BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Canada/Eastern
BEGIN:DAYLIGHT
DTSTART:20210314T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20211107T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210908T201952Z
UID:3653C2C0-935B-4BC1-BBF5-A1B6C195FF0A
DTSTART;TZID=Canada/Eastern:20210916T090000
DTEND;TZID=Canada/Eastern:20210916T100000
DESCRIPTION:As the Internet-of-Things devices are being widely adopted in a
 ll fields\, such as smart houses\, healthcare\, and transportation\, large
  amounts of data are being collected\, shared\, and processed. This fact r
 aises many challenges on how to make the best use of this huge amount of d
 ata to improve the IoT systems’ security using artificial intelligence\,
  taking into consideration the resource limitations in IoT devices and iss
 ues regarding data privacy. Different techniques have been studied and dev
 eloped throughout the years. For example\, Federated Learning (FL)\, which
  is an emerging learning technique that is very well known for preserving 
 and respecting the privacy of the collaborating clients’ data during mod
 el training. The concepts of FL and Hierarchical Federated Learning (HFL) 
 are evaluated and compared with respect of detection accuracy and speed of
  convergence\, through simulating an Intrusion Detection System for Intern
 et-of-Things applications. Different kinds of datasets (e.g.\, NSL-KDD) ar
 e used in our work to prove that our developed schemes are superior compar
 ed to other schemes in terms of training loss\, testing accuracy\, and spe
 ed of convergence. HFL also showed its efficiency over FL in reducing the 
 effect of the non-identically and independently distributed data on the co
 llaborative learning process.\n\nIn this Keynote\, we review the current e
 fforts by experts around the world to mitigate some of these challenges. T
 hen\, we showcase our research activities to contribute to these efforts a
 nd advocate possible solutions using AI and other tools. We provide ways o
 n how to manage the available resources intelligently and efficiently in o
 rder to offer better conditions and provide improved services. Finally\, w
 e discuss some of our research results to support a variety of application
 s including how to secure these devices for successful healthcare service 
 delivery in different aspects.\n\nSpeaker: Mohsen Guizani\, Professor and 
 IEEE Fellow\; Senior EiC\, IEEE Network\n\nCo-sponsored by: Canadian Confe
 rence on Electrical and Computer Engineering (CCECE) 2021\n\nSpeaker(s): D
 r. Mohsen Guizani\, \n\nVirtual: https://events.vtools.ieee.org/m/280086
LOCATION:Virtual: https://events.vtools.ieee.org/m/280086
ORGANIZER:murraymacdonald@ieee.org
SEQUENCE:3
SUMMARY:CCECE 2021 Keynote Speech - Federated Learning and its applications
  to Internet of Things
URL;VALUE=URI:https://events.vtools.ieee.org/m/280086
X-ALT-DESC:Description: <br /><p>As the Internet-of-Things devices are bein
 g widely adopted in all fields\, such as smart houses\, healthcare\, and t
 ransportation\, large amounts of data are being collected\, shared\, and p
 rocessed. This fact raises many challenges on how to make the best use of 
 this huge amount of data to improve the IoT systems&rsquo\; security using
  artificial intelligence\, taking into consideration the resource limitati
 ons in IoT devices and issues regarding data privacy. Different techniques
  have been studied and developed throughout the years. For example\, Feder
 ated Learning (FL)\, which is an emerging learning technique that is very 
 well known for preserving and respecting the privacy of the collaborating 
 clients&rsquo\; data during model training. The concepts of FL and Hierarc
 hical Federated Learning (HFL) are evaluated and compared with respect of 
 detection accuracy and speed of convergence\, through simulating an Intrus
 ion Detection System for Internet-of-Things applications. Different kinds 
 of datasets (e.g.\, NSL-KDD) are used in our work to prove that our develo
 ped schemes are superior compared to other schemes in terms of training lo
 ss\, testing accuracy\, and speed of convergence. HFL also showed its effi
 ciency over FL in reducing the effect of the non-identically and independe
 ntly distributed data on the collaborative learning process.</p>\n<p>In th
 is Keynote\, we review the current efforts by experts around the world to 
 mitigate some of these challenges. Then\, we showcase our research activit
 ies to contribute to these efforts and advocate possible solutions using A
 I and other tools. We provide ways on how to manage the available resource
 s intelligently and efficiently in order to offer better conditions and pr
 ovide improved services. Finally\, we discuss some of our research results
  to support a variety of applications including how to secure these device
 s for successful healthcare service delivery in different aspects.</p>\n<p
 >Speaker: Mohsen Guizani\, Professor and IEEE Fellow\;&nbsp\;Senior EiC\, 
 IEEE Network</p>
END:VEVENT
END:VCALENDAR