BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251016T135133Z
LOCATION:Grand Hall L
DTSTART;TZID=America/Chicago:20251017T082000
DTEND;TZID=America/Chicago:20251017T084000
UID:HFESAM_ASPIRE 2025_sess230_LECT468@linklings.com
SUMMARY:Generalizing Predictive Models of Situation Awareness to Unseen Pa
 rticipants
DESCRIPTION:Kieran Smith (University of Colorado Boulder, Draper); Torin C
 lark (University of Colorado Boulder); and Tristan Endsley (Draper)\n\nMon
 itoring pilot performance is critical in commercial aviation, where mistak
 es can lead to high consequences. Situation awareness (SA) is particularly
  important because it is strongly correlated with piloting performance and
  could be used to intervene and prevent disaster. This work demonstrates t
 he challenge of predicting SA for pilots that are excluded from model-trai
 ning and evaluates how much operator information is required for state-of-
 the-art predictive performance. Written informed consent was collected fro
 m 31 participants in a protocol approved by the Institutional Review Board
  for the University of Colorado Boulder. Participants performed a complex 
 task and responded to objective SA assessments. Their scores were predicte
 d from cognitive, physiological, and behavioral measures captured during t
 he task. ANOVA results (F(30,299) = 17, p << 0.05) suggest that inter-indi
 vidual differences account for much of the variance in SA scores. When mod
 els are evaluated on unseen participants, errors increase. Standardized me
 an absolute errors grow from 0.74, 0.76, and 0.69 for perception, comprehe
 nsion, and projection scores respectively to 0.98, 1.04, and 0.93 when par
 ticipants were left out from training entirely, but improve when incorpora
 ting operator background information. SA monitoring remains dependent on a
 ccess to individual training data, but operator background information can
  mitigate this limitation.\n\nTrack: Human Performance Modeling\n\nSession
  Chairs: Richard Steinberg (Northrop Grumman Corporation) and Lesong Jia (
 University of Pittsburgh)\n\n
END:VEVENT
END:VCALENDAR