BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251220T070447Z
UID:DF790524-E38F-436B-8888-0EA4C1A37AFB
DTSTART;TZID=America/New_York:20251219T103000
DTEND;TZID=America/New_York:20251219T113000
DESCRIPTION:In this seminar\, we explore the potential role of digital twin
 s (DTs) in Edge Intelligence (EI)-empowered Integrated Sensing and Communi
 cation (ISAC) with two case studies. First\, we show that DTs can be used 
 to model the stochastic spatial distributions of sensing targets\, which i
 s essential for characterizing service demands and optimizing proactive re
 source management in ISAC. Our DT design adaptively synergizes multiple ca
 ndidate spatial models for location-based resource reservation. Second\, w
 e show that DTs can enable a user-centric approach to deep neural networks
  (DNN)-based sensing data processing. Given an ISAC device with a small DN
 N model and a mobile edge computing (MEC) server with a large DNN model\, 
 our DT design supports continual learning in the presence of data drifts. 
 Leveraging the above role of DT\, we can achieve objectives such as minimi
 zing resource reservation or computation costs subject to performance cons
 traints.\n\nRoom: 460\, Bldg: ENG\, 245 church St.\, Toronto\, Ontario\, C
 anada\, M5B 2R2
LOCATION:Room: 460\, Bldg: ENG\, 245 church St.\, Toronto\, Ontario\, Canad
 a\, M5B 2R2
ORGANIZER:ajmery.sultana@algomau.ca
SEQUENCE:33
SUMMARY:Digital Twin in Edge Intelligence-empowered Integrated Sensing and 
 Communication 
URL;VALUE=URI:https://events.vtools.ieee.org/m/523737
X-ALT-DESC:Description: <br /><div dir="auto">In this seminar\, we explore 
 the potential role of digital twins (DTs) in Edge Intelligence (EI)-empowe
 red Integrated Sensing and Communication (ISAC) with two case studies. Fir
 st\, we show that DTs can be used to model the stochastic spatial distribu
 tions of sensing targets\, which is essential for characterizing service d
 emands and optimizing proactive resource management in ISAC. Our DT design
  adaptively synergizes multiple candidate spatial models for location-base
 d resource reservation. Second\, we show that DTs can enable a user-centri
 c approach to deep neural networks (DNN)-based sensing data processing. Gi
 ven an ISAC device with a small DNN model and a mobile edge computing (MEC
 ) server with a large DNN model\, our DT design supports continual learnin
 g in the presence of data drifts. Leveraging the above role of DT\, we can
  achieve objectives such as minimizing resource reservation or computation
  costs subject to performance constraints.</div>\n<div dir="auto">&nbsp\;<
 /div>
END:VEVENT
END:VCALENDAR