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:3003\, Level 3
DTSTART;TZID=America/Los_Angeles:20250623T161500
DTEND;TZID=America/Los_Angeles:20250623T163000
UID:dac_DAC 2025_sess122_RESEARCH1570@linklings.com
SUMMARY:SDISC: A Spike-Driven Human-Machine Interface with In-Situ Computi
 ng for Real-Time Low-Power Interaction
DESCRIPTION:Fangduo Zhu, Jingyi Chen, Jingsong Zhang, Xumeng Zhang, Siyuan
  Ouyang, Chenyang Li, and Hao Jiang (Fudan University); Xiaonan Yang (Zhen
 gzhou University); and Qi Liu (Fudan University)\n\nFeature extraction and
  classification of bio-signals are crucial in human-machine interface (HMI
 ), yet suffer from high delay and limited energy efficiency using conventi
 onal hardware. To mitigate this challenge, we propose an SDISC architectur
 e, a neuromorphic HMI with the innovation from signal encoding, computing-
 in-memory (CIM) hardware, to algorithm-hardware co-optimization. The follo
 wing strategies are implemented: (1) A spike-driven feature extractor, ach
 ieving >10× sparser dataflow than frame-based method; (2) In-situ computin
 g based on resistive random-access memory (RRAM), enabling energy-efficien
 t (4.09 TOPS/W) spiking neural network (SNN) classifier; (3) A Spike-Activ
 ity-Distillation algorithm and an Aid-Loser-Only recovery scheme alleviate
  the non-ideality of RRAM devices, ensuring SDISC maintains high accuracy 
 (∼98.0%) in long time inference (>15 days). We further develop an end-to-e
 nd SDISC system for real-time EMG-based robot control, achieving a low lat
 ency (34 μs) and low power (39.72 μW/sample) interaction on edge.\n\nTopic
 s: Design\n\nTracks: DES3: Emerging Models of ComputatioN\n\nSession Chair
 s: Cheng Wang (Iowa State University) and Jun Shiomi (The University of Os
 aka)\n\n
END:VEVENT
END:VCALENDAR