BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20221106T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20221102T210624Z UID:F91D2CE9-4C1F-4369-84F6-A1E0BCB149E6 DTSTART;TZID=America/New_York:20221102T160000 DTEND;TZID=America/New_York:20221102T170500 DESCRIPTION:Abstract:\n\nDue to the explosive growth of new users and new a pplications\, it is expected that the wireless spectrum will need to be us ed in a dynamic fashion starting in the near future. This can be achieved by using the concept of cognitive radio\, giving users access to the unuse d spectrum under dynamic spectrum access. It is generally accepted that co nventional methods of cognitive radio will fall short of being able to han dle the enormous demand for spectral resources\, and therefore it is expec ted that techniques from artificial intelligence or machine learning will help provide dynamic control for spectrum sharing. The process of spectrum sharing begins with sensing the spectrum. Recently\, a number of techniqu es for spectrum sensing employing machine learning have been introduced.\n \nIn this talk\, we employ a machine learning approach known as generative adversarial networks towards this purpose. This particular approach is kn own to be very successful for anomaly detection in image processing. We al ter performance criteria used in this set of networks from image processin g applications to wireless and employ such networks for spectrum sensing\, both in conventional and cooperative spectrum sensing. Initial results sh ow the efficacy of this approach.\n\nSpeaker(s): Dr. Ender\, \n\nVirtual: https://events.vtools.ieee.org/m/329642 LOCATION:Virtual: https://events.vtools.ieee.org/m/329642 ORGANIZER:syed.tamseel@ieee.org SEQUENCE:10 SUMMARY:VDL: Generative Adversarial Networks for Spectrum Sharing URL;VALUE=URI:https://events.vtools.ieee.org/m/329642 X-ALT-DESC:Description: <br /><p>Abstract:<br /><br />Due to the explosive growth of new users and new applications\, it is expected that the wireles s spectrum will need to be used in a dynamic fashion starting in the near future. This can be achieved by using the concept of cognitive radio\, giv ing users access to the unused spectrum under dynamic spectrum access. It is generally accepted that conventional methods of cognitive radio will fa ll short of being able to handle the enormous demand for spectral resource s\, and therefore it is expected that techniques from artificial intellige nce or machine learning will help provide dynamic control for spectrum sha ring. The process of spectrum sharing begins with sensing the spectrum. Re cently\, a number of techniques for spectrum sensing employing machine lea rning have been introduced.</p>\n<p>In this talk\, we employ a machine lea rning approach known as generative adversarial networks towards this purpo se. This particular approach is known to be very successful for anomaly de tection in image processing. We alter performance criteria used in this se t of networks from image processing applications to wireless and employ su ch networks for spectrum sensing\, both in conventional and cooperative sp ectrum sensing. Initial results show the efficacy of this approach.&nbsp\; </p> END:VEVENT END:VCALENDAR