BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
DTSTART:20230312T030000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230904T221732Z
UID:051D0B50-4A10-4D97-8959-4254545A17E3
DTSTART;TZID=America/Los_Angeles:20230828T103000
DTEND;TZID=America/Los_Angeles:20230828T113000
DESCRIPTION:Abstract: With the increasing demand for location-based service
 \, WiFi-based localization has become one of the most popular methods due 
 to the wide deployment of WiFi and its relatively low cost. In this talk\,
  we present a deep Gaussian process based indoor radio map construction an
 d location estimation system. Received signal strength (RSS) samples\, as 
 well earth magnetic field readings\, are used to generate accurate and fin
 e-grained radio maps with confidence intervals using deep Gaussian process
 \, while the model parameters are optimized with an offline Bayesian train
 ing method. Utilizing the maps\, an LSTM based location prediction model i
 s pre-trained with the artificial trajectory data and then fine-tuned with
  the signal measurements collected by the mobile device to be localized. O
 ur extensive experiments demonstrate the excellent performance of the prop
 osed system.\n\nRoom: 660\, Bldg: ECS\, Victoria\, British Columbia\, Cana
 da
LOCATION:Room: 660\, Bldg: ECS\, Victoria\, British Columbia\, Canada
ORGANIZER:cai@ece.uvic.ca
SEQUENCE:10
SUMMARY:Deep Gaussian process based radio map construction and localization
  
URL;VALUE=URI:https://events.vtools.ieee.org/m/370309
X-ALT-DESC:Description: <br /><p>Abstract: With the increasing demand for l
 ocation-based service\, WiFi-based localization has become one of the most
  popular methods due to the wide deployment of WiFi and its relatively low
  cost. In this talk\, we present a deep Gaussian process based indoor radi
 o map construction and location estimation system. Received signal strengt
 h (RSS) samples\, as well earth magnetic field readings\, are used to gene
 rate accurate and fine-grained radio maps with confidence intervals using 
 deep Gaussian process\, while the model parameters are optimized with an o
 ffline Bayesian training method. Utilizing the maps\, an LSTM based locati
 on prediction model is pre-trained with the artificial trajectory data and
  then fine-tuned with the signal measurements collected by the mobile devi
 ce to be localized. Our extensive experiments demonstrate the excellent pe
 rformance of the proposed system.</p>
END:VEVENT
END:VCALENDAR