BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240217T164743Z
UID:E816BAAB-E645-40F8-82C2-412009498ADB
DTSTART;TZID=America/New_York:20240207T130000
DTEND;TZID=America/New_York:20240207T140000
DESCRIPTION:Detection in the maritime domain requires the radar return from
  targets to be distinguishable\nfrom the background interference. These ra
 dars traditionally use non-coherent processing due\nto the time-varying an
 d range-varying nature of the Doppler spectra. However\, as radar\nplatfor
 ms fly higher and look down at steeper angles\, the sea clutter power will
  increase and\ntraditional methods will not be as effective. This talk cov
 ers several new approaches for\ntarget detection in the maritime domain. T
 hese include the use of sparse signal separation\nalgorithms\, including d
 ictionary learning\, two machine learning algorithms and the\napplication 
 of the single snapshot coherent detector. Each of these techniques is demo
 nstrated\nusing using either real or realistic simulated sea clutter and s
 hows good potential when\ncompared to traditional processing methods.\n\nS
 peaker(s): Luke Rosenberg\, \n\nRoom: CST 4-201\, Bldg: Center of Science 
 & Technology\, Syracuse University\, 111 College Pl\, Syracuse\, New York\
 , United States\, 13210\, Virtual: https://events.vtools.ieee.org/m/402058
LOCATION:Room: CST 4-201\, Bldg: Center of Science & Technology\, Syracuse 
 University\, 111 College Pl\, Syracuse\, New York\, United States\, 13210\
 , Virtual: https://events.vtools.ieee.org/m/402058
ORGANIZER:stone@ieee.org
SEQUENCE:14
SUMMARY:Machine Learning Approaches to Maritime Detection
URL;VALUE=URI:https://events.vtools.ieee.org/m/402058
X-ALT-DESC:Description: <br /><p>Detection in the maritime domain requires 
 the radar return from targets to be distinguishable<br />from the backgrou
 nd interference. These radars traditionally use non-coherent processing du
 e<br />to the time-varying and range-varying nature of the Doppler spectra
 . However\, as radar<br />platforms fly higher and look down at steeper an
 gles\, the sea clutter power will increase and<br />traditional methods wi
 ll not be as effective. This talk covers several new approaches for<br />t
 arget detection in the maritime domain. These include the use of sparse si
 gnal separation<br />algorithms\, including dictionary learning\, two mach
 ine learning algorithms and the<br />application of the single snapshot co
 herent detector. Each of these techniques is demonstrated<br />using using
  either real or realistic simulated sea clutter and shows good potential w
 hen<br />compared to traditional processing methods.</p>
END:VEVENT
END:VCALENDAR