BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.riscv-europe.org//eu-summit-2026//talk//QEAHWX
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-QEAHWX@cfp.riscv-europe.org
DTSTART;TZID=CET:20260610T103000
DTEND;TZID=CET:20260610T110000
DESCRIPTION:This live demonstration showcases our custom surface electromyo
 graphy (sEMG) armband\, enabling 16-channel monopolar acquisition. It feat
 ures the RISC-V-based GAPWatch platform\, which integrates two ADS1298 ADC
 s\, an ESP32 radio module\, GAP9 (a programmable multi-core RISC-V process
 or)\, and an STM32U5 microcontroller acting as a system gateway.\nThe armb
 and is used to control a cursor in a 2D reach-and-hold task through EMG ge
 stures. The system runs a context-informed incremental learning pipeline d
 irectly on GAP9. EMG signals are acquired\, filtered\, and fed to a tiny C
 NN\, which predicts one of four gestures mapped to cursor directions (e.g.
 \, index finger contraction for LEFT\, middle finger contraction for UP\, 
 etc.). Predictions are transmitted via BLE to a computer running the GUI w
 ith the task. The GUI updates the cursor position and derives a pseudolabe
 l from the task context. If the predicted movement brings the cursor close
 r to the target\, the pseudolabel acts as a reward signal\; otherwise\, it
  provides corrective feedback. This pseudolabel is returned to the device\
 , where the CNN is updated via stochastic gradient descent (SGD). A replay
  mechanism is also implemented to stabilize training. EMG processing\, inf
 erence\, and SGD are all executed on GAP9.\nDuring the demo\, a participan
 t will perform the task starting from an untrained model. As the task prog
 resses\, attendees can observe real-time on-device adaptation. The demonst
 ration highlights how parallel RISC-V processing enables fully embedded\, 
 adaptive HMIs without reliance on the cloud or external PCs for recalibrat
 ion.
DTSTAMP:20260522T163258Z
LOCATION:Devzone
SUMMARY:On-Device Context-Informed Incremental Learning for Myoelectric Con
 trol on RISC-V-based Wearable Platform - Mattia Orlandi\, Margherita Rossi
URL:https://cfp.riscv-europe.org/eu-summit-2026/talk/QEAHWX/
END:VEVENT
END:VCALENDAR