BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/St_Johns BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0430 TZOFFSETTO:-0330 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:NDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20241103T010000 TZOFFSETFROM:-0330 TZOFFSETTO:-0430 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:NST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250128T101127Z UID:2D0A1097-0E11-4BEA-8E63-C2CD2D4F1941 DTSTART;TZID=America/St_Johns:20250124T110000 DTEND;TZID=America/St_Johns:20250124T120000 DESCRIPTION:IEEE Newfoundland-Labrador Computer\, Communication\, and Circu its & Systems Joint Societies Chapter cordially invites you to a virtual t echnical presentation entitled “Deep Sigma Point Processes for Radar Cro ss Section Modeling in Spaceborne SAR Imagery” by Dr. Khalid El-Darymli\ , Defence Research and Development Canada (DRDC)\, Ottawa\, ON\, Canada.\n \nWhen: 11:00am-12:00pm\, Jan. 24\, 2025 (Friday)\n\nWhere: Virtual. See e vent location for more info.\n\nSeminar Title: Deep Sigma Point Processes for Radar Cross Section Modeling in Spaceborne SAR Imagery\n\nSeminar Abst ract:\n\nRadar Cross Section (RCS) modeling is foundational to advancing t he utility and sensitivity of spaceborne radar systems. This talk introduc es a Deep Sigma Point Process (DSPP) model for predicting RCS in Synthetic Aperture Radar (SAR) imagery\, using a RADARSAT-2 dataset containing 208\ ,191 verified ships. The DSPP model not only strives for predictive accura cy but ventures to characterize the uncertainty inherent in the intricate relationships among radar signals\, ship parameters\, and environmental co nditions. Unlike traditional approaches relying on deterministic equations with static parameters\, the DSPP leverages a hierarchical Gaussian Proce ss framework with Bayesian inference to capture variability and uncertaint y in RCS predictions. By generating predictive distributions rather than s ingle estimates\, the model effectively accounts for the complex dynamics governing radar returns. Using a Matérn kernel with Automatic Relevance D etermination\, the DSPP identifies and ranks critical features across rada r\, operational\, and environmental domains\, ensuring transparency and in terpretability. Performance evaluations demonstrate the model's superiorit y over linear regression baselines\, achieving a 20.83% reduction in Root Mean Squared Error (RMSE)\, a 25.89% increase in R²\, and a 44.4% reducti on in both residual Interquartile Range (IQR) and Median Absolute Deviatio n (MAD) on test data. By providing calibrated uncertainty bounds\, the DSP P enhances prediction reliability and supports robust decision-making. Thi s work marks a shift toward probabilistic models that incorporate the inhe rent uncertainty of complex phenomena. Transitioning from fixed equations to distributions over outcomes\, the DSPP fosters a deeper understanding o f RCS behavior\, enabling systems to thrive in dynamic operational environ ments.\n\nBiography of the Speaker:\n\nKhalid El-Darymli (Senior Member\, IEEE) received the B.Sc. degree in electrical engineering from Garyounis U niversity\, Benghazi\, Libya\, in 2001\, the M.Sc. degree in computer and information engineering from the International Islamic University of Malay sia\, Kuala Lumpur\, Malaysia\, in 2006\, and the Ph.D. degree (with disti nction) in electrical engineering from Memorial University\, St. John’s\ , NL\, Canada\, in 2015.\n\nFrom 2010 to 2014\, he was a Doctoral Research er with C-CORE\, St. John’s\, where he developed algorithms for target r ecognition in SAR imagery. From 2014 to 2017\, he worked as a Senior Engin eer with Northern Radar Inc.\, St. John’s\, co-developing a high-frequen cy software-defined radar for coastal ocean applications. Concurrently\, h e served as an instructor for both graduate and undergraduate courses in a ntennas with the Department of Electrical Engineering\, Faculty of Enginee ring and Applied Science\, Memorial University.\n\nFrom mid-2017 to early 2021\, Dr. El-Darymli was a Research and Development Scientist with MDA Sy stems\, Richmond\, BC\, Canada\, where he contributed to several projects\ , including laser guide stars for optical communications\, ground moving t arget indication (GMTI)\, velocity estimation in SAR imagery\, and target recognition in inverse SAR (ISAR) imagery. He is a licensed Professional E ngineer (P.Eng.) with the Association of Professional Engineers and Geosci entists of Alberta.\n\nSince mid-2021\, he has been a Defence Scientist wi th Defence Research and Development Canada (DRDC)\, Ottawa\, ON\, Canada\, focusing on various aspects of SAR and ISAR imagery\, along with other re search and development activities. In June 2023\, he was appointed Affilia te Faculty with the Fowler School of Engineering\, Chapman University\, Or ange\, CA\, USA.\n\nDr. El-Darymli is a Fellow of the School of Graduate S tudies. During his Ph.D. studies\, he received the Ocean Industries Studen t Research Award from the Research and Development Corporation (InnovateNL )\, Government of Newfoundland and Labrador\, for his work on SAR Detectio n in Cluttered Environments. He also won the IEEE NECEC 2013 Wally Read Be st Student Paper Award. During his M.Sc. studies\, he developed an award-w inning Speech to American Sign Language Interpreter System using machine l earning techniques.