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:20251212T154901Z
UID:FB636F7F-7954-490D-9DBD-8A3EC3A7A103
DTSTART;TZID=America/New_York:20251212T100000
DTEND;TZID=America/New_York:20251212T104500
DESCRIPTION:Abstract: The use of wireless communication has been growing si
 gnificantly. Given the limited radio spectrum available\, it is important 
 to use modulation techniques to squeeze the most information in the least 
 amount of spectrum. To improve the throughput and reliability of communica
 tion\, Automatic Modulation Classification (AMC) has become an essential t
 opic in the research of Cognitive Radio (CR). AMC is a technique to identi
 fy the modulation scheme of the received radio signals without any transmi
 ssion parameters. The state-of-the-art approach is to use a pre-trained cl
 assifier to determine the modulation in use. Unfortunately\, all forms of 
 distortions and interference are impossible to predict\, and thus these ap
 proaches fail when new distortions or interference appear that were not pr
 eviously learned. In this work\, we developed a technique where the transm
 itter periodically sends out a known ordered sequence of signals of all th
 e modulations to be used by the receiver. The receiver knows the transmiss
 ion sequence and thus knows how to label these received signals containing
  each required modulation. We used an over-the-air (OTA) radio transmissio
 n between software-defined radio (SDR) devices\, and the collected diction
 ary dataset was used to train a neural network at the receiver. Our result
 s show that training the network in real-time while the radio is in use ca
 n enable significantly better performance than any of the existing approac
 hes. Additionally\, a neuromorphic system is presented that is over 50x en
 ergy efficient than optimized digital systems at this wireless signal modu
 lation learning task for similar accuracy levels. This is important for ed
 ge applications that are power constrained.\n\nSpeaker: Dr. Tarek Taha\, P
 rofessor of Electrical and Computer Engineering\, University of Dayton\n\n
 Website: https://taha-lab.org\n\nVirtual: https://events.vtools.ieee.org/m
 /521338
LOCATION:Virtual: https://events.vtools.ieee.org/m/521338
ORGANIZER:ttaha1@udayton.edu
SEQUENCE:26
SUMMARY:Deep Learning Based Automatic Modulation Classification in Communic
 ation Jammed Environments
URL;VALUE=URI:https://events.vtools.ieee.org/m/521338
X-ALT-DESC:Description: <br /><p>Abstract: The use of wireless communicatio
 n has been growing significantly. Given the limited radio spectrum availab
 le\, it is important to use modulation techniques to squeeze the most info
 rmation in the least amount of spectrum. To improve the throughput and rel
 iability of communication\, Automatic Modulation Classification (AMC) has 
 become an essential topic in the research of Cognitive Radio (CR). AMC is 
 a technique to identify the modulation scheme of the received radio signal
 s without any transmission parameters. The state-of-the-art approach is to
  use a pre-trained classifier to determine the modulation in use. Unfortun
 ately\, all forms of distortions and interference are impossible to predic
 t\, and thus these approaches fail when new distortions or interference ap
 pear that were not previously learned. In this work\, we developed a techn
 ique where the transmitter periodically sends out a known ordered sequence
  of signals of all the modulations to be used by the receiver. The receive
 r knows the transmission sequence and thus knows how to label these receiv
 ed signals containing each required modulation. We used an over-the-air (O
 TA) radio transmission between software-defined radio (SDR) devices\, and 
 the collected dictionary dataset was used to train a neural network at the
  receiver. Our results show that training the network in real-time while t
 he radio is in use can enable significantly better performance than any of
  the existing approaches. Additionally\, a neuromorphic system is presente
 d that is over 50x energy efficient than optimized digital systems at this
  wireless signal modulation learning task for similar accuracy levels. Thi
 s is important for edge applications that are power constrained.</p>\n<p>S
 peaker: Dr. Tarek Taha\, Professor of Electrical and Computer Engineering\
 , University of Dayton</p>\n<p>Website: https://taha-lab.org</p>
END:VEVENT
END:VCALENDAR