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:20251016T135126Z
LOCATION:Grand Hall L
DTSTART;TZID=America/Chicago:20251016T095000
DTEND;TZID=America/Chicago:20251016T101000
UID:HFESAM_ASPIRE 2025_sess231_LECT203@linklings.com
SUMMARY:Human Performance Modeling with Natural Language (HPM-NL) for Uppe
 r-limb Prostheses: Generative pre-trained transformer (GPT)-based rapid HP
 M under low hallucination
DESCRIPTION:Junho Park, Reyansh BADHWAR, Parshva Dave, and Zehaan Walji (U
 niversity of Calgary)\n\nAccurately predicting how people use prosthetic h
 ands is key to improving their design and usability. Traditional human per
 formance modeling (HPM) methods—like GOMS, ACT-R, or QN-MHP—are effective 
 but often difficult to use, requiring expert knowledge and extensive time.
  We present HPM-NL, a novel, free tool that uses GPT-based natural languag
 e processing to quickly estimate task completion time and workload for upp
 er-limb prosthesis tasks. Unlike conventional approaches, HPM-NL relies on
  empirical data from 30+ years of research, minimizes hallucination risk, 
 and combines strengths from multiple HPM frameworks. It generates results 
 in under a minute from simple text inputs, making it accessible to both cl
 inicians and engineers. A validation study with graduate students compared
  predictions from HPM-NL to both Cogulator (a CPM-GOMS tool) and real huma
 n-subject data. Results showed that HPM-NL predictions closely matched act
 ual data across tasks such as clothespin relocation and target acquisition
 , while Cogulator showed more discrepancies. HPM-NL also provides step-by-
 step breakdowns and visual feedback for better interpretability. This appr
 oach reduces modeling burden and opens the door for more rapid and scalabl
 e usability testing in prosthetic design.\n\nTrack: Human Performance Mode
 ling\n\nSession Chairs: Ji-Eun Kim (University of Washington) and Yutong Z
 hang (University of Pittsburgh)\n\n
END:VEVENT
END:VCALENDAR