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:20261101T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260731T193031Z UID:66455E44-3398-4503-930A-266E03AD4C5A DTSTART;TZID=America/New_York:20260807T110000 DTEND;TZID=America/New_York:20260807T123000 DESCRIPTION:Abstract: Ensuring resilient network connectivity after natural disasters is critical to the operation of modern smart cities. However\, post-disaster network recovery faces significant challenges\, including in complete user traffic profiles\, unique post-disaster user movement patter ns\, and unknown network traffic dynamics. In this talk\, I will present a digital-twin-assisted network recovery and management (DT-NRM) framework to address these challenges. Specifically\, in the proposed framework\, we build and maintain a high-fidelity DT model through two-stage closed-loop DT lifecycles\, DT lifecycle 1 (DT-C1) and DT lifecycle 2 (DT-C2)\, which predict the post-disaster network traffic variations and further assist n etwork reconstruction via unmanned aerial vehicle (UAV) deployment. In DT- C1\, we establish the DT model through partial physical network traffic da ta collection and refinement\, integrating graph neural network (GNN)-base d user traffic prediction with a first-stage residual-based calibration to enhance the DT model performance. Based on the predicted user traffic fro m DT-C1\, DT-C2 implements a two-timescale network recovery and management solution via large-timescale proactive UAV deployment and small-timescale UAV resource allocation. Aerial-terrestrial data fusion is then applied t o restore the complete network traffic profile for a second-stage DT model calibration through transfer learning. The iterative two-stage DT lifecyc les enable continuous DT model evolution. A case study demonstrates that t he proposed DT-NRM accurately predicts network traffic dynamics and outper forms state-of-the-art approaches. We will also discuss some future resear ch directions at the end of the talk.\n\nBio: Dr. Qiang (John) Ye received the PhD degree in Electrical and Computer Engineering from the University of Waterloo\, ON\, Canada\, in 2016. Since 2023\, he has been a faculty m ember with the Department of Electrical and Software Engineering\, Schulic h School of Engineering\, University of Calgary\, AB\, Canada. Before join ing UCalgary\, he worked as a faculty member with the Memorial University of Newfoundland\, NL\, Canada from 2021 to 2023 and with the Minnesota Sta te University\, Mankato\, USA\, from 2019 to 2021\, respectively. He was w ith the Department of Electrical and Computer Engineering\, University of Waterloo as a Postdoctoral Fellow and then a Research Associate from 2016 to 2019. He has published over 90 research articles on top-ranked journals and conference proceedings. He is/was the General\, Publication\, Program Co-chairs for different reputable international conferences and workshops (e.g.\, IEEE INFOCOM\, GLOBECOM\, VTC\, ICCC\, ICCT\, WISEE\, SWC). He al so serves/served as the IEEE Vehicular Technology Society (VTS) Region 7 C hapter Coordinator in 2024\, the IEEE Communications Society (ComSoc) Sout hern Alberta Chapter Vice Chair from 2024\, and the VTS Regions 1-7 Chapte rs Coordinator from 2022 to 2023. He is the leading SIG co-chair in the IE EE ComSoc - IoT-AHSN Technical Committee. Dr. Ye serves/served as an Assoc iate Editor for prestigious IEEE journals\, such as IEEE TNSM\, IEEE WCL\, IEEE IoT-J\, IEEE TVT\, IEEE TCCN\, and IEEE OJ-COMS. He received the IEE E Open Journal of Vehicular Technology (OJVT) Best Paper Award in 2026\, t he Best Paper Award in the IEEE/CIC International Conference on Communicat ions in China (ICCC) in 2024\, the Early Career Research Excellence Award\ , Schulich School of Engineering\, University of Calgary\, in 2025\, the I EEE OJ-COMS Exemplary Editor Award in 2025\, the IEEE TCCN Exemplary Edito r Award in 2023. He has been selected as an IEEE Communication Society Dis tinguished Lecturer for the class of 2025-2026. He has been named among th e World’s Top 2% Scientists in 2021-2025 (by Stanford/Elsevier). Dr. Ye is Senior Member of IEEE.