Adaptive Integration and Optimization of Automated and Neural Processing SystemsEstablishing Neural and Behavioral Benchmarks of Optimized Performance

Report No. ARL-TR-6055
Authors: Laurie Gibson, Jon Touryan, Anthony Ries, Kaleb McDowell, Hubert Cecotti, and Barry Giesbrecht
Date/Pages: July 2012; 60 pages
Abstract: Technical advances intended to improve situational awareness by providing more information about the tactical environment place high demands on the Soldier's limited-capacity cognitive and neural systems. Information display technologies have been developed that filter information to prevent performance failures due to information overload. However, these technologies are typically rigid with respect to changes in the operator's physical and cognitive state. Thus, a further objective of the project described in this report is to develop an adaptive framework that adjusts filtering algorithms to optimize human performance in a variety of operational contexts. The work adopts a unique approach that integrates measures of behavior, brain activity, and physiology with automated information processing and display algorithms. It leverages basic science research conducted at the Institute for Collaborative Biotechnologies (ICB) that uses machine learning algorithms to detect performance failures during difficult attentional tasks based on brain activity, work done at Science Applications International Corporation (SAIC) using pattern classification algorithms to detect threats based on brain activity, and work done at the U.S. Army Research Laboratory/Human Research and Engineering Directorate (ARL/HRED) that is aimed at understanding the cognitive constraints on performance in crew stations.
Distribution: Approved for public release
  Download Report ( 2.719 MBytes )
If you are visually impaired or need a physical copy of this report, please visit and contact DTIC.

Last Update / Reviewed: July 1, 2012