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:20241103T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20240323T161134Z UID:33C7BE05-D0F6-4F44-8798-1E53AD71F764 DTSTART;TZID=America/New_York:20240316T143500 DTEND;TZID=America/New_York:20240316T153000 DESCRIPTION:Low Energy Sensor Platform - Leveraging Machine Learning\n\nAbs tract: Applications of embedded AI\, specifically ML (Machine Learning) an d object classification has\nbeen growing exponentially as decision logic moves to the edge. Proven advantages of low energy\nconsumption\, low cost s\, and independent target classification drive this implementation and is transforming\nsmart city management\, agriculture\, medical\, health care \, bridge and building structure health management\n(SHM)\, and smart logi stics just to name a few game-changing applications.\n\nSeveral specific M L applications will be discussed including a vision ML application applied to logistics\, a\nremote visual cargo classification smart sensor (curren tly in production). Challenges of a small vs. large CNN\nmodel when improv ing object identification and accuracy will also be discussed and why ML a t the network\nedge is a game-changer. Finally\, we will compare and contr ast the AI categories of large language models\nand the energy-constrained tiny ML sensor models.\n\nBio: The speaker\, Joe Jesson\, co-founded & wa s CTO of a General Electric business\, Asset Intelligence\, a GE business that designed\nand sold remote IoT sensors for the logistics and energy se ctors. Machine learning and LPWAN sensor communication became an\nintegral part of the remote monitoring and management of mobile and remote assets. An ongoing research goal is to reduce the smart\nenergy costs where 100% of the power is generated by ambient energy harvesting. Joe is currently C EO of RF Sigint Group and has\nover 25+ years of engineering and managemen t experience with Motorola APD\, Oak Technology\, BP\, and General Electri c. Master's\ndegree from DePaul University & working on a Ph.D.defense. Co ntact: jejesson4@gmail.com\n\nNote: this is a TCF Event - No need to regis ter\, but you need to purchase a TCF all-day admission ticket at https://t cf-nj.org/\n\nRoom: ED115\, Bldg: Education\, The College of New Jersey\, Metzger Dr\, Ewing\, New Jersey\, United States\, 08618 LOCATION:Room: ED115\, Bldg: Education\, The College of New Jersey\, Metzge r Dr\, Ewing\, New Jersey\, United States\, 08618 ORGANIZER:jejesson4@gmail.com SEQUENCE:5 SUMMARY:T-1 (ED 115): Low Energy Sensor Platform - Leveraging Machine Learn ing URL;VALUE=URI:https://events.vtools.ieee.org/m/409981 X-ALT-DESC:Description: <br /><p><strong>Low Energy Sensor Platform - Lever aging Machine Learning</strong></p>\n<p><strong>Abstract:</strong> Applica tions of embedded AI\, specifically ML (Machine Learning) and object class ification has<br>been growing exponentially as decision logic moves to the edge. Proven advantages of low energy<br>consumption\, low costs\, and in dependent target classification drive this implementation and is transform ing<br>smart city management\, agriculture\, medical\, health care\, bridg e and building structure health management<br>(SHM)\, and smart logistics just to name a few game-changing applications.</p>\n<p><br>Several specifi c ML applications will be discussed including a vision ML application appl ied to logistics\, a<br>remote visual cargo classification smart sensor (c urrently in production). Challenges of a small vs. large CNN<br>model when improving object identification and accuracy will also be discussed and w hy ML at the network<br>edge is a game-changer. Finally\, we will compare and contrast the AI categories of large language models<br>and the energy- constrained tiny ML sensor models.</p>\n<p><strong>Bio:&nbsp\;</strong>The speaker\, Joe Jesson\, co-founded &amp\; was CTO of a General Electric bu siness\, Asset Intelligence\, a GE business that designed<br>and sold remo te IoT sensors for the logistics and energy sectors. Machine learning and LPWAN sensor communication became an<br>integral part of the remote monito ring and management of mobile and remote assets. An ongoing research goal is to reduce the smart<br>energy costs where 100% of the power is generate d by ambient energy harvesting. Joe is currently CEO of RF Sigint Group an d has<br>over 25+ years of engineering and management experience with Moto rola APD\, Oak Technology\, BP\, and General Electric. Master's<br>degree from DePaul University &amp\; working on a Ph.D.defense. Contact: jejesson 4@gmail.com</p>\n<p><strong>Note: this is a TCF Event - No need to registe r\, but you need to purchase a TCF all-day admission ticket at&nbsp\;<a hr ef="https://tcf-nj.org/">https://tcf-nj.org/</a></strong></p> END:VEVENT END:VCALENDAR