Data Science Driven Aircrew Performance Measurement and Proficiency System
Navy SBIR FY2018.1

Sol No.: Navy SBIR FY2018.1
Topic No.: N181-026
Topic Title: Data Science Driven Aircrew Performance Measurement and Proficiency System
Proposal No.: N181-026-0453
520 S. Main Street
Suite 2448
Akron, Ohio 44311
Contact: David Sheets
Phone: (330) 374-7737
Web Site:
Abstract: Using integrated teams of Operational Analysts experienced with Naval aircrew training and Software Engineers experienced in developing dynamic analysis and reporting tools for aviation, a pragmatic and scalable approach to aircrew performance assessment and proficiency is proposed. Initial techniques to incorporate data fusion of disparate data sources are summarized from past experience and existing software solutions. These techniques can be applied to aircrew performance assessment to reduce instructor work-load while also increasing the speed and accuracy of assessment. A process outline to decompose training scenarios in a manner that supports automation, human-in-the-loop techniques, and advanced data science is presented for further refinement during the research. The methodologies proposed for research all include the ability to scale across multiple platforms, training devices, training missions, and aircrew configurations through innovative application of modern programming paradigms. The end result is a design realizing this innovation in a user-oriented toolset supporting actionable feedback in a performance assessment and proficiency system.
Benefits: The preparation of tactically and technically proficient aircrew capable of conducting Major Combatant Operations (MCO) in support of the United States National Command Authority (NCA) is the end-sate objective of the Naval Air Force. Many high-end efficiencies are demonstrated by the NAE solution currently in place, however, the low-end tasks of collecting data for Individual Aircrew Performance Assessment and Squadron/Detachment Performance Assessment to support Immediate Superiors in Command (ISIC) validation and completion of CB T&R training requirements is not as refined. Few, if any, commercially-available debriefing system vendors have made any significant inroads into collecting, storing and presenting information via commonly-accepted applied data science techniques applicable to the desired end-state solution. With aircraft and weapon systems increasing in complexity, limited flight hour funding, range and airspace constraints, increased operational tempo, aircrew and airframe shortages, and a challenging data collection landscape all conspiring to make the problem of performance assessment more difficult, BGI will employ proven and effective data science methodologies that feed accurate and objective data into the NAE process for both Individual Aircrew Performance Assessment and Squadron/Detachment Performance Assessment. With automated collection techniques operating on correlated data, an instructor is supported with indicators of performance supported by objective evidence.