Workload State Classification
With Automation During Simulated
Air Traffic Control
David B. Kaber and Carlene M. Perry
Edward P. Fitts Department of Industrial and Systems Engineering,
North Carolina State University, Raleigh, NC
Noa Segall
Human Simulation and Patient Safety Center,
Duke University Medical Center, Durham, NC
Mohamed A. Sheik-Nainar
Research and Development, Synaptics, Inc., Santa Clara, CA
Real-time operator workload assessment and state classification may be useful for
decisions about when and how to dynamically apply automation to information pro-
cessing functions in aviation systems. This research examined multiple cognitive
workload measures, including secondary task performance and physiological (car-
diac) measures, as inputs to a neural network for operator functional state classifica-
tion during a simulated air traffic control (ATC) task. Twenty-five participants per-
formed a low-fidelity simulation under manual control or 1 of 4 different forms of
automation. Traffic volume was either low (3 aircraft) or high (7 aircraft). Partici-
pants also performed a secondary (gauge) monitoring task. Results demonstrated sig-
nificant effects of traffic volume (workload) on aircraft clearances (p < .01) and tra-
jectory conflicts (p < .01), secondary task performance (p < .01), and subjective
ratings of task workload (p < .01). The form of ATC automation affected the number
of aircraft collisions (p < .05), secondary task performance (p < .01), and heart rate
(HR; p < .01). However, heart rate and heart rate variability measures were not sensi-
tive to the traffic manipulation. Neural network models of controller workload (de-
fined in terms of traffic volume) were developed using the secondary task perfor-
mance and simple heart rate measure as inputs. The best workload classification
accuracy using a genetic algorithm (across all forms of ATC automation) was 64%,
THE INTERNATIONAL JOURNAL OF AVIATION PSYCHOLOGY, 17(4), 371–390
Copyright © 2007, Lawrence Erlbaum Associates, Inc.
Correspondence should be sent to David B. Kaber, Edward P. Fitts Department of Industrial & Systems
Engineering, North Carolina State University, Raleigh, NC 27695–7906. E-mail: dbkaber@ncsu.edu