BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Pacific BEGIN:DAYLIGHT DTSTART:20200308T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20191103T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20200219T050628Z UID:C1788F29-C047-4660-A3E2-7EB7B105D0F5 DTSTART;TZID=US/Pacific:20200218T183000 DTEND;TZID=US/Pacific:20200218T200000 DESCRIPTION:“A pedestrian is killed by a car roughly every 90 minutes in the United States. And until this week\, all of those drivers were human. ” This was a newspaper headline in March 2018 after a pedestrian was str uck and killed by a self-driving car. Even though self-driving vehicles do not pose any more of a risk to pedestrians than cars piloted by humans\, making autonomous vehicles drive safely in dense urban environment is stil l a challenge. This talk addresses how a radar system can recognize differ ent human motions\, including a pedestrian walking.\n\nRadar is a remote s ensor that has been proven successful in human motion recognition. Compare d with LiDAR and camera\, radar provides reliable monitoring while being r obust to lighting\, temperature and weather conditions. This presentation covers traditional and novel recognition methods of human motion radar sig natures. Traditional methods are based on manual feature extraction or Pri ncipal component analysis (PCA). Novel methods are based on deep learning techniques. Deep learning has emerged as the key part in the field of arti ficial intelligence due to its powerful brain-mimicking neural network str uctures. These complex structures allow an automated way of learning and c apturing the intricate properties of the human motion signatures in differ ent domains. Experimental results demonstrate that the deep learning metho ds provide high accuracy compared with the traditional methods.\n\nSpeaker (s): Branka Jokanovic\, \n\nAgenda: \nPizza and networking 6:30 p.m.\n\nTa lk 7:00 P.M.\n\nSkyworks inc\, 649 Lawrence Ave\, THOUSAND OAKS\, Californ ia\, United States\, 91320 LOCATION:Skyworks inc\, 649 Lawrence Ave\, THOUSAND OAKS\, California\, Uni ted States\, 91320 ORGANIZER:CSEABURY@PACBELL.NET SEQUENCE:2 SUMMARY:Human Motion Recognition Methods Using Radars URL;VALUE=URI:https://events.vtools.ieee.org/m/219333 X-ALT-DESC:Description: <br /><p class="Spacing"><span style="font-family: Verdana\; font-size: small\;"><span style="font-size: 11.0pt\;">&ldquo\;A pedestrian is killed by a car roughly every 90 minutes in the United State s. And until this week\, all of those drivers were human.&rdquo\; This was a newspaper headline in March 2018 after a pedestrian was struck and kill ed by a self-driving car. Even though self-driving vehicles do not pose an y more of a risk to pedestrians than cars piloted by humans\, making auton omous vehicles drive safely in dense urban environment is still a challeng e. This talk addresses how a radar system can recognize different human mo tions\, including a pedestrian walking.</span></span></p>\n<p class="Spaci ng"><span style="font-family: Verdana\; font-size: small\;"><span style="f ont-size: 11.0pt\;">Radar is a remote sensor that has been proven successf ul in human motion recognition. Compared with LiDAR and camera\, radar pro vides reliable monitoring while being robust to lighting\, temperature and weather conditions. This presentation covers traditional and novel recogn ition methods of human motion radar signatures. Traditional methods are ba sed on manual feature extraction or Principal component analysis (PCA). No vel methods are based on deep learning techniques. Deep learning has emerg ed as the key part in the field of artificial intelligence due to its powe rful brain-mimicking neural network structures. These complex structures a llow an automated way of learning and capturing the intricate properties o f the human motion signatures in different domains. Experimental results d emonstrate that the deep learning methods provide high accuracy compared w ith the traditional methods.</span></span></p><br /><br />Agenda: <br /><p >Pizza and networking 6:30 p.m.&nbsp\;</p>\n<p>Talk 7:00 P.M.&nbsp\;</p> END:VEVENT END:VCALENDAR