BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260402T024533Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20250623T180000
DTEND;TZID=America/Los_Angeles:20250623T190000
UID:dac_DAC 2025_sess262_RESEARCH981@linklings.com
SUMMARY:Towards Accurate, Real-Time, and Energy-Efficient Attention Monito
 ring
DESCRIPTION:Anice Jahanjoo (Technische Universität Wien) and Vimala Bauer,
  Soheil Khooyooz, Mostafa Haghi, and Nima TaheriNejad (Heidelberg Universi
 ty)\n\nttention monitoring is crucial in various fields,\nespecially those
  involving prolonged periods of passive\nobservation. Electroencephalograp
 hy (EEG) offers a cost-\neffective, portable, and non-invasive solution; h
 owever,\nthe signal's intrinsic complexity necessitate advanced\nanalysis 
 techniques. This research proposes a novel\napproach for accurate attentio
 n classification. We selected\na representative channel and applied Recurs
 ive Feature\nElimination (RFE) to identify the most discriminating\nfeatur
 es to enhance detection accuracy and minimize energy\nconsumption. On a pu
 blic dataset, our optimized XGBoost\nalgorithm achieved 98.29% and 94.25% 
 accuracy for binary\nand three-class attention classification, respectivel
 y. The\nrefined feature set reduces execution time by 9%, memory\nusage by
  38%, and energy consumption by 8% on an Intel\ni9-13900 platform. On a Ra
 spberry Pi 5 the improvements\nare 15%, 14%, and 14% respectively. By addr
 essing these\nchallenges our approach facilitates adoption of wearable\nde
 vices for attention monitoring in various settings.\nIndex Terms—EEG signa
 l, attention detection, machine\nlearning, feature engineering, wearable d
 evices.\n\nTracks: DES5: Emerging Device and Interconnect Technologies\n\n
END:VEVENT
END:VCALENDAR