BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Lisbon
BEGIN:DAYLIGHT
DTSTART:20260329T020000
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:WEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T010000
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:WET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260319T161026Z
UID:02EF341C-4E8A-416C-91BA-5EA12DDB1C7E
DTSTART;TZID=Europe/Lisbon:20260319T103000
DTEND;TZID=Europe/Lisbon:20260319T120000
DESCRIPTION:Collecting environmental information with mobile sensors had be
 en one of the focus areas of the mobile computing community for several de
 cades. In the last five years\, however\, two major developments brought n
 ew perspectives to the field. The significant decrease in the cost and wid
 e availability of drones made them the default technology in mobile sensin
 g. At the same time\, significant developments in artificial intelligence 
 brought new tools into the toolkit of researchers allowing models that use
  predictive models to react more dynamically to changes in the environment
  and real-time results of sensing.\n\nIn this talk\, I describe an algorit
 hm that is a good example of the new generation of algorithms enabled by t
 he AI revolution. Confidence Guided Path-planning (CGP) has the goal of in
 creasing the confidence in the accuracy of the estimated model at any time
  point in the data collection process. The approach employs a local estima
 tor based on a Gaussian process regressor and takes advantage of the uncer
 tainty estimation to guide the sensor to areas of lower confidence. In an 
 experimental study comparing CGP with systematic lawnmower-type exploratio
 n and random waypoint movement\, we found that CGP achieves better scores 
 than both during most of the exploration process\, being outperformed only
  by a fully completed systematic exploration.\n\nCo-sponsored by: FCT NOVA
 \, Universidade Nova de Lisboa\n\nSpeaker(s): Damla Turgut\n\nAgenda: \n10
 :30 Damla Turgut\, AI driven dynamic path planning in mobile sensors\n\nRo
 om: Auditório\, Bldg: Biblioteca\, NOVA FCT\, Universidade Nova de Lisboa
 \, Caparica\, Lisboa\, Portugal\, 2829-516
LOCATION:Room: Auditório\, Bldg: Biblioteca\, NOVA FCT\, Universidade Nova
  de Lisboa\, Caparica\, Lisboa\, Portugal\, 2829-516
ORGANIZER:lflb@fct.unl.pt
SEQUENCE:105
SUMMARY:AI driven dynamic path planning in mobile sensors (FCT Nova)
URL;VALUE=URI:https://events.vtools.ieee.org/m/547039
X-ALT-DESC:Description: <br /><p>Collecting environmental information with 
 mobile sensors had been one of the focus areas of the mobile computing com
 munity for several decades. In the last five years\, however\, two major d
 evelopments brought new perspectives to the field. The significant decreas
 e in the cost and wide availability of drones made them the default techno
 logy in mobile sensing. At the same time\, significant developments in art
 ificial intelligence brought new tools into the toolkit of researchers all
 owing models that use predictive models to react more dynamically to chang
 es in the environment and real-time results of sensing. <br>&nbsp\;<br>In 
 this talk\, I describe an algorithm that is a good example of the new gene
 ration of algorithms enabled by the AI revolution. Confidence Guided Path-
 planning (CGP) has the goal of increasing the confidence in the accuracy o
 f the estimated model at any time point in the data collection process. Th
 e approach employs a local estimator based on a Gaussian process regressor
  and takes advantage of the uncertainty estimation to guide the sensor to 
 areas of lower confidence. In an experimental study comparing CGP with sys
 tematic lawnmower-type exploration and random waypoint movement\, we found
  that CGP achieves better scores than both during most of the exploration 
 process\, being outperformed only by a fully completed systematic explorat
 ion.</p><br /><br />Agenda: <br /><p>10:30 Damla Turgut\, <span style="fon
 t-size: 11.0pt\; font-family: 'Aptos'\,sans-serif\; mso-ascii-theme-font: 
 minor-latin\; mso-fareast-font-family: 'Times New Roman'\; mso-hansi-theme
 -font: minor-latin\; mso-bidi-font-family: Aptos\; mso-bidi-theme-font: mi
 nor-latin\; mso-font-kerning: 0pt\; mso-ligatures: none\; mso-ansi-languag
 e: #1000\; mso-fareast-language: EN-GB\; mso-bidi-language: AR-SA\;">AI dr
 iven dynamic path planning in mobile sensors</span></p>
END:VEVENT
END:VCALENDAR