BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.riscv-europe.org//eu-summit-2026//speaker//UZZQXC
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-eu-summit-2026-LMUL9F@cfp.riscv-europe.org
DTSTART;TZID=CET:20260610T133000
DTEND;TZID=CET:20260610T140000
DESCRIPTION:This live demonstration showcases GAPses\, an ultra-low-power s
 mart-glasses platform based on an ultra-low power RISC-V multicore process
 or (GAP9)\, enabling always-on\, real-time\, energy-efficient edge process
 ing of electrooculography (EOG) and electroencephalography. GAPses perform
 s on-device signal processing and machine-learning inference\, converting 
 raw biosignals into events without cloud compute or continuous high-bandwi
 dth streaming\, enabling energy-scalable and privacy-preserving operation.
  In the demo\, dry electrodes integrated into the glasses frame capture ho
 rizontal/vertical EOG\, and an on-device lightweight CNN running on GAP9 c
 lassifies saccadic eye movements from these EOG signals in real time. The 
 resulting eye-movement events are transmitted via BLE to a laptop running 
 a visualization application\, which displays the CNN outputs alongside fil
 tered EOG traces. The classification stream drives multiple interactive sc
 enarios\, including grid control\, a Tetris game\, and live class-probabil
 ity visualization. During the demo session\, we will run the complete pipe
 line live: a team member will wear the glasses and perform a sequence of s
 accades to trigger on-device CNN inference. The GUI updates in real time w
 ith predicted classes and EOG traces\, allowing attendees to observe laten
 cy\, robustness\, and privacy benefits of RISC-V-based embedded biosignal 
 inference in a practical wearable form factor. Overall\, the demo highligh
 ts GAPses as an open\, fully wearable research platform and illustrates ho
 w parallel RISC-V compute enables always-on neural interfaces by executing
  sensing\, inference\, and event-level decisions locally without cloud dep
 endence or continuous high-bandwidth streaming.
DTSTAMP:20260522T162455Z
LOCATION:Devzone
SUMMARY:RISC-V Edge Inference for Real-Time Eye-Movement Control on GAPses 
 Smart Glasses - Sebastian Frey\, Andrea Helga Bernardi
URL:https://cfp.riscv-europe.org/eu-summit-2026/talk/LMUL9F/
END:VEVENT
END:VCALENDAR