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:20251016T135137Z
LOCATION:Riverside East
DTSTART;TZID=America/Chicago:20251014T173000
DTEND;TZID=America/Chicago:20251014T183000
UID:HFESAM_ASPIRE 2025_sess131_POST218@linklings.com
SUMMARY:Predicting Cognitive Workload from Pupillometry: A Machine Learnin
 g Approach
DESCRIPTION:Sachithra Karunathilake, Nurul Ahad Choudhury, Pratima Saravan
 an, and Akash Deep (Oklahoma State University)\n\nMonitoring and controlli
 ng cognitive workload are critical for maintaining smooth performance in c
 omplex visuospatial tasks requiring high mental effort. This study utilize
 s pupillometry with machine learning models to predict cognitive workload 
 for a Lego building task. Twenty university students were recruited to par
 ticipate in the complex Lego building task while pupil diameter data were 
 collected using an eye tracker. After the data were preprocessed and norma
 lized, the K-means clustering method classified baseline-corrected pupil d
 ata into moderate and high workload levels. Random forest, XGBoost, and Lo
 ng Short-Term Memory (LSTM) were trained to predict the workload levels. R
 esults showed moderate prediction accuracy, with LSTM providing better acc
 uracy than the other models. These findings demonstrate the usability of p
 upillometric measurements and machine learning to predict cognitive worklo
 ad and benefit professionals in various domains with complex visuospatial 
 tasks.\n\n
END:VEVENT
END:VCALENDAR