\n\nSpeaker(s): Dr. Khalid El-Darymli\n\nVirtual: https ://events.vtools.ieee.org/m/462940 LOCATION:Virtual: https://events.vtools.ieee.org/m/462940 ORGANIZER:lzhang@mun.ca SEQUENCE:17 SUMMARY:IEEE NL CCCS Chapter Technical Event - Deep Sigma Point Processes f or Radar Cross Section Modeling in Spaceborne SAR Imagery URL;VALUE=URI:https://events.vtools.ieee.org/m/462940 X-ALT-DESC:Description: <br /><p>IEEE Newfoundland-Labrador Computer\, Comm unication\, and Circuits &amp\; Systems Joint Societies Chapter cordially invites you to a virtual technical presentation entitled &ldquo\;Deep Sigm a Point Processes for Radar Cross Section Modeling in Spaceborne SAR Image ry&rdquo\; by Dr. Khalid El-Darymli\, Defence Research and Development Can ada (DRDC)\, Ottawa\, ON\, Canada.</p>\n<p>&nbsp\;</p>\n<p><strong>When: < /strong>11:00am-12:00pm\, Jan. 24\, 2025 (Friday)</p>\n<p>&nbsp\;</p>\n<p> <strong>Where: </strong>Virtual. See event location for more info.</p>\n<p >&nbsp\;</p>\n<p><strong>Seminar Title:</strong> Deep Sigma Point Processe s for Radar Cross Section Modeling in Spaceborne SAR Imagery</p>\n<p>&nbsp \;</p>\n<p><strong>Seminar Abstract:</strong></p>\n<p>Radar Cross Section (RCS) modeling is foundational to advancing the utility and sensitivity of spaceborne radar systems. This talk introduces a Deep Sigma Point Process (DSPP) model for predicting RCS in Synthetic Aperture Radar (SAR) imagery \, using a RADARSAT-2 dataset containing 208\,191 verified ships. The DSPP model not only strives for predictive accuracy but ventures to characteri ze the uncertainty inherent in the intricate relationships among radar sig nals\, ship parameters\, and environmental conditions. Unlike traditional approaches relying on deterministic equations with static parameters\, the DSPP leverages a hierarchical Gaussian Process framework with Bayesian in ference to capture variability and uncertainty in RCS predictions. By gene rating predictive distributions rather than single estimates\, the model e ffectively accounts for the complex dynamics governing radar returns. Usin g a Mat&eacute\;rn kernel with Automatic Relevance Determination\, the DSP P identifies and ranks critical features across radar\, operational\, and environmental domains\, ensuring transparency and interpretability. Perfor mance evaluations demonstrate the model's superiority over linear regressi on baselines\, achieving a 20.83% reduction in Root Mean Squared Error (RM SE)\, a 25.89% increase in R&sup2\;\, and a 44.4% reduction in both residu al Interquartile Range (IQR) and Median Absolute Deviation (MAD) on test d ata. By providing calibrated uncertainty bounds\, the DSPP enhances predic tion reliability and supports robust decision-making. This work marks a sh ift toward probabilistic models that incorporate the inherent uncertainty of complex phenomena. Transitioning from fixed equations to distributions over outcomes\, the DSPP fosters a deeper understanding of RCS behavior\, enabling systems to thrive in dynamic operational environments.</p>\n<p><s trong>Biography of the Speaker:</strong></p>\n<p>Khalid El-Darymli (Senior Member\, IEEE) received the B.Sc. degree in electrical engineering from G aryounis University\, Benghazi\, Libya\, in 2001\, the M.Sc. degree in com puter and information engineering from the International Islamic Universit y of Malaysia\, Kuala Lumpur\, Malaysia\, in 2006\, and the Ph.D. degree ( with distinction) in electrical engineering from Memorial University\, St. John&rsquo\;s\, NL\, Canada\, in 2015.</p>\n<p>From 2010 to 2014\, he was a Doctoral Researcher with C-CORE\, St. John&rsquo\;s\, where he develope d algorithms for target recognition in SAR imagery. From 2014 to 2017\, he worked as a Senior Engineer with Northern Radar Inc.\, St. John&rsquo\;s\ , co-developing a high-frequency software-defined radar for coastal ocean applications. Concurrently\, he served as an instructor for both graduate and undergraduate courses in antennas with the Department of Electrical En gineering\, Faculty of Engineering and Applied Science\, Memorial Universi ty.</p>\n<p>From mid-2017 to early 2021\, Dr. El-Darymli was a Research an d Development Scientist with MDA Systems\, Richmond\, BC\, Canada\, where he contributed to several projects\, including laser guide stars for optic al communications\, ground moving target indication (GMTI)\, velocity esti mation in SAR imagery\, and target recognition in inverse SAR (ISAR) image ry. He is a licensed Professional Engineer (P.Eng.) with the Association o f Professional Engineers and Geoscientists of Alberta.</p>\n<p>Since mid-2 021\, he has been a Defence Scientist with Defence Research and Developmen t Canada (DRDC)\, Ottawa\, ON\, Canada\, focusing on various aspects of SA R and ISAR imagery\, along with other research and development activities. In June 2023\, he was appointed Affiliate Faculty with the Fowler School of Engineering\, Chapman University\, Orange\, CA\, USA.</p>\n<p>Dr. El-Da rymli is a Fellow of the School of Graduate Studies. During his Ph.D. stud ies\, he received the Ocean Industries Student Research Award from the Res earch and Development Corporation (InnovateNL)\, Government of Newfoundlan d and Labrador\, for his work on SAR Detection in Cluttered Environments. He also won the IEEE NECEC 2013 Wally Read Best Student Paper Award. Durin g his M.Sc. studies\, he developed an award-winning Speech to American Sig n Language Interpreter System using machine learning techniques.</p> END:VEVENT END:VCALENDAR