BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260921T014648Z
UID:3F50A29B-0C1A-43E0-9CD5-F5DC4496CD49
DTSTART;TZID=America/New_York:20260922T200000
DTEND;TZID=America/New_York:20260922T214500
DESCRIPTION:This talk looks at AI in amateur radio not as a hobbyist curios
 ity\, but through the lens of MOVE&#39;s own recent deployments. Starting with
  Hurricane Helene&#39;s response in Asheville\, NC\, we&#39;ll walk through concre
 te “what if AI had been in the loop?” scenarios\; from pre-positioning
  trucks using signal-outage data\, to cutting through RF noise with deep-l
 earning tools\, to triaging urgent welfare-check traffic. We&#39;ll ground eac
 h scenario in real\, citable techniques: an IEEE-published noise-suppressi
 on framework\, and peer-reviewed machine-learning work from HamSCI (covere
 d in QST) on detecting ionospheric disturbances. We&#39;ll also look at a seco
 nd deployment: the LA wildfires\, and at something that isn&#39;t hypothetical
  at all: MOVE&#39;s own 2025–26 Truck Data Science Challenge\, which is alre
 ady applying anomaly detection to the club&#39;s fleet telemetry. The talk clo
 ses with an open discussion: where is AI operationally ready for a real de
 ployment today\, and where does it still need to earn trust?\n\nCo-sponsor
 ed by: IEEE-USA MOVE Program\n\nSpeaker(s): Joseph Kasser\n\nVirtual: http
 s://events.vtools.ieee.org/m/578875
LOCATION:Virtual: https://events.vtools.ieee.org/m/578875
ORGANIZER:l.arellano@ieee.org
SEQUENCE:20
SUMMARY:MOVE USA SEP 2026 Tech Talk - AI in Amateur Radio Disaster Response
 s
URL;VALUE=URI:https://events.vtools.ieee.org/m/578875
X-ALT-DESC:Description: &lt;br /&gt;&lt;p style=&quot;margin: 0in\;&quot;&gt;&lt;span style=&quot;font-fa
 mily: arial\, helvetica\, sans-serif\; font-size: 14pt\;&quot;&gt;This talk looks 
 at AI in amateur radio not as a hobbyist curiosity\, but through the lens 
 of MOVE&#39;s own recent deployments. Starting with Hurricane Helene&#39;s respons
 e in Asheville\, NC\, we&#39;ll walk through concrete &amp;ldquo\;what if AI had b
 een in the loop?&amp;rdquo\; scenarios\; from pre-positioning trucks using sig
 nal-outage data\, to cutting through RF noise with deep-learning tools\, t
 o triaging urgent welfare-check traffic. We&#39;ll ground each scenario in rea
 l\, citable techniques: an IEEE-published noise-suppression framework\, an
 d peer-reviewed machine-learning work from HamSCI (covered in QST) on dete
 cting ionospheric disturbances. We&#39;ll also look at a second deployment: th
 e LA wildfires\, and at something that isn&#39;t hypothetical at all: MOVE&#39;s o
 wn 2025&amp;ndash\;26 Truck Data Science Challenge\, which is already applying
  anomaly detection to the club&#39;s fleet telemetry. The talk closes with an 
 open discussion: where is AI operationally ready for a real deployment tod
 ay\, and where does it still need to earn trust?&lt;/span&gt;&lt;/p&gt;
END:VEVENT
END:VCALENDAR

