[time]
2020-10-08T16:26:17+02:00

[team_name]
UMinho

[team_institution]
University of Minho

[logolink]
https://drive.google.com/file/d/1mwCPknLhHidxOgcnrYs5UfQoiMUKunC0/view?usp=sharing

[system_name]


[website]


[track]
3

[reference_person]
Ivo Silva

[email]
ivo@dsi.uminho.pt

[description]
UMinho team participated in the previous years’ competitions and for this year challenge they decided to essentially improve their previous solution, upgrading some of the algorithms and solving some specific cases where the system appear to be performing not so good.
Team members have a long experience in Wi-Fi fingerprinting solutions for indoor position. However, it is necessary to consider data from other sensors available on smartphones to be able to estimate the position with a high accuracy.
The UMinho team solution is based on a Wi-Fi radio map built with the signals available in the training dataset. It uses sensor fusion to merge the results obtained from the Wi-Fi fingerprinting with data from other sensors, including accelerometers records to detect the person steps, the mobile phone 3D orientation records for heading estimation and pressure sensors for floor transition detection.

[references]