systems involved that evolve over time. The goal of our Phase II SBIR project is to demonstrate the applicability of machine learning and network information theory for identifying bottlenecks in the intelligence production process by leveraging the structure (inter-dependence) and function (transactional metadata) of these intelligence sources.