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:20240626T180034Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20240626T180000
DTEND;TZID=America/Los_Angeles:20240626T190000
UID:dac_DAC 2024_sess237_RESEARCH389@linklings.com
SUMMARY:DRL-based Voltage Optimization for Multiple Droplet Routing in DMF
 Bs
DESCRIPTION:Work-in-Progress Poster\n\nTomohisa Kawakami (Ritsumeikan Univ
 ersity), Hiroki Nishikawa (Osaka University), and Hiroyuki Tomiyama and Sh
 igeru Yamashita (Ritsumeikan University)\n\nThis study presents a Deep Rei
 nforcement Learning (DRL) framework for optimizing the routing of multiple
  droplets in Digital Microfluidic Biochips (DMFBs). Our approach significa
 ntly reduces computational costs by optimizing voltage-applied cell positi
 ons, enabling the parallel movement of multiple droplets with a single neu
 ral network pass. Experimental results on various DMFB sizes and droplet c
 ounts demonstrate a reduction of up to 98% in neural network parameters an
 d 95% in memory usage for a 10x10 grid with two droplets. Additionally, th
 e proposed method enhances success rates of routing as the number of dropl
 ets increases, surpassing existing multi-agent DRL techniques.\n\nTopic: A
 I, Autonomous Systems, Cloud, Design, EDA, Embedded Systems, IP, Security
END:VEVENT
END:VCALENDAR