Data & Analytics Tools for Agile Training & Readiness Assessment

The return of American warfighters to their bases and their garrisons presents an opportunity to bolster scarce training resources and expertise with new assessment technologies. America made a similar investment in the 20th century as it shifted its intelligence budget to supplement human intelligence gathering with technologies that unobtrusively captured data concerning the activities of foreign powers. Here, we present a unifying vision of several emerging technologies that can improve military training. Following a human systems engineering approach, we first define the functional requirements of future training and readiness assessment systems, describe the architectural requirements for providing those functions, and then describe systems for the Marine Corps and Air Force that instantiate this architecture. Next we focus on two fundamental and new components of this emerging architecture: sensors that capture human performance data unobtrusively, and big data analytics that make sensor data meaningful and actionable. Finally, we identify several scientific and technical challenges encountered during the initial implementation and planned testing of these architectures.

[1]  John R. Boyd,et al.  The Essence of Winning and Losing , 2012 .

[2]  Alex Pentland,et al.  To Signal Is Human , 2010 .

[3]  Chris Arney.  Social Physics: How Good Ideas Spread - the Lessons from a New Science , 2014 .

[4]  Dylan D. Schmorrow,et al.  Proceedings of the 5th International Conference on Foundations of Augmented Cognition. Neuroergonomics and Operational Neuroscience: Held as Part of HCI International 2009 , 2009 .

[5]  Dana E. Sims,et al.  Is there a “Big Five” in Teamwork? , 2005 .

[6]  Denise Nicholson,et al.  A virtual environment for modeling and testing sensemaking with multisensor information , 2014, Defense + Security Symposium.

[7]  Emily S. Patterson,et al.  Identifying Emergent Thought Leaders , 2014, SBP.

[8]  Russell M. Taylor,et al.  VRPN: a device-independent, network-transparent VR peripheral system , 2001, VRST '01.

[9]  Jared Freeman,et al.  Learning and Detecting Patterns in Multi-Attributed Network Data , 2012, AAAI Fall Symposium: Social Networks and Social Contagion.

[10]  Randy Jensen,et al.  Automatic Causal Explanation Analysis for Combined Arms Training AAR , 2005 .

[11]  Gwendolyn E. Campbell,et al.  Reentrant Processing in Intuitive Perception , 2010, PloS one.

[12]  Brian J. Taylor,et al.  Automatic identification of quasi-experimental designs for discovering causal knowledge , 2008, KDD.

[13]  S. Hart,et al.  Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research , 1988 .

[14]  G. King,et al.  What to Do about Missing Values in Time‐Series Cross‐Section Data , 2010 .

[15]  Emily E. Wiese,et al.  Enhancing Distributed Debriefs with Performance Measurement Objects , 2006 .

[16]  Jared Freeman,et al.  Higher Automated Learning through Principal Component Analysis and Markov Models , 2013, AIED.

[17]  Kurt VanLehn,et al.  The Behavior of Tutoring Systems , 2006, Int. J. Artif. Intell. Educ..

[18]  Jean MacMillan,et al.  Measuring Team Performance in Complex and Dynamic Military Environments: The SPOTLITE Method , 2013 .