BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Phoenix BEGIN:STANDARD DTSTART:19671029T010000 TZOFFSETFROM:-0600 TZOFFSETTO:-0700 TZNAME:MST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20231019T200908Z UID:321D2C22-550E-4943-80A2-FF6C5D391944 DTSTART;TZID=America/Phoenix:20231019T120000 DTEND;TZID=America/Phoenix:20231019T130000 DESCRIPTION:AI/ML Open-Source solutions are becoming more prevalent with th e increased availability of data along with faster and low-cost processing compute. Neethu\, alongside her team\, created an AI/ML Data pipeline Pro cessing infrastructure to enable healthcare use cases with open source Edg eX Foundries microservices that automatically detect\, manage\, and proces s images received from OEM equipment. This project enabled managing AI/ML pipelines for image processing and automating image comparisons\, and deve loping an adaptable solution for different use cases and settings\, levera ging a containerized microservices based architecture and various communic ation APIs & messaging bus including MQTT. This project included interesti ng challenges such as a distributed deployment at the edge scenario where some services ran on windows-based OEM equipment\, while others ran on a L inux Edge box\, timing-dependent issues leading to a lack of idempotency i n integration tests\, and discussions around the idea of adding wait strat egy for dependent services to be up and ready before accepting TCP connect ions. This session will cover the architecture & design\, with integration of EdgeX features to develop this solution for Edge devices along with th e learnings from this open-source project.\n\nOpen-Source code for setup\, install\, and execution of software\, with complete developer documentati on - https://github.com/intel/AiCSD\n\nCo-sponsored by: Neethu Elizabeth S imon\n\nSpeaker(s): Neethu Elizabeth Simon\n\nVirtual: https://events.vtoo ls.ieee.org/m/377039 LOCATION:Virtual: https://events.vtools.ieee.org/m/377039 ORGANIZER:neige.lam@gmail.com SEQUENCE:19 SUMMARY:AI/ML Data Pipeline Processing with Go Microservices based solution at the Edge using Open-Source Technology URL;VALUE=URI:https://events.vtools.ieee.org/m/377039 X-ALT-DESC:Description: <br /><p style="margin: 0in\; margin-left: .375in\; font-family: Arial\; font-size: 11.0pt\; color: #222222\;">AI/ML Open-Sou rce solutions are becoming more prevalent with the increased availability of data along with faster and low-cost processing compute. Neethu\, alongs ide her team\, created an AI/ML Data pipeline Processing infrastructure to enable healthcare use cases with open source EdgeX Foundries microservice s that automatically detect\, manage\, and process images received from OE M equipment. This project enabled managing AI/ML pipelines for image proce ssing and automating image comparisons\, and developing an adaptable solut ion for different use cases and settings\, leveraging a containerized micr oservices based architecture and various communication APIs &amp\; messagi ng bus including MQTT. This project included interesting challenges such a s a distributed deployment at the edge scenario where some services ran on windows-based OEM equipment\, while others ran on a Linux Edge box\, timi ng-dependent issues leading to a lack of idempotency in integration tests\ , and discussions around the idea of adding wait strategy for dependent se rvices to be up and ready before accepting TCP connections. This session w ill cover the architecture &amp\; design\, with integration of EdgeX featu res to develop this solution for Edge devices along with the learnings fro m this open-source project.</p>\n<p style="margin: 0in\; margin-left: .375 in\; font-family: Arial\; font-size: 11.0pt\;"><span style="color: #222222 \;">Open-Source code for setup\, install\, and execution of software\, wit h complete developer documentation -&nbsp\; </span><a href="https://github .com/intel/AiCSD">https://github.com/intel/AiCSD</a></p> END:VEVENT END:VCALENDAR