\n\n[]\n\nSpeaker(s): John\, \n\nRoom: WLH 314\, Bldg: Walter Light Hall\, Queen's University\, 19 Union St\, Kingston\, On tario\, Canada\, K7L 3N9\, Virtual: https://events.vtools.ieee.org/m/57054 7 LOCATION:Room: WLH 314\, Bldg: Walter Light Hall\, Queen's University\, 19 Union St\, Kingston\, Ontario\, Canada\, K7L 3N9\, Virtual: https://events .vtools.ieee.org/m/570547 ORGANIZER:chan-f@rmc.ca SEQUENCE:34 SUMMARY:IEEE DLT: Synergizing Digital Twins and UAVs for Post-Disaster Netw ork Recovery and Management URL;VALUE=URI:https://events.vtools.ieee.org/m/570547 X-ALT-DESC:Description: <br /><p class="MsoNormal" style="margin-left: 2.85 pt\;"><strong><span lang="EN-US" style="font-size: 12.0pt\; font-family: ' Times New Roman'\,serif\;">Abstract:</span></strong><span lang="EN-US" sty le="font-size: 12.0pt\; font-family: 'Times New Roman'\,serif\;"> Ensuring resilient network connectivity after natural disasters is critical to the operation of modern smart cities. However\, post-disaster network recover y faces significant challenges\, including incomplete user traffic profile s\, unique post-disaster user movement patterns\, and unknown network traf fic dynamics. In this talk\, I will present a digital-twin-assisted networ k recovery and management (DT-NRM) framework to address these challenges. Specifically\, in the proposed framework\, we build and maintain a high-fi delity DT model through two-stage closed-loop DT lifecycles\, DT lifecycle 1 (DT-C1) and DT lifecycle 2 (DT-C2)\, which predict the post-disaster ne twork traffic variations and further assist network reconstruction via unm anned aerial vehicle (UAV) deployment. In DT-C1\, we establish the DT mode l through partial physical network traffic data collection and refinement\ , integrating graph neural network (GNN)-based user traffic prediction wit h a first-stage residual-based calibration to enhance the DT model perform ance. Based on the predicted user traffic from DT-C1\, DT-C2 implements a two-timescale network recovery and management solution via large-timescale proactive UAV deployment and small-timescale UAV resource allocation. Aer ial-terrestrial data fusion is then applied to restore the complete networ k traffic profile for a second-stage DT model calibration through transfer learning. The iterative two-stage DT lifecycles enable continuous DT mode l evolution. A case study demonstrates that the proposed DT-NRM accurately predicts network traffic dynamics and outperforms state-of-the-art approa ches. We will also discuss some future research directions at the end of t he talk.</span></p>\n<p class="MsoNormal" style="margin-left: 2.85pt\;"><s pan lang="EN-US" style="font-size: 12.0pt\; font-family: 'Times New Roman' \,serif\;">&nbsp\;</span></p>\n<p class="MsoNormal" style="margin-left: 2. 85pt\;"><strong><span lang="EN-US" style="font-size: 12.0pt\; font-family: 'Times New Roman'\,serif\;">Bio:</span></strong><span lang="EN-US" style= "font-size: 12.0pt\; font-family: 'Times New Roman'\,serif\;"> Dr. Qiang ( John) Ye received the PhD degree in Electrical and Computer Engineering fr om the University of Waterloo\, ON\, Canada\, in 2016. Since 2023\, he has been a faculty member with the Department of Electrical and Software Engi neering\, Schulich School of Engineering\, University of Calgary\, AB\, Ca nada. Before joining UCalgary\, he worked as a faculty member with the Mem orial University of Newfoundland\, NL\, Canada from 2021 to 2023 and with the Minnesota State University\, Mankato\, USA\, from 2019 to 2021\, respe ctively. He was with the Department of Electrical and Computer Engineering \, University of Waterloo as a Postdoctoral Fellow and then a Research Ass ociate from 2016 to 2019. He has published over 90 research articles on to p-ranked journals and conference proceedings. He is/was the General\, Publ ication\, Program Co-chairs for different reputable international conferen ces and workshops (e.g.\, IEEE INFOCOM\, GLOBECOM\, VTC\, ICCC\, ICCT\, WI SEE\, SWC). He also serves/served as the IEEE Vehicular Technology Society (VTS) Region 7 Chapter Coordinator in 2024\, the IEEE Communications Soci ety (ComSoc) Southern Alberta Chapter Vice Chair from 2024\, and the VTS R egions 1-7 Chapters Coordinator from 2022 to 2023. He is the leading SIG c o-chair in the IEEE ComSoc - IoT-AHSN Technical Committee. Dr. Ye serves/s erved as an Associate Editor for prestigious IEEE journals\, such as IEEE TNSM\, IEEE WCL\, IEEE IoT-J\, IEEE TVT\, IEEE TCCN\, and IEEE OJ-COMS. He received the IEEE Open Journal of Vehicular Technology (OJVT) Best Paper Award in 2026\, the Best Paper Award in the IEEE/CIC International Confere nce on Communications in China (ICCC) in 2024\, the Early Career Research Excellence Award\, Schulich School of Engineering\, University of Calgary\ , in 2025\, the IEEE OJ-COMS Exemplary Editor Award in 2025\, the IEEE TCC N Exemplary Editor Award in 2023. He has been selected as an IEEE Communic ation Society Distinguished Lecturer for the class of 2025-2026. He has be en named among the World&rsquo\;s Top 2% Scientists in 2021-2025 (by Stanf ord/Elsevier). Dr. Ye is Senior Member of IEEE.</span></p>\n<p class="MsoN ormal" style="margin-left: 2.85pt\;">&nbsp\;</p>\n<p class="MsoNormal" sty le="margin-left: 2.85pt\;">&nbsp\;</p>\n<p class="MsoNormal" style="margin -left: 2.85pt\;"><span lang="EN-US" style="font-size: 12.0pt\; font-family : 'Times New Roman'\,serif\;"><img src="https://events.vtools.ieee.org/vto ols_ui/media/display/84c70c93-dca7-4a0e-934c-9c61775d6042" alt="" width="2 66" height="398"></span></p> END:VEVENT END:VCALENDAR